MyArxiv

2025-08-19

Sound 13

☆ Evaluating Identity Leakage in Speaker De-Identification Systems ICASSP 2026

Seungmin Seo, Oleg Aulov, Afzal Godil, Kevin Mangold

Speaker de-identification aims to conceal a speaker's identity while preserving intelligibility of the underlying speech. We introduce a benchmark that quantifies residual identity leakage with three complementary error rates: equal error rate, cumulative match characteristic hit rate, and embedding-space similarity measured via canonical correlation analysis and Procrustes analysis. Evaluation results reveal that all state-of-the-art speaker de-identification systems leak identity information. The highest performing system in our evaluation performs only slightly better than random guessing, while the lowest performing system achieves a 45% hit rate within the top 50 candidates based on CMC. These findings highlight persistent privacy risks in current speaker de-identification technologies.

comment: Submitted to ICASSP 2026

☆ MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

Sonal Kumar, Šimon Sedláček, Vaibhavi Lokegaonkar, Fernando López, Wenyi Yu, Nishit Anand, Hyeonggon Ryu, Lichang Chen, Maxim Plička, Miroslav Hlaváček, William Fineas Ellingwood, Sathvik Udupa, Siyuan Hou, Allison Ferner, Sara Barahona, Cecilia Bolaños, Satish Rahi, Laura Herrera-Alarcón, Satvik Dixit, Siddhi Patil, Soham Deshmukh, Lasha Koroshinadze, Yao Liu, Leibny Paola Garcia Perera, Eleni Zanou, Themos Stafylakis, Joon Son Chung, David Harwath, Chao Zhang, Dinesh Manocha, Alicia Lozano-Diez, Santosh Kesiraju, Sreyan Ghosh, Ramani Duraiswami

Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio understanding to qualify as generally intelligent. However, evaluating auditory intelligence comprehensively remains challenging. To address this gap, we introduce MMAU-Pro, the most comprehensive and rigorously curated benchmark for assessing audio intelligence in AI systems. MMAU-Pro contains 5,305 instances, where each instance has one or more audios paired with human expert-generated question-answer pairs, spanning speech, sound, music, and their combinations. Unlike existing benchmarks, MMAU-Pro evaluates auditory intelligence across 49 unique skills and multiple complex dimensions, including long-form audio comprehension, spatial audio reasoning, multi-audio understanding, among others. All questions are meticulously designed to require deliberate multi-hop reasoning, including both multiple-choice and open-ended response formats. Importantly, audio data is sourced directly ``from the wild" rather than from existing datasets with known distributions. We evaluate 22 leading open-source and proprietary multimodal AI models, revealing significant limitations: even state-of-the-art models such as Gemini 2.5 Flash and Audio Flamingo 3 achieve only 59.2% and 51.7% accuracy, respectively, approaching random performance in multiple categories. Our extensive analysis highlights specific shortcomings and provides novel insights, offering actionable perspectives for the community to enhance future AI systems' progression toward audio general intelligence. The benchmark and code is available at https://sonalkum.github.io/mmau-pro.

☆ DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer

Yisu Liu, Chenxing Li, Wanqian Zhang, Wenfu Wang, Meng Yu, Ruibo Fu, Zheng Lin, Weiping Wang, Dong Yu

Controllable text-to-audio generation aims to synthesize audio from textual descriptions while satisfying user-specified constraints, including event types, temporal sequences, and onset and offset timestamps. This enables precise control over both the content and temporal structure of the generated audio. Despite recent progress, existing methods still face inherent trade-offs among accurate temporal localization, open-vocabulary scalability, and practical efficiency. To address these challenges, we propose DegDiT, a novel dynamic event graph-guided diffusion transformer framework for open-vocabulary controllable audio generation. DegDiT encodes the events in the description as structured dynamic graphs. The nodes in each graph are designed to represent three aspects: semantic features, temporal attributes, and inter-event connections. A graph transformer is employed to integrate these nodes and produce contextualized event embeddings that serve as guidance for the diffusion model. To ensure high-quality and diverse training data, we introduce a quality-balanced data selection pipeline that combines hierarchical event annotation with multi-criteria quality scoring, resulting in a curated dataset with semantic diversity. Furthermore, we present consensus preference optimization, facilitating audio generation through consensus among multiple reward signals. Extensive experiments on AudioCondition, DESED, and AudioTime datasets demonstrate that DegDiT achieves state-of-the-art performances across a variety of objective and subjective evaluation metrics.

☆ Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancement

Rong Chao, Wenze Ren, You-Jin Li, Kuo-Hsuan Hung, Sung-Feng Huang, Szu-Wei Fu, Wen-Huang Cheng, Yu Tsao

Recent Mamba-based models have shown promise in speech enhancement by efficiently modeling long-range temporal dependencies. However, models like Speech Enhancement Mamba (SEMamba) remain limited to single-speaker scenarios and struggle in complex multi-speaker environments such as the cocktail party problem. To overcome this, we introduce AVSEMamba, an audio-visual speech enhancement model that integrates full-face visual cues with a Mamba-based temporal backbone. By leveraging spatiotemporal visual information, AVSEMamba enables more accurate extraction of target speech in challenging conditions. Evaluated on the AVSEC-4 Challenge development and blind test sets, AVSEMamba outperforms other monaural baselines in speech intelligibility (STOI), perceptual quality (PESQ), and non-intrusive quality (UTMOS), and achieves \textbf{1st place} on the monaural leaderboard.

comment: Accepted to Interspeech 2025 Workshop

☆ End-to-End Audio-Visual Learning for Cochlear Implant Sound Coding in Noisy Environments

Meng-Ping Lin, Enoch Hsin-Ho Huang, Shao-Yi Chien, Yu Tsao

The cochlear implant (CI) is a remarkable biomedical device that successfully enables individuals with severe-to-profound hearing loss to perceive sound by converting speech into electrical stimulation signals. Despite advancements in the performance of recent CI systems, speech comprehension in noisy or reverberant conditions remains a challenge. Recent and ongoing developments in deep learning reveal promising opportunities for enhancing CI sound coding capabilities, not only through replicating traditional signal processing methods with neural networks, but also through integrating visual cues as auxiliary data for multimodal speech processing. Therefore, this paper introduces a novel noise-suppressing CI system, AVSE-ECS, which utilizes an audio-visual speech enhancement (AVSE) model as a pre-processing module for the deep-learning-based ElectrodeNet-CS (ECS) sound coding strategy. Specifically, a joint training approach is applied to model AVSE-ECS, an end-to-end CI system. Experimental results indicate that the proposed method outperforms the previous ECS strategy in noisy conditions, with improved objective speech intelligibility scores. The methods and findings in this study demonstrate the feasibility and potential of using deep learning to integrate the AVSE module into an end-to-end CI system

comment: 6 pages, 4 figures

☆ Is Transfer Learning Necessary for Violin Transcription?

Yueh-Po Peng, Ting-Kang Wang, Li Su, Vincent K. M. Cheung

Automatic music transcription (AMT) has achieved remarkable progress for instruments such as the piano, largely due to the availability of large-scale, high-quality datasets. In contrast, violin AMT remains underexplored due to limited annotated data. A common approach is to fine-tune pretrained models for other downstream tasks, but the effectiveness of such transfer remains unclear in the presence of timbral and articulatory differences. In this work, we investigate whether training from scratch on a medium-scale violin dataset can match the performance of fine-tuned piano-pretrained models. We adopt a piano transcription architecture without modification and train it on the MOSA dataset, which contains about 30 hours of aligned violin recordings. Our experiments on URMP and Bach10 show that models trained from scratch achieved competitive or even superior performance compared to fine-tuned counterparts. These findings suggest that strong violin AMT is possible without relying on pretrained piano representations, highlighting the importance of instrument-specific data collection and augmentation strategies.

♻ ☆ Can Masked Autoencoders Also Listen to Birds?

Lukas Rauch, René Heinrich, Ilyass Moummad, Alexis Joly, Bernhard Sick, Christoph Scholz

Masked Autoencoders (MAEs) learn rich semantic representations in audio classification through an efficient self-supervised reconstruction task. However, general-purpose models fail to generalize well when applied directly to fine-grained audio domains. Specifically, bird-sound classification requires distinguishing subtle inter-species differences and managing high intra-species acoustic variability, revealing the performance limitations of general-domain Audio-MAEs. This work demonstrates that bridging this domain gap domain gap requires full-pipeline adaptation, not just domain-specific pretraining data. We systematically revisit and adapt the pretraining recipe, fine-tuning methods, and frozen feature utilization to bird sounds using BirdSet, a large-scale bioacoustic dataset comparable to AudioSet. Our resulting Bird-MAE achieves new state-of-the-art results in BirdSet's multi-label classification benchmark. Additionally, we introduce the parameter-efficient prototypical probing, enhancing the utility of frozen MAE representations and closely approaching fine-tuning performance in low-resource settings. Bird-MAE's prototypical probes outperform linear probing by up to 37 percentage points in mean average precision and narrow the gap to fine-tuning across BirdSet downstream tasks. Bird-MAE also demonstrates robust few-shot capabilities with prototypical probing in our newly established few-shot benchmark on BirdSet, highlighting the potential of tailored self-supervised learning pipelines for fine-grained audio domains.

comment: accepted @TMLR: https://openreview.net/forum?id=GIBWR0Xo2J

♻ ☆ Multi-Sampling-Frequency Naturalness MOS Prediction Using Self-Supervised Learning Model with Sampling-Frequency-Independent Layer

Go Nishikawa, Wataru Nakata, Yuki Saito, Kanami Imamura, Hiroshi Saruwatari, Tomohiko Nakamura

We introduce our submission to the AudioMOS Challenge (AMC) 2025 Track 3: mean opinion score (MOS) prediction for speech with multiple sampling frequencies (SFs). Our submitted model integrates an SF-independent (SFI) convolutional layer into a self-supervised learning (SSL) model to achieve SFI speech feature extraction for MOS prediction. We present some strategies to improve the MOS prediction performance of our model: distilling knowledge from a pretrained non-SFI-SSL model and pretraining with a large-scale MOS dataset. Our submission to the AMC 2025 Track 3 ranked the first in one evaluation metric and the fourth in the final ranking. We also report the results of our ablation study to investigate essential factors of our model.

comment: 4 pages, 2 figures; Accepted to ASRU 2025 Challenge track

♻ ☆ What Matters for Bioacoustic Encoding

Marius Miron, David Robinson, Milad Alizadeh, Ellen Gilsenan-McMahon, Gagan Narula, Emmanuel Chemla, Maddie Cusimano, Felix Effenberger, Masato Hagiwara, Benjamin Hoffman, Sara Keen, Diane Kim, Jane Lawton, Jen-Yu Liu, Aza Raskin, Olivier Pietquin, Matthieu Geist

Bioacoustics, the study of sounds produced by living organisms, plays a vital role in conservation, biodiversity monitoring, and behavioral studies. Many tasks in this field, such as species, individual, and behavior classification and detection, are well-suited to machine learning. However, they often suffer from limited annotated data, highlighting the need for a general-purpose bioacoustic encoder capable of extracting useful representations for diverse downstream tasks. Such encoders have been proposed before, but are often limited in scope due to a focus on a narrow range of species (typically birds), and a reliance on a single model architecture or training paradigm. Moreover, they are usually evaluated on a small set of tasks and datasets. In this work, we present a large-scale empirical study that covers aspects of bioacoustics that are relevant to research but have previously been scarcely considered: training data diversity and scale, model architectures and training recipes, and the breadth of evaluation tasks and datasets. We obtain encoders that are state-of-the-art on the existing and proposed benchmarks. We also identify what matters for training these encoders, such that this work can be extended when more data are available or better architectures are proposed. Specifically, across 26 datasets with tasks including species classification, detection, individual ID, and vocal repertoire discovery, we find self-supervised pre-training followed by supervised post-training on a mixed bioacoustics + general-audio corpus yields the strongest in- and out-of-distribution performance. We show the importance of data diversity in both stages. To support ongoing research and application, we will release the model checkpoints.

♻ ☆ Less is More: Data Curation Matters in Scaling Speech Enhancement

Chenda Li, Wangyou Zhang, Wei Wang, Robin Scheibler, Kohei Saijo, Samuele Cornell, Yihui Fu, Marvin Sach, Zhaoheng Ni, Anurag Kumar, Tim Fingscheidt, Shinji Watanabe, Yanmin Qian

The vast majority of modern speech enhancement systems rely on data-driven neural network models. Conventionally, larger datasets are presumed to yield superior model performance, an observation empirically validated across numerous tasks in other domains. However, recent studies reveal diminishing returns when scaling speech enhancement data. We focus on a critical factor: prevalent quality issues in ``clean'' training labels within large-scale datasets. This work re-examines this phenomenon and demonstrates that, within large-scale training sets, prioritizing high-quality training data is more important than merely expanding the data volume. Experimental findings suggest that models trained on a carefully curated subset of 700 hours can outperform models trained on the 2,500-hour full dataset. This outcome highlights the crucial role of data curation in scaling speech enhancement systems effectively.

comment: Accepted by ASRU2025

♻ ☆ AxLSTMs: learning self-supervised audio representations with xLSTMs INTERSPEECH 2025

Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan

While the transformer has emerged as the eminent neural architecture, several independent lines of research have emerged to address its limitations. Recurrent neural approaches have observed a lot of renewed interest, including the extended long short-term memory (xLSTM) architecture, which reinvigorates the original LSTM. However, while xLSTMs have shown competitive performance compared to the transformer, their viability for learning self-supervised general-purpose audio representations has not been evaluated. This work proposes Audio xLSTM (AxLSTM), an approach for learning audio representations from masked spectrogram patches in a self-supervised setting. Pretrained on the AudioSet dataset, the proposed AxLSTM models outperform comparable self-supervised audio spectrogram transformer (SSAST) baselines by up to 25% in relative performance across a set of ten diverse downstream tasks while having up to 45% fewer parameters.

comment: INTERSPEECH 2025

♻ ☆ Adaptation and Optimization of Automatic Speech Recognition (ASR) for the Maritime Domain in the Field of VHF Communication

Emin Cagatay Nakilcioglu, Maximilian Reimann, Ole John

This paper introduces a multilingual automatic speech recognizer (ASR) for maritime radio communi-cation that automatically converts received VHF radio signals into text. The challenges of maritime radio communication are described at first, and the deep learning architecture of marFM consisting of audio processing techniques and machine learning algorithms is presented. Subsequently, maritime radio data of interest is analyzed and then used to evaluate the transcription performance of our ASR model for various maritime radio data.

♻ ☆ VoiceCloak: A Multi-Dimensional Defense Framework against Unauthorized Diffusion-based Voice Cloning

Qianyue Hu, Junyan Wu, Wei Lu, Xiangyang Luo

Diffusion Models (DMs) have achieved remarkable success in realistic voice cloning (VC), while they also increase the risk of malicious misuse. Existing proactive defenses designed for traditional VC models aim to disrupt the forgery process, but they have been proven incompatible with DMs due to the intricate generative mechanisms of diffusion. To bridge this gap, we introduce VoiceCloak, a multi-dimensional proactive defense framework with the goal of obfuscating speaker identity and degrading perceptual quality in potential unauthorized VC. To achieve these goals, we conduct a focused analysis to identify specific vulnerabilities within DMs, allowing VoiceCloak to disrupt the cloning process by introducing adversarial perturbations into the reference audio. Specifically, to obfuscate speaker identity, VoiceCloak first targets speaker identity by distorting representation learning embeddings to maximize identity variation, which is guided by auditory perception principles. Additionally, VoiceCloak disrupts crucial conditional guidance processes, particularly attention context, thereby preventing the alignment of vocal characteristics that are essential for achieving convincing cloning. Then, to address the second objective, VoiceCloak introduces score magnitude amplification to actively steer the reverse trajectory away from the generation of high-quality speech. Noise-guided semantic corruption is further employed to disrupt structural speech semantics captured by DMs, degrading output quality. Extensive experiments highlight VoiceCloak's outstanding defense success rate against unauthorized diffusion-based voice cloning. Audio samples of VoiceCloak are available at https://voice-cloak.github.io/VoiceCloak/.

Audio and Speech Processing 11

☆ MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

☆ Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancement

Rong Chao, Wenze Ren, You-Jin Li, Kuo-Hsuan Hung, Sung-Feng Huang, Szu-Wei Fu, Wen-Huang Cheng, Yu Tsao

comment: Accepted to Interspeech 2025 Workshop

☆ End-to-End Audio-Visual Learning for Cochlear Implant Sound Coding in Noisy Environments

Meng-Ping Lin, Enoch Hsin-Ho Huang, Shao-Yi Chien, Yu Tsao

comment: 6 pages, 4 figures

☆ Is Transfer Learning Necessary for Violin Transcription?

Yueh-Po Peng, Ting-Kang Wang, Li Su, Vincent K. M. Cheung

♻ ☆ Can Masked Autoencoders Also Listen to Birds?

Lukas Rauch, René Heinrich, Ilyass Moummad, Alexis Joly, Bernhard Sick, Christoph Scholz

comment: accepted @TMLR: https://openreview.net/forum?id=GIBWR0Xo2J

♻ ☆ Multi-Sampling-Frequency Naturalness MOS Prediction Using Self-Supervised Learning Model with Sampling-Frequency-Independent Layer

Go Nishikawa, Wataru Nakata, Yuki Saito, Kanami Imamura, Hiroshi Saruwatari, Tomohiko Nakamura

comment: 4 pages, 2 figures; Accepted to ASRU 2025 Challenge track

♻ ☆ Speech Enhancement based on cascaded two flows

Seonggyu Lee, Sein Cheong, Sangwook Han, Kihyuk Kim, Jong Won Shin

Speech enhancement (SE) based on diffusion probabilistic models has exhibited impressive performance, while requiring a relatively high number of function evaluations (NFE). Recently, SE based on flow matching has been proposed, which showed competitive performance with a small NFE. Early approaches adopted the noisy speech as the only conditioning variable. There have been other approaches which utilize speech enhanced with a predictive model as another conditioning variable and to sample an initial value, but they require a separate predictive model on top of the generative SE model. In this work, we propose to employ an identical model based on flow matching for both SE and generating enhanced speech used as an initial starting point and a conditioning variable. Experimental results showed that the proposed method required the same or fewer NFEs even with two cascaded generative methods while achieving equivalent or better performances to the previous baselines.

comment: Accepted at Interspeech 2025

♻ ☆ Less is More: Data Curation Matters in Scaling Speech Enhancement

Chenda Li, Wangyou Zhang, Wei Wang, Robin Scheibler, Kohei Saijo, Samuele Cornell, Yihui Fu, Marvin Sach, Zhaoheng Ni, Anurag Kumar, Tim Fingscheidt, Shinji Watanabe, Yanmin Qian

comment: Accepted by ASRU2025

♻ ☆ AxLSTMs: learning self-supervised audio representations with xLSTMs INTERSPEECH 2025

Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan

comment: INTERSPEECH 2025

♻ ☆ Adaptation and Optimization of Automatic Speech Recognition (ASR) for the Maritime Domain in the Field of VHF Communication

Emin Cagatay Nakilcioglu, Maximilian Reimann, Ole John

♻ ☆ VoiceCloak: A Multi-Dimensional Defense Framework against Unauthorized Diffusion-based Voice Cloning

Qianyue Hu, Junyan Wu, Wei Lu, Xiangyang Luo

Computer Vision and Pattern Recognition 150

☆ LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Chin-Yang Lin, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu

LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift, inaccurate geometry initialization, and severe memory limitations. To address these issues, we introduce LongSplat, a robust unposed 3D Gaussian Splatting framework featuring: (1) Incremental Joint Optimization that concurrently optimizes camera poses and 3D Gaussians to avoid local minima and ensure global consistency; (2) a robust Pose Estimation Module leveraging learned 3D priors; and (3) an efficient Octree Anchor Formation mechanism that converts dense point clouds into anchors based on spatial density. Extensive experiments on challenging benchmarks demonstrate that LongSplat achieves state-of-the-art results, substantially improving rendering quality, pose accuracy, and computational efficiency compared to prior approaches. Project page: https://linjohnss.github.io/longsplat/

comment: ICCV 2025. Project page: https://linjohnss.github.io/longsplat/

☆ Beyond Simple Edits: Composed Video Retrieval with Dense Modifications

Omkar Thawakar, Dmitry Demidov, Ritesh Thawkar, Rao Muhammad Anwer, Mubarak Shah, Fahad Shahbaz Khan, Salman Khan

Composed video retrieval is a challenging task that strives to retrieve a target video based on a query video and a textual description detailing specific modifications. Standard retrieval frameworks typically struggle to handle the complexity of fine-grained compositional queries and variations in temporal understanding limiting their retrieval ability in the fine-grained setting. To address this issue, we introduce a novel dataset that captures both fine-grained and composed actions across diverse video segments, enabling more detailed compositional changes in retrieved video content. The proposed dataset, named Dense-WebVid-CoVR, consists of 1.6 million samples with dense modification text that is around seven times more than its existing counterpart. We further develop a new model that integrates visual and textual information through Cross-Attention (CA) fusion using grounded text encoder, enabling precise alignment between dense query modifications and target videos. The proposed model achieves state-of-the-art results surpassing existing methods on all metrics. Notably, it achieves 71.3\% Recall@1 in visual+text setting and outperforms the state-of-the-art by 3.4\%, highlighting its efficacy in terms of leveraging detailed video descriptions and dense modification texts. Our proposed dataset, code, and model are available at :https://github.com/OmkarThawakar/BSE-CoVR

comment: Accepted to ICCV-2025

☆ Distilled-3DGS:Distilled 3D Gaussian Splatting

Lintao Xiang, Xinkai Chen, Jianhuang Lai, Guangcong Wang

3D Gaussian Splatting (3DGS) has exhibited remarkable efficacy in novel view synthesis (NVS). However, it suffers from a significant drawback: achieving high-fidelity rendering typically necessitates a large number of 3D Gaussians, resulting in substantial memory consumption and storage requirements. To address this challenge, we propose the first knowledge distillation framework for 3DGS, featuring various teacher models, including vanilla 3DGS, noise-augmented variants, and dropout-regularized versions. The outputs of these teachers are aggregated to guide the optimization of a lightweight student model. To distill the hidden geometric structure, we propose a structural similarity loss to boost the consistency of spatial geometric distributions between the student and teacher model. Through comprehensive quantitative and qualitative evaluations across diverse datasets, the proposed Distilled-3DGS, a simple yet effective framework without bells and whistles, achieves promising rendering results in both rendering quality and storage efficiency compared to state-of-the-art methods. Project page: https://distilled3dgs.github.io . Code: https://github.com/lt-xiang/Distilled-3DGS .

comment: Project page: https://distilled3dgs.github.io Code: https://github.com/lt-xiang/Distilled-3DGS

☆ GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation

Ken Deng, Yunhan Yang, Jingxiang Sun, Xihui Liu, Yebin Liu, Ding Liang, Yan-Pei Cao

Modern 3D generation methods can rapidly create shapes from sparse or single views, but their outputs often lack geometric detail due to computational constraints. We present DetailGen3D, a generative approach specifically designed to enhance these generated 3D shapes. Our key insight is to model the coarse-to-fine transformation directly through data-dependent flows in latent space, avoiding the computational overhead of large-scale 3D generative models. We introduce a token matching strategy that ensures accurate spatial correspondence during refinement, enabling local detail synthesis while preserving global structure. By carefully designing our training data to match the characteristics of synthesized coarse shapes, our method can effectively enhance shapes produced by various 3D generation and reconstruction approaches, from single-view to sparse multi-view inputs. Extensive experiments demonstrate that DetailGen3D achieves high-fidelity geometric detail synthesis while maintaining efficiency in training.

comment: https://detailgen3d.github.io/GeoSAM2/

☆ InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing

Shaoshu Yang, Zhe Kong, Feng Gao, Meng Cheng, Xiangyu Liu, Yong Zhang, Zhuoliang Kang, Wenhan Luo, Xunliang Cai, Ran He, Xiaoming Wei

Recent breakthroughs in video AIGC have ushered in a transformative era for audio-driven human animation. However, conventional video dubbing techniques remain constrained to mouth region editing, resulting in discordant facial expressions and body gestures that compromise viewer immersion. To overcome this limitation, we introduce sparse-frame video dubbing, a novel paradigm that strategically preserves reference keyframes to maintain identity, iconic gestures, and camera trajectories while enabling holistic, audio-synchronized full-body motion editing. Through critical analysis, we identify why naive image-to-video models fail in this task, particularly their inability to achieve adaptive conditioning. Addressing this, we propose InfiniteTalk, a streaming audio-driven generator designed for infinite-length long sequence dubbing. This architecture leverages temporal context frames for seamless inter-chunk transitions and incorporates a simple yet effective sampling strategy that optimizes control strength via fine-grained reference frame positioning. Comprehensive evaluations on HDTF, CelebV-HQ, and EMTD datasets demonstrate state-of-the-art performance. Quantitative metrics confirm superior visual realism, emotional coherence, and full-body motion synchronization.

comment: 11 pages, 7 figures

☆ UNICON: UNIfied CONtinual Learning for Medical Foundational Models

Mohammad Areeb Qazi, Munachiso S Nwadike, Ibrahim Almakky, Mohammad Yaqub, Numan Saeed

Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every domain, modality, or task challenging. Continual learning offers a solution by fine-tuning a model sequentially on different domains or tasks, enabling it to integrate new knowledge without requiring large datasets for each training phase. In this paper, we propose UNIfied CONtinual Learning for Medical Foundational Models (UNICON), a framework that enables the seamless adaptation of foundation models to diverse domains, tasks, and modalities. Unlike conventional adaptation methods that treat these changes in isolation, UNICON provides a unified, perpetually expandable framework. Through careful integration, we show that foundation models can dynamically expand across imaging modalities, anatomical regions, and clinical objectives without catastrophic forgetting or task interference. Empirically, we validate our approach by adapting a chest CT foundation model initially trained for classification to a prognosis and segmentation task. Our results show improved performance across both additional tasks. Furthermore, we continually incorporated PET scans and achieved a 5\% improvement in Dice score compared to respective baselines. These findings establish that foundation models are not inherently constrained to their initial training scope but can evolve, paving the way toward generalist AI models for medical imaging.

comment: 10 pages, 1 figure

☆ Backdooring Self-Supervised Contrastive Learning by Noisy Alignment

Tuo Chen, Jie Gui, Minjing Dong, Ju Jia, Lanting Fang, Jian Liu

Self-supervised contrastive learning (CL) effectively learns transferable representations from unlabeled data containing images or image-text pairs but suffers vulnerability to data poisoning backdoor attacks (DPCLs). An adversary can inject poisoned images into pretraining datasets, causing compromised CL encoders to exhibit targeted misbehavior in downstream tasks. Existing DPCLs, however, achieve limited efficacy due to their dependence on fragile implicit co-occurrence between backdoor and target object and inadequate suppression of discriminative features in backdoored images. We propose Noisy Alignment (NA), a DPCL method that explicitly suppresses noise components in poisoned images. Inspired by powerful training-controllable CL attacks, we identify and extract the critical objective of noisy alignment, adapting it effectively into data-poisoning scenarios. Our method implements noisy alignment by strategically manipulating contrastive learning's random cropping mechanism, formulating this process as an image layout optimization problem with theoretically derived optimal parameters. The resulting method is simple yet effective, achieving state-of-the-art performance compared to existing DPCLs, while maintaining clean-data accuracy. Furthermore, Noisy Alignment demonstrates robustness against common backdoor defenses. Codes can be found at https://github.com/jsrdcht/Noisy-Alignment.

comment: Accepted by ICCV 2025

☆ Online 3D Gaussian Splatting Modeling with Novel View Selection

Byeonggwon Lee, Junkyu Park, Khang Truong Giang, Soohwan Song

This study addresses the challenge of generating online 3D Gaussian Splatting (3DGS) models from RGB-only frames. Previous studies have employed dense SLAM techniques to estimate 3D scenes from keyframes for 3DGS model construction. However, these methods are limited by their reliance solely on keyframes, which are insufficient to capture an entire scene, resulting in incomplete reconstructions. Moreover, building a generalizable model requires incorporating frames from diverse viewpoints to achieve broader scene coverage. However, online processing restricts the use of many frames or extensive training iterations. Therefore, we propose a novel method for high-quality 3DGS modeling that improves model completeness through adaptive view selection. By analyzing reconstruction quality online, our approach selects optimal non-keyframes for additional training. By integrating both keyframes and selected non-keyframes, the method refines incomplete regions from diverse viewpoints, significantly enhancing completeness. We also present a framework that incorporates an online multi-view stereo approach, ensuring consistency in 3D information throughout the 3DGS modeling process. Experimental results demonstrate that our method outperforms state-of-the-art methods, delivering exceptional performance in complex outdoor scenes.

☆ ResPlan: A Large-Scale Vector-Graph Dataset of 17,000 Residential Floor Plans

Mohamed Abouagour, Eleftherios Garyfallidis

We introduce ResPlan, a large-scale dataset of 17,000 detailed, structurally rich, and realistic residential floor plans, created to advance spatial AI research. Each plan includes precise annotations of architectural elements (walls, doors, windows, balconies) and functional spaces (such as kitchens, bedrooms, and bathrooms). ResPlan addresses key limitations of existing datasets such as RPLAN (Wu et al., 2019) and MSD (van Engelenburg et al., 2024) by offering enhanced visual fidelity and greater structural diversity, reflecting realistic and non-idealized residential layouts. Designed as a versatile, general-purpose resource, ResPlan supports a wide range of applications including robotics, reinforcement learning, generative AI, virtual and augmented reality, simulations, and game development. Plans are provided in both geometric and graph-based formats, enabling direct integration into simulation engines and fast 3D conversion. A key contribution is an open-source pipeline for geometry cleaning, alignment, and annotation refinement. Additionally, ResPlan includes structured representations of room connectivity, supporting graph-based spatial reasoning tasks. Finally, we present comparative analyses with existing benchmarks and outline several open benchmark tasks enabled by ResPlan. Ultimately, ResPlan offers a significant advance in scale, realism, and usability, providing a robust foundation for developing and benchmarking next-generation spatial intelligence systems.

comment: 18 pages, 3 figures, 4 tables

☆ Self-Supervised Sparse Sensor Fusion for Long Range Perception

Edoardo Palladin, Samuel Brucker, Filippo Ghilotti, Praveen Narayanan, Mario Bijelic, Felix Heide

Outside of urban hubs, autonomous cars and trucks have to master driving on intercity highways. Safe, long-distance highway travel at speeds exceeding 100 km/h demands perception distances of at least 250 m, which is about five times the 50-100m typically addressed in city driving, to allow sufficient planning and braking margins. Increasing the perception ranges also allows to extend autonomy from light two-ton passenger vehicles to large-scale forty-ton trucks, which need a longer planning horizon due to their high inertia. However, most existing perception approaches focus on shorter ranges and rely on Bird's Eye View (BEV) representations, which incur quadratic increases in memory and compute costs as distance grows. To overcome this limitation, we built on top of a sparse representation and introduced an efficient 3D encoding of multi-modal and temporal features, along with a novel self-supervised pre-training scheme that enables large-scale learning from unlabeled camera-LiDAR data. Our approach extends perception distances to 250 meters and achieves an 26.6% improvement in mAP in object detection and a decrease of 30.5% in Chamfer Distance in LiDAR forecasting compared to existing methods, reaching distances up to 250 meters. Project Page: https://light.princeton.edu/lrs4fusion/

☆ Physics-Based 3D Simulation for Synthetic Data Generation and Failure Analysis in Packaging Stability Assessment

Samuel Seligardi, Pietro Musoni, Eleonora Iotti, Gianluca Contesso, Alessandro Dal Palù

The design and analysis of pallet setups are essential for ensuring safety of packages transportation. With rising demands in the logistics sector, the development of automated systems utilizing advanced technologies has become increasingly crucial. Moreover, the widespread use of plastic wrapping has motivated researchers to investigate eco-friendly alternatives that still adhere to safety standards. We present a fully controllable and accurate physical simulation system capable of replicating the behavior of moving pallets. It features a 3D graphics-based virtual environment that supports a wide range of configurations, including variable package layouts, different wrapping materials, and diverse dynamic conditions. This innovative approach reduces the need for physical testing, cutting costs and environmental impact while improving measurement accuracy for analyzing pallet dynamics. Additionally, we train a deep neural network to evaluate the rendered videos generated by our simulator, as a crash-test predictor for pallet configurations, further enhancing the system's utility in safety analysis.

☆ OmViD: Omni-supervised active learning for video action detection

Aayush Rana, Akash Kumar, Vibhav Vineet, Yogesh S Rawat

Video action detection requires dense spatio-temporal annotations, which are both challenging and expensive to obtain. However, real-world videos often vary in difficulty and may not require the same level of annotation. This paper analyzes the appropriate annotation types for each sample and their impact on spatio-temporal video action detection. It focuses on two key aspects: 1) how to obtain varying levels of annotation for videos, and 2) how to learn action detection from different annotation types. The study explores video-level tags, points, scribbles, bounding boxes, and pixel-level masks. First, a simple active learning strategy is proposed to estimate the necessary annotation type for each video. Then, a novel spatio-temporal 3D-superpixel approach is introduced to generate pseudo-labels from these annotations, enabling effective training. The approach is validated on UCF101-24 and JHMDB-21 datasets, significantly cutting annotation costs with minimal performance loss.

comment: ICCVW'25

☆ ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving

Xianda Guo, Ruijun Zhang, Yiqun Duan, Ruilin Wang, Keyuan Zhou, Wenzhao Zheng, Wenke Huang, Gangwei Xu, Mike Horton, Yuan Si, Hao Zhao, Long Chen

Depth estimation is a fundamental task for 3D scene understanding in autonomous driving, robotics, and augmented reality. Existing depth datasets, such as KITTI, nuScenes, and DDAD, have advanced the field but suffer from limitations in diversity and scalability. As benchmark performance on these datasets approaches saturation, there is an increasing need for a new generation of large-scale, diverse, and cost-efficient datasets to support the era of foundation models and multi-modal learning. To address these challenges, we introduce a large-scale, diverse, frame-wise continuous dataset for depth estimation in dynamic outdoor driving environments, comprising 20K video frames to evaluate existing methods. Our lightweight acquisition pipeline ensures broad scene coverage at low cost, while sparse yet statistically sufficient ground truth enables robust training. Compared to existing datasets, ours presents greater diversity in driving scenarios and lower depth density, creating new challenges for generalization. Benchmark experiments with standard monocular depth estimation models validate the dataset's utility and highlight substantial performance gaps in challenging conditions, establishing a new platform for advancing depth estimation research.

☆ RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation

Tianyi Niu, Jaemin Cho, Elias Stengel-Eskin, Mohit Bansal

We investigate to what extent Multimodal Large Language Models (MLLMs) can accurately identify the orientation of input images rotated 0{\deg}, 90{\deg}, 180{\deg}, and 270{\deg}. This task demands robust visual reasoning capabilities to detect rotational cues and contextualize spatial relationships within images, regardless of their orientation. To evaluate MLLMs on these abilities, we introduce RotBench -- a 350-image manually-filtered benchmark comprising lifestyle, portrait, and landscape images. Despite the relatively simple nature of this task, we show that several state-of-the-art open and proprietary MLLMs, including GPT-5, o3, and Gemini-2.5-Pro, do not reliably identify rotation in input images. Providing models with auxiliary information -- including captions, depth maps, and more -- or using chain-of-thought prompting offers only small and inconsistent improvements. Our results indicate that most models are able to reliably identify right-side-up (0{\deg}) images, while certain models are able to identify upside-down (180{\deg}) images. None can reliably distinguish between 90{\deg} and 270{\deg}. Simultaneously showing the image rotated in different orientations leads to moderate performance gains for reasoning models, while a modified setup using voting improves the performance of weaker models. We further show that fine-tuning does not improve models' ability to distinguish 90{\deg} and 270{\deg} rotations, despite substantially improving the identification of 180{\deg} images. Together, these results reveal a significant gap between MLLMs' spatial reasoning capabilities and human perception in identifying rotation.

comment: 20 pages. Code and data: https://github.com/tianyiniu/RotBench

☆ Augmenting cobots for sheet-metal SMEs with 3D object recognition and localisation

Martijn Cramer, Yanming Wu, David De Schepper, Eric Demeester

Due to high-mix-low-volume production, sheet-metal workshops today are challenged by small series and varying orders. As standard automation solutions tend to fall short, SMEs resort to repetitive manual labour impacting production costs and leading to tech-skilled workforces not being used to their full potential. The COOCK+ ROBUST project aims to transform cobots into mobile and reconfigurable production assistants by integrating existing technologies, including 3D object recognition and localisation. This article explores both the opportunities and challenges of enhancing cobotic systems with these technologies in an industrial setting, outlining the key steps involved in the process. Additionally, insights from a past project, carried out by the ACRO research unit in collaboration with an industrial partner, serves as a concrete implementation example throughout.

comment: 13 pages, 25 figures

☆ ViT-FIQA: Assessing Face Image Quality using Vision Transformers

Andrea Atzori, Fadi Boutros, Naser Damer

Face Image Quality Assessment (FIQA) aims to predict the utility of a face image for face recognition (FR) systems. State-of-the-art FIQA methods mainly rely on convolutional neural networks (CNNs), leaving the potential of Vision Transformer (ViT) architectures underexplored. This work proposes ViT-FIQA, a novel approach that extends standard ViT backbones, originally optimized for FR, through a learnable quality token designed to predict a scalar utility score for any given face image. The learnable quality token is concatenated with the standard image patch tokens, and the whole sequence is processed via global self-attention by the ViT encoders to aggregate contextual information across all patches. At the output of the backbone, ViT-FIQA branches into two heads: (1) the patch tokens are passed through a fully connected layer to learn discriminative face representations via a margin-penalty softmax loss, and (2) the quality token is fed into a regression head to learn to predict the face sample's utility. Extensive experiments on challenging benchmarks and several FR models, including both CNN- and ViT-based architectures, demonstrate that ViT-FIQA consistently achieves top-tier performance. These results underscore the effectiveness of transformer-based architectures in modeling face image utility and highlight the potential of ViTs as a scalable foundation for future FIQA research https://cutt.ly/irHlzXUC.

comment: Accepted at the IEEE/CVF International Conference on Computer Vision Workshops 2025 (ICCVW 2025)

☆ Real-Time, Population-Based Reconstruction of 3D Bone Models via Very-Low-Dose Protocols

Yiqun Lin, Haoran Sun, Yongqing Li, Rabia Aslam, Lung Fung Tse, Tiange Cheng, Chun Sing Chui, Wing Fung Yau, Victorine R. Le Meur, Meruyert Amangeldy, Kiho Cho, Yinyu Ye, James Zou, Wei Zhao, Xiaomeng Li

Patient-specific bone models are essential for designing surgical guides and preoperative planning, as they enable the visualization of intricate anatomical structures. However, traditional CT-based approaches for creating bone models are limited to preoperative use due to the low flexibility and high radiation exposure of CT and time-consuming manual delineation. Here, we introduce Semi-Supervised Reconstruction with Knowledge Distillation (SSR-KD), a fast and accurate AI framework to reconstruct high-quality bone models from biplanar X-rays in 30 seconds, with an average error under 1.0 mm, eliminating the dependence on CT and manual work. Additionally, high tibial osteotomy simulation was performed by experts on reconstructed bone models, demonstrating that bone models reconstructed from biplanar X-rays have comparable clinical applicability to those annotated from CT. Overall, our approach accelerates the process, reduces radiation exposure, enables intraoperative guidance, and significantly improves the practicality of bone models, offering transformative applications in orthopedics.

☆ MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models

Jiacheng Ruan, Dan Jiang, Xian Gao, Ting Liu, Yuzhuo Fu, Yangyang Kang

Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously refined and improved. In this process, benchmarks in the scientific domain have played an important role in assessing the reasoning capabilities of MLLMs. However, existing benchmarks still face three key challenges: 1) Insufficient evaluation of models' reasoning abilities in multilingual scenarios; 2) Inadequate assessment of MLLMs' comprehensive modality coverage; 3) Lack of fine-grained annotation of scientific knowledge points. To address these gaps, we propose MME-SCI, a comprehensive and challenging benchmark. We carefully collected 1,019 high-quality question-answer pairs, which involve 3 distinct evaluation modes. These pairs cover four subjects, namely mathematics, physics, chemistry, and biology, and support five languages: Chinese, English, French, Spanish, and Japanese. We conducted extensive experiments on 16 open-source models and 4 closed-source models, and the results demonstrate that MME-SCI is widely challenging for existing MLLMs. For instance, under the Image-only evaluation mode, o4-mini achieved accuracy of only 52.11%, 24.73%, 36.57%, and 29.80% in mathematics, physics, chemistry, and biology, respectively, indicating a significantly higher difficulty level compared to existing benchmarks. More importantly, using MME-SCI's multilingual and fine-grained knowledge attributes, we analyzed existing models' performance in depth and identified their weaknesses in specific domains. The Data and Evaluation Code are available at https://github.com/JCruan519/MME-SCI.

comment: 9 pages, 6 figures, work in progress

☆ MMIS-Net for Retinal Fluid Segmentation and Detection

Nchongmaje Ndipenocha, Alina Mirona, Kezhi Wanga, Yongmin Li

Purpose: Deep learning methods have shown promising results in the segmentation, and detection of diseases in medical images. However, most methods are trained and tested on data from a single source, modality, organ, or disease type, overlooking the combined potential of other available annotated data. Numerous small annotated medical image datasets from various modalities, organs, and diseases are publicly available. In this work, we aim to leverage the synergistic potential of these datasets to improve performance on unseen data. Approach: To this end, we propose a novel algorithm called MMIS-Net (MultiModal Medical Image Segmentation Network), which features Similarity Fusion blocks that utilize supervision and pixel-wise similarity knowledge selection for feature map fusion. Additionally, to address inconsistent class definitions and label contradictions, we created a one-hot label space to handle classes absent in one dataset but annotated in another. MMIS-Net was trained on 10 datasets encompassing 19 organs across 2 modalities to build a single model. Results: The algorithm was evaluated on the RETOUCH grand challenge hidden test set, outperforming large foundation models for medical image segmentation and other state-of-the-art algorithms. We achieved the best mean Dice score of 0.83 and an absolute volume difference of 0.035 for the fluids segmentation task, as well as a perfect Area Under the Curve of 1 for the fluid detection task. Conclusion: The quantitative results highlight the effectiveness of our proposed model due to the incorporation of Similarity Fusion blocks into the network's backbone for supervision and similarity knowledge selection, and the use of a one-hot label space to address label class inconsistencies and contradictions.

☆ DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts ACM MM 2025

Ziang Wang, Xiaoqin Wang, Dingyi Wang, Qiang Li, Shushan Qiao

Image degradation caused by complex lighting conditions such as low-light and backlit scenarios is commonly encountered in real-world environments, significantly affecting image quality and downstream vision tasks. Most existing methods focus on a single type of illumination degradation and lack the ability to handle diverse lighting conditions in a unified manner. To address this issue, we propose a dual-illumination enhancement framework called DIME-Net. The core of our method is a Mixture-of-Experts illumination estimator module, where a sparse gating mechanism adaptively selects suitable S-curve expert networks based on the illumination characteristics of the input image. By integrating Retinex theory, this module effectively performs enhancement tailored to both low-light and backlit images. To further correct illumination-induced artifacts and color distortions, we design a damage restoration module equipped with Illumination-Aware Cross Attention and Sequential-State Global Attention mechanisms. In addition, we construct a hybrid illumination dataset, MixBL, by integrating existing datasets, allowing our model to achieve robust illumination adaptability through a single training process. Experimental results show that DIME-Net achieves competitive performance on both synthetic and real-world low-light and backlit datasets without any retraining. These results demonstrate its generalization ability and potential for practical multimedia applications under diverse and complex illumination conditions.

comment: Accepted at ACM Multimedia 2025 (ACM MM 2025)

☆ PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis

Chunji Lv, Zequn Chen, Donglin Di, Weinan Zhang, Hao Li, Wei Chen, Changsheng Li

While physics-grounded 3D motion synthesis has seen significant progress, current methods face critical limitations. They typically rely on pre-reconstructed 3D Gaussian Splatting (3DGS) representations, while physics integration depends on either inflexible, manually defined physical attributes or unstable, optimization-heavy guidance from video models. To overcome these challenges, we introduce PhysGM, a feed-forward framework that jointly predicts a 3D Gaussian representation and its physical properties from a single image, enabling immediate, physical simulation and high-fidelity 4D rendering. We first establish a base model by jointly optimizing for Gaussian reconstruction and probabilistic physics prediction. The model is then refined with physically plausible reference videos to enhance both rendering fidelity and physics prediction accuracy. We adopt the Direct Preference Optimization (DPO) to align its simulations with reference videos, circumventing Score Distillation Sampling (SDS) optimization which needs back-propagating gradients through the complex differentiable simulation and rasterization. To facilitate the training, we introduce a new dataset PhysAssets of over 24,000 3D assets, annotated with physical properties and corresponding guiding videos. Experimental results demonstrate that our method effectively generates high-fidelity 4D simulations from a single image in one minute. This represents a significant speedup over prior works while delivering realistic rendering results. Our project page is at:https://hihixiaolv.github.io/PhysGM.github.io/

☆ Learning to See Through Flare

Xiaopeng Peng, Heath Gemar, Erin Fleet, Kyle Novak, Abbie Watnik, Grover Swartzlander

Machine vision systems are susceptible to laser flare, where unwanted intense laser illumination blinds and distorts its perception of the environment through oversaturation or permanent damage to sensor pixels. We introduce NeuSee, the first computational imaging framework for high-fidelity sensor protection across the full visible spectrum. It jointly learns a neural representation of a diffractive optical element (DOE) and a frequency-space Mamba-GAN network for image restoration. NeuSee system is adversarially trained end-to-end on 100K unique images to suppress the peak laser irradiance as high as $10^6$ times the sensor saturation threshold $I_{\textrm{sat}}$, the point at which camera sensors may experience damage without the DOE. Our system leverages heterogeneous data and model parallelism for distributed computing, integrating hyperspectral information and multiple neural networks for realistic simulation and image restoration. NeuSee takes into account open-world scenes with dynamically varying laser wavelengths, intensities, and positions, as well as lens flare effects, unknown ambient lighting conditions, and sensor noises. It outperforms other learned DOEs, achieving full-spectrum imaging and laser suppression for the first time, with a 10.1\% improvement in restored image quality.

comment: accepted by ICCVW 2025

☆ Multimodal Data Storage and Retrieval for Embodied AI: A Survey

Yihao Lu, Hao Tang

Embodied AI (EAI) agents continuously interact with the physical world, generating vast, heterogeneous multimodal data streams that traditional management systems are ill-equipped to handle. In this survey, we first systematically evaluate five storage architectures (Graph Databases, Multi-Model Databases, Data Lakes, Vector Databases, and Time-Series Databases), focusing on their suitability for addressing EAI's core requirements, including physical grounding, low-latency access, and dynamic scalability. We then analyze five retrieval paradigms (Fusion Strategy-Based Retrieval, Representation Alignment-Based Retrieval, Graph-Structure-Based Retrieval, Generation Model-Based Retrieval, and Efficient Retrieval-Based Optimization), revealing a fundamental tension between achieving long-term semantic coherence and maintaining real-time responsiveness. Based on this comprehensive analysis, we identify key bottlenecks, spanning from the foundational Physical Grounding Gap to systemic challenges in cross-modal integration, dynamic adaptation, and open-world generalization. Finally, we outline a forward-looking research agenda encompassing physics-aware data models, adaptive storage-retrieval co-optimization, and standardized benchmarking, to guide future research toward principled data management solutions for EAI. Our survey is based on a comprehensive review of more than 180 related studies, providing a rigorous roadmap for designing the robust, high-performance data management frameworks essential for the next generation of autonomous embodied systems.

☆ SCRNet: Spatial-Channel Regulation Network for Medical Ultrasound Image Segmentation

Weixin Xu, Ziliang Wang

Medical ultrasound image segmentation presents a formidable challenge in the realm of computer vision. Traditional approaches rely on Convolutional Neural Networks (CNNs) and Transformer-based methods to address the intricacies of medical image segmentation. Nevertheless, inherent limitations persist, as CNN-based methods tend to disregard long-range dependencies, while Transformer-based methods may overlook local contextual information. To address these deficiencies, we propose a novel Feature Aggregation Module (FAM) designed to process two input features from the preceding layer. These features are seamlessly directed into two branches of the Convolution and Cross-Attention Parallel Module (CCAPM) to endow them with different roles in each of the two branches to help establish a strong connection between the two input features. This strategy enables our module to focus concurrently on both long-range dependencies and local contextual information by judiciously merging convolution operations with cross-attention mechanisms. Moreover, by integrating FAM within our proposed Spatial-Channel Regulation Module (SCRM), the ability to discern salient regions and informative features warranting increased attention is enhanced. Furthermore, by incorporating the SCRM into the encoder block of the UNet architecture, we introduce a novel framework dubbed Spatial-Channel Regulation Network (SCRNet). The results of our extensive experiments demonstrate the superiority of SCRNet, which consistently achieves state-of-the-art (SOTA) performance compared to existing methods.

comment: 8 pagegs

☆ Forecasting Smog Events Using ConvLSTM: A Spatio-Temporal Approach for Aerosol Index Prediction in South Asia

Taimur Khan

The South Asian Smog refers to the recurring annual air pollution events marked by high contaminant levels, reduced visibility, and significant socio-economic impacts, primarily affecting the Indo-Gangetic Plains (IGP) from November to February. Over the past decade, increased air pollution sources such as crop residue burning, motor vehicles, and changing weather patterns have intensified these smog events. However, real-time forecasting systems for increased particulate matter concentrations are still not established at regional scale. The Aerosol Index, closely tied to smog formation and a key component in calculating the Air Quality Index (AQI), reflects particulate matter concentrations. This study forecasts aerosol events using Sentinel-5P air constituent data (2019-2023) and a Convolutional Long-Short Term Memory (ConvLSTM) neural network, which captures spatial and temporal correlations more effectively than previous models. Using the Ultraviolet (UV) Aerosol Index at 340-380 nm as the predictor, results show the Aerosol Index can be forecasted at five-day intervals with a Mean Squared Error of ~0.0018, loss of ~0.3995, and Structural Similarity Index of ~0.74. While effective, the model can be improved by integrating additional data and refining its architecture.

☆ In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging

Valentina Corbetta, Floris Six Dijkstra, Regina Beets-Tan, Hoel Kervadec, Kristoffer Wickstrøm, Wilson Silva

Deep learning models in medical imaging often achieve strong in-distribution performance but struggle to generalise under distribution shifts, frequently relying on spurious correlations instead of clinically meaningful features. We introduce LCRReg, a novel regularisation approach that leverages Latent Concept Representations (LCRs) (e.g., Concept Activation Vectors (CAVs)) to guide models toward semantically grounded representations. LCRReg requires no concept labels in the main training set and instead uses a small auxiliary dataset to synthesise high-quality, disentangled concept examples. We extract LCRs for predefined relevant features, and incorporate a regularisation term that guides a Convolutional Neural Network (CNN) to activate within latent subspaces associated with those concepts. We evaluate LCRReg across synthetic and real-world medical tasks. On a controlled toy dataset, it significantly improves robustness to injected spurious correlations and remains effective even in multi-concept and multiclass settings. On the diabetic retinopathy binary classification task, LCRReg enhances performance under both synthetic spurious perturbations and out-of-distribution (OOD) generalisation. Compared to baselines, including multitask learning, linear probing, and post-hoc concept-based models, LCRReg offers a lightweight, architecture-agnostic strategy for improving model robustness without requiring dense concept supervision. Code is available at the following link: https://github.com/Trustworthy-AI-UU-NKI/lcr\_regularization

comment: 13 pages, 13 figures, 2 tables, accepted at PHAROS-AFE-AIMI Workshop in conjunction with the International Conference on Computer Vision (ICCV), 2025. This is the submitted manuscript with added link to the github repo, funding acknowledgments and author names and affiliations, and a correction to numbers in Table 1. Final version not published yet

☆ RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection

Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Pani Paudel, Luc Van Gool

Incremental Learning (IL) trains models sequentially on new data without full retraining, offering privacy, efficiency, and scalability. IL must balance adaptability to new data with retention of old knowledge. However, evaluations often rely on synthetic, simplified benchmarks, obscuring real-world IL performance. To address this, we introduce two Realistic Incremental Object Detection Benchmarks (RICO): Domain RICO (D-RICO) features domain shifts with a fixed class set, and Expanding-Classes RICO (EC-RICO) integrates new domains and classes per IL step. Built from 14 diverse datasets covering real and synthetic domains, varying conditions (e.g., weather, time of day), camera sensors, perspectives, and labeling policies, both benchmarks capture challenges absent in existing evaluations. Our experiments show that all IL methods underperform in adaptability and retention, while replaying a small amount of previous data already outperforms all methods. However, individual training on the data remains superior. We heuristically attribute this gap to weak teachers in distillation, single models' inability to manage diverse tasks, and insufficient plasticity. Our code will be made publicly available.

comment: Accepted to ICCV Workshops 2025

☆ A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler

Wenxuan Zhang, Shuai Li, Xinyi Wang, Yu Sun, Hongyu Kang, Pui Yuk Chryste Wan, Yong-Ping Zheng, Sai-Kit Lam

The Circle of Willis (CoW), vital for ensuring consistent blood flow to the brain, is closely linked to ischemic stroke. Accurate assessment of the CoW is important for identifying individuals at risk and guiding appropriate clinical management. Among existing imaging methods, Transcranial Color-coded Doppler (TCCD) offers unique advantages due to its radiation-free nature, affordability, and accessibility. However, reliable TCCD assessments depend heavily on operator expertise for identifying anatomical landmarks and performing accurate angle correction, which limits its widespread adoption. To address this challenge, we propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries. No prior studies have explored AI-driven cerebrovascular segmentation using TCCD. In this work, we introduce a novel Attention-Augmented Wavelet YOLO (AAW-YOLO) network tailored for TCCD data, designed to provide real-time guidance for brain vessel segmentation in the CoW. We prospectively collected TCCD data comprising 738 annotated frames and 3,419 labeled artery instances to establish a high-quality dataset for model training and evaluation. The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels, achieving an average Dice score of 0.901, IoU of 0.823, precision of 0.882, recall of 0.926, and mAP of 0.953, with a per-frame inference speed of 14.199 ms. This system offers a practical solution to reduce reliance on operator experience in TCCD-based cerebrovascular screening, with potential applications in routine clinical workflows and resource-constrained settings. Future research will explore bilateral modeling and larger-scale validation.

☆ A Comprehensive Re-Evaluation of Biometric Modality Properties in the Modern Era

Rouqaiah Al-Refai, Pankaja Priya Ramasamy, Ragini Ramesh, Patricia Arias-Cabarcos, Philipp Terhörst

The rapid advancement of authentication systems and their increasing reliance on biometrics for faster and more accurate user verification experience, highlight the critical need for a reliable framework to evaluate the suitability of biometric modalities for specific applications. Currently, the most widely known evaluation framework is a comparative table from 1998, which no longer adequately captures recent technological developments or emerging vulnerabilities in biometric systems. To address these challenges, this work revisits the evaluation of biometric modalities through an expert survey involving 24 biometric specialists. The findings indicate substantial shifts in property ratings across modalities. For example, face recognition, shows improved ratings due to technological progress, while fingerprint, shows decreased reliability because of emerging vulnerabilities and attacks. Further analysis of expert agreement levels across rated properties highlighted the consistency of the provided evaluations and ensured the reliability of the ratings. Finally, expert assessments are compared with dataset-level uncertainty across 55 biometric datasets, revealing strong alignment in most modalities and underscoring the importance of integrating empirical evidence with expert insight. Moreover, the identified expert disagreements reveal key open challenges and help guide future research toward resolving them.

☆ RED.AI Id-Pattern: First Results of Stone Deterioration Patterns with Multi-Agent Systems

Daniele Corradetti, José Delgado Rodrigues

The Id-Pattern system within the RED.AI project (Reabilita\c{c}\~ao Estrutural Digital atrav\'es da AI) consists of an agentic system designed to assist in the identification of stone deterioration patterns. Traditional methodologies, based on direct observation by expert teams, are accurate but costly in terms of time and resources. The system developed here introduces and evaluates a multi-agent artificial intelligence (AI) system, designed to simulate collaboration between experts and automate the diagnosis of stone pathologies from visual evidence. The approach is based on a cognitive architecture that orchestrates a team of specialized AI agents which, in this specific case, are limited to five: a lithologist, a pathologist, an environmental expert, a conservator-restorer, and a diagnostic coordinator. To evaluate the system we selected 28 difficult images involving multiple deterioration patterns. Our first results showed a huge boost on all metrics of our system compared to the foundational model.

comment: 11 pages, 1 figure, 1 table. Contribution for REEACH 2025 Symposium

☆ SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation

Paul Grimal, Michaël Soumm, Hervé Le Borgne, Olivier Ferret, Akihiro Sugimoto

State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts, leading to missing critical elements or unintended blending of distinct concepts. We propose a novel approach that learns a high-success-rate distribution conditioned on a target prompt, ensuring that generated images faithfully reflect the corresponding prompts. Our method explicitly models the signal component during the denoising process, offering fine-grained control that mitigates over-optimization and out-of-distribution artifacts. Moreover, our framework is training-free and seamlessly integrates with both existing diffusion and flow matching architectures. It also supports additional conditioning modalities -- such as bounding boxes -- for enhanced spatial alignment. Extensive experiments demonstrate that our approach outperforms current state-of-the-art methods. The code is available at https://github.com/grimalPaul/gsn-factory.

☆ Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction

Niklas Bubeck, Suprosanna Shit, Chen Chen, Can Zhao, Pengfei Guo, Dong Yang, Georg Zitzlsberger, Daguang Xu, Bernhard Kainz, Daniel Rueckert, Jiazhen Pan

Cardiac Magnetic Resonance (CMR) imaging is a critical tool for diagnosing and managing cardiovascular disease, yet its utility is often limited by the sparse acquisition of 2D short-axis slices, resulting in incomplete volumetric information. Accurate 3D reconstruction from these sparse slices is essential for comprehensive cardiac assessment, but existing methods face challenges, including reliance on predefined interpolation schemes (e.g., linear or spherical), computational inefficiency, and dependence on additional semantic inputs such as segmentation labels or motion data. To address these limitations, we propose a novel \textbf{Ca}rdiac \textbf{L}atent \textbf{I}nterpolation \textbf{D}iffusion (CaLID) framework that introduces three key innovations. First, we present a data-driven interpolation scheme based on diffusion models, which can capture complex, non-linear relationships between sparse slices and improves reconstruction accuracy. Second, we design a computationally efficient method that operates in the latent space and speeds up 3D whole-heart upsampling time by a factor of 24, reducing computational overhead compared to previous methods. Third, with only sparse 2D CMR images as input, our method achieves SOTA performance against baseline methods, eliminating the need for auxiliary input such as morphological guidance, thus simplifying workflows. We further extend our method to 2D+T data, enabling the effective modeling of spatiotemporal dynamics and ensuring temporal coherence. Extensive volumetric evaluations and downstream segmentation tasks demonstrate that CaLID achieves superior reconstruction quality and efficiency. By addressing the fundamental limitations of existing approaches, our framework advances the state of the art for spatio and spatiotemporal whole-heart reconstruction, offering a robust and clinically practical solution for cardiovascular imaging.

☆ Self-Aware Adaptive Alignment: Enabling Accurate Perception for Intelligent Transportation Systems

Tong Xiang, Hongxia Zhao, Fenghua Zhu, Yuanyuan Chen, Yisheng Lv

Achieving top-notch performance in Intelligent Transportation detection is a critical research area. However, many challenges still need to be addressed when it comes to detecting in a cross-domain scenario. In this paper, we propose a Self-Aware Adaptive Alignment (SA3), by leveraging an efficient alignment mechanism and recognition strategy. Our proposed method employs a specified attention-based alignment module trained on source and target domain datasets to guide the image-level features alignment process, enabling the local-global adaptive alignment between the source domain and target domain. Features from both domains, whose channel importance is re-weighted, are fed into the region proposal network, which facilitates the acquisition of salient region features. Also, we introduce an instance-to-image level alignment module specific to the target domain to adaptively mitigate the domain gap. To evaluate the proposed method, extensive experiments have been conducted on popular cross-domain object detection benchmarks. Experimental results show that SA3 achieves superior results to the previous state-of-the-art methods.

comment: Domain adaptation, Virtual Reality, Object Detection

☆ Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering

Diaa Addeen Abuhani, Marco Seccaroni, Martina Mazzarello, Imran Zualkernan, Fabio Duarte, Carlo Ratti

Urban tree biodiversity is critical for climate resilience, ecological stability, and livability in cities, yet most municipalities lack detailed knowledge of their canopies. Field-based inventories provide reliable estimates of Shannon and Simpson diversity but are costly and time-consuming, while supervised AI methods require labeled data that often fail to generalize across regions. We introduce an unsupervised clustering framework that integrates visual embeddings from street-level imagery with spatial planting patterns to estimate biodiversity without labels. Applied to eight North American cities, the method recovers genus-level diversity patterns with high fidelity, achieving low Wasserstein distances to ground truth for Shannon and Simpson indices and preserving spatial autocorrelation. This scalable, fine-grained approach enables biodiversity mapping in cities lacking detailed inventories and offers a pathway for continuous, low-cost monitoring to support equitable access to greenery and adaptive management of urban ecosystems.

comment: 26 pages, 7 figures, Nature Format

☆ Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation

Donghwa Kang, Doohyun Kim, Sang-Ki Ko, Jinkyu Lee, Hyeongboo Baek, Brent ByungHoon Kang

State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing, rendering them infeasible for practical real-time applications. This inefficiency stems from their design as direct extensions of ANN paradigms, which fail to exploit key SNN properties. In this paper, we propose the timestep-compressed attack (TCA), a novel framework that significantly reduces attack latency. TCA introduces two components founded on key insights into SNN behavior. First, timestep-level backpropagation (TLBP) is based on our finding that global temporal information in backpropagation to generate perturbations is not critical for an attack's success, enabling per-timestep evaluation for early stopping. Second, adversarial membrane potential reuse (A-MPR) is motivated by the observation that initial timesteps are inefficiently spent accumulating membrane potential, a warm-up phase that can be pre-calculated and reused. Our experiments on VGG-11 and ResNet-17 with the CIFAR-10/100 and CIFAR10-DVS datasets show that TCA significantly reduces the required attack latency by up to 56.6% and 57.1% compared to SOTA methods in white-box and black-box settings, respectively, while maintaining a comparable attack success rate.

comment: 8 pages

☆ Is-NeRF: In-scattering Neural Radiance Field for Blurred Images

Nan Luo, Chenglin Ye, Jiaxu Li, Gang Liu, Bo Wan, Di Wang, Lupeng Liu, Jun Xiao

Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which struggles to handle sophisticated lightpath scenarios and introduces geometric ambiguities during training, particularly evident when processing motion-blurred images. To address these challenges, this work proposes a novel deblur neural radiance field, Is-NeRF, featuring explicit lightpath modeling in real-world environments. By unifying six common light propagation phenomena through an in-scattering representation, we establish a new scattering-aware volume rendering pipeline adaptable to complex lightpaths. Additionally, we introduce an adaptive learning strategy that enables autonomous determining of scattering directions and sampling intervals to capture finer object details. The proposed network jointly optimizes NeRF parameters, scattering parameters, and camera motions to recover fine-grained scene representations from blurry images. Comprehensive evaluations demonstrate that it effectively handles complex real-world scenarios, outperforming state-of-the-art approaches in generating high-fidelity images with accurate geometric details.

☆ Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing

Feng-Lin Liu, Shi-Yang Li, Yan-Pei Cao, Hongbo Fu, Lin Gao

Recent video editing methods achieve attractive results in style transfer or appearance modification. However, editing the structural content of 3D scenes in videos remains challenging, particularly when dealing with significant viewpoint changes, such as large camera rotations or zooms. Key challenges include generating novel view content that remains consistent with the original video, preserving unedited regions, and translating sparse 2D inputs into realistic 3D video outputs. To address these issues, we propose Sketch3DVE, a sketch-based 3D-aware video editing method to enable detailed local manipulation of videos with significant viewpoint changes. To solve the challenge posed by sparse inputs, we employ image editing methods to generate edited results for the first frame, which are then propagated to the remaining frames of the video. We utilize sketching as an interaction tool for precise geometry control, while other mask-based image editing methods are also supported. To handle viewpoint changes, we perform a detailed analysis and manipulation of the 3D information in the video. Specifically, we utilize a dense stereo method to estimate a point cloud and the camera parameters of the input video. We then propose a point cloud editing approach that uses depth maps to represent the 3D geometry of newly edited components, aligning them effectively with the original 3D scene. To seamlessly merge the newly edited content with the original video while preserving the features of unedited regions, we introduce a 3D-aware mask propagation strategy and employ a video diffusion model to produce realistic edited videos. Extensive experiments demonstrate the superiority of Sketch3DVE in video editing. Homepage and code: http://http://geometrylearning.com/Sketch3DVE/

comment: SIGGRAPH 2025

☆ A Fully Transformer Based Multimodal Framework for Explainable Cancer Image Segmentation Using Radiology Reports

Enobong Adahada, Isabel Sassoon, Kate Hone, Yongmin Li

We introduce Med-CTX, a fully transformer based multimodal framework for explainable breast cancer ultrasound segmentation. We integrate clinical radiology reports to boost both performance and interpretability. Med-CTX achieves exact lesion delineation by using a dual-branch visual encoder that combines ViT and Swin transformers, as well as uncertainty aware fusion. Clinical language structured with BI-RADS semantics is encoded by BioClinicalBERT and combined with visual features utilising cross-modal attention, allowing the model to provide clinically grounded, model generated explanations. Our methodology generates segmentation masks, uncertainty maps, and diagnostic rationales all at once, increasing confidence and transparency in computer assisted diagnosis. On the BUS-BRA dataset, Med-CTX achieves a Dice score of 99% and an IoU of 95%, beating existing baselines U-Net, ViT, and Swin. Clinical text plays a key role in segmentation accuracy and explanation quality, as evidenced by ablation studies that show a -5.4% decline in Dice score and -31% in CIDEr. Med-CTX achieves good multimodal alignment (CLIP score: 85%) and increased confi dence calibration (ECE: 3.2%), setting a new bar for trustworthy, multimodal medical architecture.

☆ VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization

Jailing Lin, Shu Jiang, Qingyuan Zeng, Zhenzhong Wang, Min Jiang

The intrinsic dynamics of an object governs its physical behavior in the real world, playing a critical role in enabling physically plausible interactive simulation with 3D assets. Existing methods have attempted to infer the intrinsic dynamics of objects from visual observations, but generally face two major challenges: one line of work relies on manually defined constitutive priors, making it difficult to generalize to complex scenarios; the other models intrinsic dynamics using neural networks, resulting in limited interpretability and poor generalization. To address these challenges, we propose VisionLaw, a bilevel optimization framework that infers interpretable expressions of intrinsic dynamics from visual observations. At the upper level, we introduce an LLMs-driven decoupled constitutive evolution strategy, where LLMs are prompted as a knowledgeable physics expert to generate and revise constitutive laws, with a built-in decoupling mechanism that substantially reduces the search complexity of LLMs. At the lower level, we introduce a vision-guided constitutive evaluation mechanism, which utilizes visual simulation to evaluate the consistency between the generated constitutive law and the underlying intrinsic dynamics, thereby guiding the upper-level evolution. Experiments on both synthetic and real-world datasets demonstrate that VisionLaw can effectively infer interpretable intrinsic dynamics from visual observations. It significantly outperforms existing state-of-the-art methods and exhibits strong generalization for interactive simulation in novel scenarios.

comment: 9 pages, 6 figures

☆ Shape-from-Template with Generalised Camera

Agniva Sengupta, Stefan Zachow

This article presents a new method for non-rigidly registering a 3D shape to 2D keypoints observed by a constellation of multiple cameras. Non-rigid registration of a 3D shape to observed 2D keypoints, i.e., Shape-from-Template (SfT), has been widely studied using single images, but SfT with information from multiple-cameras jointly opens new directions for extending the scope of known use-cases such as 3D shape registration in medical imaging and registration from hand-held cameras, to name a few. We represent such multi-camera setup with the generalised camera model; therefore any collection of perspective or orthographic cameras observing any deforming object can be registered. We propose multiple approaches for such SfT: the first approach where the corresponded keypoints lie on a direction vector from a known 3D point in space, the second approach where the corresponded keypoints lie on a direction vector from an unknown 3D point in space but with known orientation w.r.t some local reference frame, and a third approach where, apart from correspondences, the silhouette of the imaged object is also known. Together, these form the first set of solutions to the SfT problem with generalised cameras. The key idea behind SfT with generalised camera is the improved reconstruction accuracy from estimating deformed shape while utilising the additional information from the mutual constraints between multiple views of a deformed object. The correspondence-based approaches are solved with convex programming while the silhouette-based approach is an iterative refinement of the results from the convex solutions. We demonstrate the accuracy of our proposed methods on many synthetic and real data

comment: Pre-print of the IMAVIS article: https://www.sciencedirect.com/science/article/abs/pii/S0262885625001672 Code and data in: https://git.zib.de/asengupta/sft-generalised

☆ Comparing Conditional Diffusion Models for Synthesizing Contrast-Enhanced Breast MRI from Pre-Contrast Images

Sebastian Ibarra, Javier del Riego, Alessandro Catanese, Julian Cuba, Julian Cardona, Nataly Leon, Jonathan Infante, Karim Lekadir, Oliver Diaz, Richard Osuala

Dynamic contrast-enhanced (DCE) MRI is essential for breast cancer diagnosis and treatment. However, its reliance on contrast agents introduces safety concerns, contraindications, increased cost, and workflow complexity. To this end, we present pre-contrast conditioned denoising diffusion probabilistic models to synthesize DCE-MRI, introducing, evaluating, and comparing a total of 22 generative model variants in both single-breast and full breast settings. Towards enhancing lesion fidelity, we introduce both tumor-aware loss functions and explicit tumor segmentation mask conditioning. Using a public multicenter dataset and comparing to respective pre-contrast baselines, we observe that subtraction image-based models consistently outperform post-contrast-based models across five complementary evaluation metrics. Apart from assessing the entire image, we also separately evaluate the region of interest, where both tumor-aware losses and segmentation mask inputs improve evaluation metrics. The latter notably enhance qualitative results capturing contrast uptake, albeit assuming access to tumor localization inputs that are not guaranteed to be available in screening settings. A reader study involving 2 radiologists and 4 MRI technologists confirms the high realism of the synthetic images, indicating an emerging clinical potential of generative contrast-enhancement. We share our codebase at https://github.com/sebastibar/conditional-diffusion-breast-MRI.

comment: 13 pages, 5 figures, submitted and accepted to MICCAI Deepbreath workshop 2025

☆ MR6D: Benchmarking 6D Pose Estimation for Mobile Robots

Anas Gouda, Shrutarv Awasthi, Christian Blesing, Lokeshwaran Manohar, Frank Hoffmann, Alice Kirchheim

Existing 6D pose estimation datasets primarily focus on small household objects typically handled by robot arm manipulators, limiting their relevance to mobile robotics. Mobile platforms often operate without manipulators, interact with larger objects, and face challenges such as long-range perception, heavy self-occlusion, and diverse camera perspectives. While recent models generalize well to unseen objects, evaluations remain confined to household-like settings that overlook these factors. We introduce MR6D, a dataset designed for 6D pose estimation for mobile robots in industrial environments. It includes 92 real-world scenes featuring 16 unique objects across static and dynamic interactions. MR6D captures the challenges specific to mobile platforms, including distant viewpoints, varied object configurations, larger object sizes, and complex occlusion/self-occlusion patterns. Initial experiments reveal that current 6D pipelines underperform in these settings, with 2D segmentation being another hurdle. MR6D establishes a foundation for developing and evaluating pose estimation methods tailored to the demands of mobile robotics. The dataset is available at https://huggingface.co/datasets/anas-gouda/mr6d.

comment: accepted CVPR 2025 Workshop on Recovering 6D Object Pose (R6D)

☆ Deep Biomechanically-Guided Interpolation for Keypoint-Based Brain Shift Registration

Tiago Assis, Ines P. Machado, Benjamin Zwick, Nuno C. Garcia, Reuben Dorent

Accurate compensation of brain shift is critical for maintaining the reliability of neuronavigation during neurosurgery. While keypoint-based registration methods offer robustness to large deformations and topological changes, they typically rely on simple geometric interpolators that ignore tissue biomechanics to create dense displacement fields. In this work, we propose a novel deep learning framework that estimates dense, physically plausible brain deformations from sparse matched keypoints. We first generate a large dataset of synthetic brain deformations using biomechanical simulations. Then, a residual 3D U-Net is trained to refine standard interpolation estimates into biomechanically guided deformations. Experiments on a large set of simulated displacement fields demonstrate that our method significantly outperforms classical interpolators, reducing by half the mean square error while introducing negligible computational overhead at inference time. Code available at: \href{https://github.com/tiago-assis/Deep-Biomechanical-Interpolator}{https://github.com/tiago-assis/Deep-Biomechanical-Interpolator}.

comment: Accepted at COLlaborative Intelligence and Autonomy in Image-guided Surgery (COLAS) Workshop - MICCAI 2025

☆ Mitigating Cross-Image Information Leakage in LVLMs for Multi-Image Tasks

Yeji Park, Minyoung Lee, Sanghyuk Chun, Junsuk Choe

Large Vision-Language Models (LVLMs) demonstrate strong performance on single-image tasks. However, we observe that their performance degrades significantly when handling multi-image inputs. This occurs because visual cues from different images become entangled in the model's output. We refer to this phenomenon as cross-image information leakage. To address this issue, we propose FOCUS, a training-free and architecture-agnostic decoding strategy that mitigates cross-image information leakage during inference. FOCUS sequentially masks all but one image with random noise, guiding the model to focus on the single clean image. We repeat this process across all target images to obtain logits under partially masked contexts. These logits are aggregated and then contrastively refined using a noise-only reference input, which suppresses the leakage and yields more accurate outputs. FOCUS consistently improves performance across four multi-image benchmarks and diverse LVLM families. This demonstrates that FOCUS offers a general and practical solution for enhancing multi-image reasoning without additional training or architectural modifications.

comment: Source code is available at https://github.com/yejipark-m/FOCUS

☆ Enhancing Targeted Adversarial Attacks on Large Vision-Language Models through Intermediate Projector Guidance

Yiming Cao, Yanjie Li, Kaisheng Liang, Yuni Lai, Bin Xiao

Targeted adversarial attacks are essential for proactively identifying security flaws in Vision-Language Models before real-world deployment. However, current methods perturb images to maximize global similarity with the target text or reference image at the encoder level, collapsing rich visual semantics into a single global vector. This limits attack granularity, hindering fine-grained manipulations such as modifying a car while preserving its background. Furthermore, these methods largely overlook the projector module, a critical semantic bridge between the visual encoder and the language model in VLMs, thereby failing to disrupt the full vision-language alignment pipeline within VLMs and limiting attack effectiveness. To address these issues, we propose the Intermediate Projector Guided Attack (IPGA), the first method to attack using the intermediate stage of the projector module, specifically the widely adopted Q-Former, which transforms global image embeddings into fine-grained visual features. This enables more precise control over adversarial perturbations by operating on semantically meaningful visual tokens rather than a single global representation. Specifically, IPGA leverages the Q-Former pretrained solely on the first vision-language alignment stage, without LLM fine-tuning, which improves both attack effectiveness and transferability across diverse VLMs. Furthermore, we propose Residual Query Alignment (RQA) to preserve unrelated visual content, thereby yielding more controlled and precise adversarial manipulations. Extensive experiments show that our attack method consistently outperforms existing methods in both standard global image captioning tasks and fine-grained visual question-answering tasks in black-box environment. Additionally, IPGA successfully transfers to multiple commercial VLMs, including Google Gemini and OpenAI GPT.

☆ Hierarchical Vision-Language Retrieval of Educational Metaverse Content in Agriculture

Ali Abdari, Alex Falcon, Giuseppe Serra

Every day, a large amount of educational content is uploaded online across different areas, including agriculture and gardening. When these videos or materials are grouped meaningfully, they can make learning easier and more effective. One promising way to organize and enrich such content is through the Metaverse, which allows users to explore educational experiences in an interactive and immersive environment. However, searching for relevant Metaverse scenarios and finding those matching users' interests remains a challenging task. A first step in this direction has been done recently, but existing datasets are small and not sufficient for training advanced models. In this work, we make two main contributions: first, we introduce a new dataset containing 457 agricultural-themed virtual museums (AgriMuseums), each enriched with textual descriptions; and second, we propose a hierarchical vision-language model to represent and retrieve relevant AgriMuseums using natural language queries. In our experimental setting, the proposed method achieves up to about 62\% R@1 and 78\% MRR, confirming its effectiveness, and it also leads to improvements on existing benchmarks by up to 6\% R@1 and 11\% MRR. Moreover, an extensive evaluation validates our design choices. Code and dataset are available at https://github.com/aliabdari/Agricultural_Metaverse_Retrieval .

comment: Accepted for publication at the 23rd International Conference on Image Analysis and Processing (ICIAP 2025)

☆ Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation

Shumeng Li, Jian Zhang, Lei Qi, Luping Zhou, Yinghuan Shi, Yang Gao

Acquiring high-quality annotated data for medical image segmentation is tedious and costly. Semi-supervised segmentation techniques alleviate this burden by leveraging unlabeled data to generate pseudo labels. Recently, advanced state space models, represented by Mamba, have shown efficient handling of long-range dependencies. This drives us to explore their potential in semi-supervised medical image segmentation. In this paper, we propose a novel Diversity-enhanced Collaborative Mamba framework (namely DCMamba) for semi-supervised medical image segmentation, which explores and utilizes the diversity from data, network, and feature perspectives. Firstly, from the data perspective, we develop patch-level weak-strong mixing augmentation with Mamba's scanning modeling characteristics. Moreover, from the network perspective, we introduce a diverse-scan collaboration module, which could benefit from the prediction discrepancies arising from different scanning directions. Furthermore, from the feature perspective, we adopt an uncertainty-weighted contrastive learning mechanism to enhance the diversity of feature representation. Experiments demonstrate that our DCMamba significantly outperforms other semi-supervised medical image segmentation methods, e.g., yielding the latest SSM-based method by 6.69% on the Synapse dataset with 20% labeled data.

☆ subCellSAM: Zero-Shot (Sub-)Cellular Segmentation for Hit Validation in Drug Discovery

Jacob Hanimann, Daniel Siegismund, Mario Wieser, Stephan Steigele

High-throughput screening using automated microscopes is a key driver in biopharma drug discovery, enabling the parallel evaluation of thousands of drug candidates for diseases such as cancer. Traditional image analysis and deep learning approaches have been employed to analyze these complex, large-scale datasets, with cell segmentation serving as a critical step for extracting relevant structures. However, both strategies typically require extensive manual parameter tuning or domain-specific model fine-tuning. We present a novel method that applies a segmentation foundation model in a zero-shot setting (i.e., without fine-tuning), guided by an in-context learning strategy. Our approach employs a three-step process for nuclei, cell, and subcellular segmentation, introducing a self-prompting mechanism that encodes morphological and topological priors using growing masks and strategically placed foreground/background points. We validate our method on both standard cell segmentation benchmarks and industry-relevant hit validation assays, demonstrating that it accurately segments biologically relevant structures without the need for dataset-specific tuning.

comment: Accepted at DAGM German Conference on Pattern Recognition (GCPR) 2025

☆ HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes

Keliang Li, Hongze Shen, Hao Shi, Ruibing Hou, Hong Chang, Jie Huang, Chenghao Jia, Wen Wang, Yiling Wu, Dongmei Jiang, Shiguang Shan, Xilin Chen

The aspiration for artificial general intelligence, fueled by the rapid progress of multimodal models, demands human-comparable performance across diverse environments. We propose HumanPCR, an evaluation suite for probing MLLMs' capacity about human-related visual contexts across three hierarchical levels: Perception, Comprehension, and Reasoning (denoted by Human-P, Human-C, and Human-R, respectively). Human-P and Human-C feature over 6,000 human-verified multiple choice questions, assessing massive tasks of 9 dimensions, including but not limited to essential skills frequently overlooked by existing benchmarks. Human-R offers a challenging manually curated video reasoning test that requires integrating multiple visual evidences, proactively extracting context beyond question cues, and applying human-like expertise. Each question includes human-annotated Chain-of-Thought (CoT) rationales with key visual evidence to support further research. Extensive evaluations on over 30 state-of-the-art models exhibit significant challenges in human-centric visual understanding, particularly in tasks involving detailed space perception, temporal understanding, and mind modeling. Moreover, analysis of Human-R reveals the struggle of models in extracting essential proactive visual evidence from diverse human scenes and their faulty reliance on query-guided retrieval. Even with advanced techniques like scaling visual contexts and test-time thinking yield only limited benefits. We hope HumanPCR and our findings will advance the development, evaluation, and human-centric application of multimodal models.

☆ DeH4R: A Decoupled and Hybrid Method for Road Network Graph Extraction

Dengxian Gong, Shunping Ji

The automated extraction of complete and precise road network graphs from remote sensing imagery remains a critical challenge in geospatial computer vision. Segmentation-based approaches, while effective in pixel-level recognition, struggle to maintain topology fidelity after vectorization postprocessing. Graph-growing methods build more topologically faithful graphs but suffer from computationally prohibitive iterative ROI cropping. Graph-generating methods first predict global static candidate road network vertices, and then infer possible edges between vertices. They achieve fast topology-aware inference, but limits the dynamic insertion of vertices. To address these challenges, we propose DeH4R, a novel hybrid model that combines graph-generating efficiency and graph-growing dynamics. This is achieved by decoupling the task into candidate vertex detection, adjacent vertex prediction, initial graph contruction, and graph expansion. This architectural innovation enables dynamic vertex (edge) insertions while retaining fast inference speed and enhancing both topology fidelity and spatial consistency. Comprehensive evaluations on CityScale and SpaceNet benchmarks demonstrate state-of-the-art (SOTA) performance. DeH4R outperforms the prior SOTA graph-growing method RNGDet++ by 4.62 APLS and 10.18 IoU on CityScale, while being approximately 10 $\times$ faster. The code will be made publicly available at https://github.com/7777777FAN/DeH4R.

comment: Under review

☆ Model-based Multi-object Visual Tracking: Identification and Standard Model Limitations

Jan Krejčí, Oliver Kost, Yuxuan Xia, Lennart Svensson, Ondřej Straka

This paper uses multi-object tracking methods known from the radar tracking community to address the problem of pedestrian tracking using 2D bounding box detections. The standard point-object (SPO) model is adopted, and the posterior density is computed using the Poisson multi-Bernoulli mixture (PMBM) filter. The selection of the model parameters rooted in continuous time is discussed, including the birth and survival probabilities. Some parameters are selected from the first principles, while others are identified from the data, which is, in this case, the publicly available MOT-17 dataset. Although the resulting PMBM algorithm yields promising results, a mismatch between the SPO model and the data is revealed. The model-based approach assumes that modifying the problematic components causing the SPO model-data mismatch will lead to better model-based algorithms in future developments.

comment: Submitted to FUSION 2025 conference

☆ OmniTry: Virtual Try-On Anything without Masks

Yutong Feng, Linlin Zhang, Hengyuan Cao, Yiming Chen, Xiaoduan Feng, Jian Cao, Yuxiong Wu, Bin Wang

Virtual Try-ON (VTON) is a practical and widely-applied task, for which most of existing works focus on clothes. This paper presents OmniTry, a unified framework that extends VTON beyond garment to encompass any wearable objects, e.g., jewelries and accessories, with mask-free setting for more practical application. When extending to various types of objects, data curation is challenging for obtaining paired images, i.e., the object image and the corresponding try-on result. To tackle this problem, we propose a two-staged pipeline: For the first stage, we leverage large-scale unpaired images, i.e., portraits with any wearable items, to train the model for mask-free localization. Specifically, we repurpose the inpainting model to automatically draw objects in suitable positions given an empty mask. For the second stage, the model is further fine-tuned with paired images to transfer the consistency of object appearance. We observed that the model after the first stage shows quick convergence even with few paired samples. OmniTry is evaluated on a comprehensive benchmark consisting of 12 common classes of wearable objects, with both in-shop and in-the-wild images. Experimental results suggest that OmniTry shows better performance on both object localization and ID-preservation compared with existing methods. The code, model weights, and evaluation benchmark of OmniTry will be made publicly available at https://omnitry.github.io/.

☆ DiffIER: Optimizing Diffusion Models with Iterative Error Reduction

Ao Chen, Lihe Ding, Tianfan Xue

Diffusion models have demonstrated remarkable capabilities in generating high-quality samples and enhancing performance across diverse domains through Classifier-Free Guidance (CFG). However, the quality of generated samples is highly sensitive to the selection of the guidance weight. In this work, we identify a critical ``training-inference gap'' and we argue that it is the presence of this gap that undermines the performance of conditional generation and renders outputs highly sensitive to the guidance weight. We quantify this gap by measuring the accumulated error during the inference stage and establish a correlation between the selection of guidance weight and minimizing this gap. Furthermore, to mitigate this gap, we propose DiffIER, an optimization-based method for high-quality generation. We demonstrate that the accumulated error can be effectively reduced by an iterative error minimization at each step during inference. By introducing this novel plug-and-play optimization framework, we enable the optimization of errors at every single inference step and enhance generation quality. Empirical results demonstrate that our proposed method outperforms baseline approaches in conditional generation tasks. Furthermore, the method achieves consistent success in text-to-image generation, image super-resolution, and text-to-speech generation, underscoring its versatility and potential for broad applications in future research.

☆ State of Abdominal CT Datasets: A Critical Review of Bias, Clinical Relevance, and Real-world Applicability

Saeide Danaei, Zahra Dehghanian, Elahe Meftah, Nariman Naderi, Seyed Amir Ahmad Safavi-Naini, Faeze Khorasanizade, Hamid R. Rabiee

This systematic review critically evaluates publicly available abdominal CT datasets and their suitability for artificial intelligence (AI) applications in clinical settings. We examined 46 publicly available abdominal CT datasets (50,256 studies). Across all 46 datasets, we found substantial redundancy (59.1\% case reuse) and a Western/geographic skew (75.3\% from North America and Europe). A bias assessment was performed on the 19 datasets with >=100 cases; within this subset, the most prevalent high-risk categories were domain shift (63\%) and selection bias (57\%), both of which may undermine model generalizability across diverse healthcare environments -- particularly in resource-limited settings. To address these challenges, we propose targeted strategies for dataset improvement, including multi-institutional collaboration, adoption of standardized protocols, and deliberate inclusion of diverse patient populations and imaging technologies. These efforts are crucial in supporting the development of more equitable and clinically robust AI models for abdominal imaging.

comment: Preprint. Submitted to IEEE Journal of Biomedical and Health Informatics (under review). 10 pages, 3 figures, 5 tables

☆ RCGNet: RGB-based Category-Level 6D Object Pose Estimation with Geometric Guidance

Sheng Yu, Di-Hua Zhai, Yuanqing Xia

While most current RGB-D-based category-level object pose estimation methods achieve strong performance, they face significant challenges in scenes lacking depth information. In this paper, we propose a novel category-level object pose estimation approach that relies solely on RGB images. This method enables accurate pose estimation in real-world scenarios without the need for depth data. Specifically, we design a transformer-based neural network for category-level object pose estimation, where the transformer is employed to predict and fuse the geometric features of the target object. To ensure that these predicted geometric features faithfully capture the object's geometry, we introduce a geometric feature-guided algorithm, which enhances the network's ability to effectively represent the object's geometric information. Finally, we utilize the RANSAC-PnP algorithm to compute the object's pose, addressing the challenges associated with variable object scales in pose estimation. Experimental results on benchmark datasets demonstrate that our approach is not only highly efficient but also achieves superior accuracy compared to previous RGB-based methods. These promising results offer a new perspective for advancing category-level object pose estimation using RGB images.

comment: Accepted by IROS2025

☆ TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

Shunian Chen, Hejin Huang, Yexin Liu, Zihan Ye, Pengcheng Chen, Chenghao Zhu, Michael Guan, Rongsheng Wang, Junying Chen, Guanbin Li, Ser-Nam Lim, Harry Yang, Benyou Wang

Audio-driven talking head synthesis has achieved remarkable photorealism, yet state-of-the-art (SOTA) models exhibit a critical failure: they lack generalization to the full spectrum of human diversity in ethnicity, language, and age groups. We argue that this generalization gap is a direct symptom of limitations in existing training data, which lack the necessary scale, quality, and diversity. To address this challenge, we introduce TalkVid, a new large-scale, high-quality, and diverse dataset containing 1244 hours of video from 7729 unique speakers. TalkVid is curated through a principled, multi-stage automated pipeline that rigorously filters for motion stability, aesthetic quality, and facial detail, and is validated against human judgments to ensure its reliability. Furthermore, we construct and release TalkVid-Bench, a stratified evaluation set of 500 clips meticulously balanced across key demographic and linguistic axes. Our experiments demonstrate that a model trained on TalkVid outperforms counterparts trained on previous datasets, exhibiting superior cross-dataset generalization. Crucially, our analysis on TalkVid-Bench reveals performance disparities across subgroups that are obscured by traditional aggregate metrics, underscoring its necessity for future research. Code and data can be found in https://github.com/FreedomIntelligence/TalkVid

☆ Two-Factor Authentication Smart Entryway Using Modified LBPH Algorithm

Zakiah Ayop, Wan Mohamad Hariz Bin Wan Mohamad Rosdi, Looi Wei Hua, Syarulnaziah Anawar, Nur Fadzilah Othman

Face mask detection has become increasingly important recently, particularly during the COVID-19 pandemic. Many face detection models have been developed in smart entryways using IoT. However, there is a lack of IoT development on face mask detection. This paper proposes a two-factor authentication system for smart entryway access control using facial recognition and passcode verification and an automation process to alert the owner and activate the surveillance system when a stranger is detected and controls the system remotely via Telegram on a Raspberry Pi platform. The system employs the Local Binary Patterns Histograms for the full face recognition algorithm and modified LBPH algorithm for occluded face detection. On average, the system achieved an Accuracy of approximately 70%, a Precision of approximately 80%, and a Recall of approximately 83.26% across all tested users. The results indicate that the system is capable of conducting face recognition and mask detection, automating the operation of the remote control to register users, locking or unlocking the door, and notifying the owner. The sample participants highly accept it for future use in the user acceptance test.

☆ PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction

Xiaolu Hou, Bing Ma, Jiaxiang Cheng, Xuhua Ren, Kai Yu, Wenyue Li, Tianxiang Zheng, Qinglin Lu

With the growing demand for short videos and personalized content, automated Video Log (Vlog) generation has become a key direction in multimodal content creation. Existing methods mostly rely on predefined scripts, lacking dynamism and personal expression. Therefore, there is an urgent need for an automated Vlog generation approach that enables effective multimodal collaboration and high personalization. To this end, we propose PersonaVlog, an automated multimodal stylized Vlog generation framework that can produce personalized Vlogs featuring videos, background music, and inner monologue speech based on a given theme and reference image. Specifically, we propose a multi-agent collaboration framework based on Multimodal Large Language Models (MLLMs). This framework efficiently generates high-quality prompts for multimodal content creation based on user input, thereby improving the efficiency and creativity of the process. In addition, we incorporate a feedback and rollback mechanism that leverages MLLMs to evaluate and provide feedback on generated results, thereby enabling iterative self-correction of multimodal content. We also propose ThemeVlogEval, a theme-based automated benchmarking framework that provides standardized metrics and datasets for fair evaluation. Comprehensive experiments demonstrate the significant advantages and potential of our framework over several baselines, highlighting its effectiveness and great potential for generating automated Vlogs.

comment: Project Page: https://personavlog-paper.github.io/

☆ Unleashing Semantic and Geometric Priors for 3D Scene Completion

Shiyuan Chen, Wei Sui, Bohao Zhang, Zeyd Boukhers, John See, Cong Yang

Camera-based 3D semantic scene completion (SSC) provides dense geometric and semantic perception for autonomous driving and robotic navigation. However, existing methods rely on a coupled encoder to deliver both semantic and geometric priors, which forces the model to make a trade-off between conflicting demands and limits its overall performance. To tackle these challenges, we propose FoundationSSC, a novel framework that performs dual decoupling at both the source and pathway levels. At the source level, we introduce a foundation encoder that provides rich semantic feature priors for the semantic branch and high-fidelity stereo cost volumes for the geometric branch. At the pathway level, these priors are refined through specialised, decoupled pathways, yielding superior semantic context and depth distributions. Our dual-decoupling design produces disentangled and refined inputs, which are then utilised by a hybrid view transformation to generate complementary 3D features. Additionally, we introduce a novel Axis-Aware Fusion (AAF) module that addresses the often-overlooked challenge of fusing these features by anisotropically merging them into a unified representation. Extensive experiments demonstrate the advantages of FoundationSSC, achieving simultaneous improvements in both semantic and geometric metrics, surpassing prior bests by +0.23 mIoU and +2.03 IoU on SemanticKITTI. Additionally, we achieve state-of-the-art performance on SSCBench-KITTI-360, with 21.78 mIoU and 48.61 IoU. The code will be released upon acceptance.

comment: 9 pages, 5 figures, 6 tables

☆ Towards Efficient Vision State Space Models via Token Merging

Jinyoung Park, Minseok Son, Changick Kim

State Space Models (SSMs) have emerged as powerful architectures in computer vision, yet improving their computational efficiency remains crucial for practical and scalable deployment.While token reduction serves as an effective approach for model efficiency, applying it to SSMs requires careful consideration of their unique sequential modeling capabilities.In this work, we propose MaMe, a token-merging strategy tailored for SSM-based vision models.MaMe addresses two key challenges: quantifying token importance and preserving sequential properties. Our approach leverages the state transition parameter $\mathbf{\Delta}$ as an informativeness measure and introduces strategic token arrangements to preserve sequential information flow.Extensive experiments demonstrate that MaMe achieves superior efficiency-performance trade-offs for both fine-tuned and off-the-shelf models. Particularly, our approach maintains robustness even under aggressive token reduction where existing methods undergo significant performance degradation.Beyond image classification, MaMe shows strong generalization capabilities across video and audio domains, establishing an effective approach for enhancing efficiency in diverse SSM applications.

comment: under review

☆ Bridging Clear and Adverse Driving Conditions

Yoel Shapiro, Yahia Showgan, Koustav Mullick

Autonomous Driving (AD) systems exhibit markedly degraded performance under adverse environmental conditions, such as low illumination and precipitation. The underrepresentation of adverse conditions in AD datasets makes it challenging to address this deficiency. To circumvent the prohibitive cost of acquiring and annotating adverse weather data, we propose a novel Domain Adaptation (DA) pipeline that transforms clear-weather images into fog, rain, snow, and nighttime images. Here, we systematically develop and evaluate several novel data-generation pipelines, including simulation-only, GAN-based, and hybrid diffusion-GAN approaches, to synthesize photorealistic adverse images from labelled clear images. We leverage an existing DA GAN, extend it to support auxiliary inputs, and develop a novel training recipe that leverages both simulated and real images. The simulated images facilitate exact supervision by providing perfectly matched image pairs, while the real images help bridge the simulation-to-real (sim2real) gap. We further introduce a method to mitigate hallucinations and artifacts in Stable-Diffusion Image-to-Image (img2img) outputs by blending them adaptively with their progenitor images. We finetune downstream models on our synthetic data and evaluate them on the Adverse Conditions Dataset with Correspondences (ACDC). We achieve 1.85 percent overall improvement in semantic segmentation, and 4.62 percent on nighttime, demonstrating the efficacy of our hybrid method for robust AD perception under challenging conditions.

☆ Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation

Lei Chen, Xuanle Zhao, Zhixiong Zeng, Jing Huang, Liming Zheng, Yufeng Zhong, Lin Ma

While reinforcement learning (RL) has proven highly effective for general reasoning in vision-language models, its application to tasks requiring in-depth understanding of information-rich images and generation of structured outputs remains underexplored. Chart-to-code generation exemplifies this challenge, demanding complex reasoning over visual charts to generate structured code. Supervised fine-tuning (SFT) alone is often insufficient, highlighting the need for effective RL strategies that appropriately reward structured outputs. We systematically investigate the performance plateau in SFT through large-scale experiments and propose Multimodal Structured Reinforcement Learning (MSRL) for chart-to-code generation, which substantially breaks through this plateau. We construct the largest training corpus to date, containing 3 million chart-code pairs from real-world arXiv tables to mitigate simplistic patterns of prior synthetic data. Despite reaching state-of-the-art performance, our experiments show that scaling SFT data eventually hits a plateau where further increases yield negligible improvements. Our MSRL method leverages a multi-granularity structured reward system using multimodal textual and visual feedback. At the textual level, rule-based rewards validate fine-grained code details. At the visual level, model-based rewards assess structural similarity by rendering generated code into images and employing an evaluator model. We implement this within a two-stage curriculum for training stability. Results demonstrate that MSRL significantly breaks the SFT plateau, improving high-level metrics by 6.2% and 9.9% on ChartMimic and ReachQA benchmarks respectively, achieving competitive performance with advanced closed-source models.

comment: technical report

☆ Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model

Ruixin Zhang, Jiaqing Fan, Yifan Liao, Qian Qiao, Fanzhang Li

Referring Video Object Segmentation (RVOS) aims to segment specific objects in a video according to textual descriptions. We observe that recent RVOS approaches often place excessive emphasis on feature extraction and temporal modeling, while relatively neglecting the design of the segmentation head. In fact, there remains considerable room for improvement in segmentation head design. To address this, we propose a Temporal-Conditional Referring Video Object Segmentation model, which innovatively integrates existing segmentation methods to effectively enhance boundary segmentation capability. Furthermore, our model leverages a text-to-video diffusion model for feature extraction. On top of this, we remove the traditional noise prediction module to avoid the randomness of noise from degrading segmentation accuracy, thereby simplifying the model while improving performance. Finally, to overcome the limited feature extraction capability of the VAE, we design a Temporal Context Mask Refinement (TCMR) module, which significantly improves segmentation quality without introducing complex designs. We evaluate our method on four public RVOS benchmarks, where it consistently achieves state-of-the-art performance.

comment: 11 pages, 7 figures

☆ Generative Model-Based Feature Attention Module for Video Action Analysis

Guiqin Wang, Peng Zhao, Cong Zhao, Jing Huang, Siyan Guo, Shusen Yang

Video action analysis is a foundational technology within the realm of intelligent video comprehension, particularly concerning its application in Internet of Things(IoT). However, existing methodologies overlook feature semantics in feature extraction and focus on optimizing action proposals, thus these solutions are unsuitable for widespread adoption in high-performance IoT applications due to the limitations in precision, such as autonomous driving, which necessitate robust and scalable intelligent video analytics analysis. To address this issue, we propose a novel generative attention-based model to learn the relation of feature semantics. Specifically, by leveraging the differences of actions' foreground and background, our model simultaneously learns the frame- and segment-dependencies of temporal action feature semantics, which takes advantage of feature semantics in the feature extraction effectively. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark video task, action recognition and action detection. In the context of action detection tasks, we substantiate the superiority of our approach through comprehensive validation on widely recognized datasets. Moreover, we extend the validation of the effectiveness of our proposed method to a broader task, video action recognition. Our code is available at https://github.com/Generative-Feature-Model/GAF.

☆ The 9th AI City Challenge

Zheng Tang, Shuo Wang, David C. Anastasiu, Ming-Ching Chang, Anuj Sharma, Quan Kong, Norimasa Kobori, Munkhjargal Gochoo, Ganzorig Batnasan, Munkh-Erdene Otgonbold, Fady Alnajjar, Jun-Wei Hsieh, Tomasz Kornuta, Xiaolong Li, Yilin Zhao, Han Zhang, Subhashree Radhakrishnan, Arihant Jain, Ratnesh Kumar, Vidya N. Murali, Yuxing Wang, Sameer Satish Pusegaonkar, Yizhou Wang, Sujit Biswas, Xunlei Wu, Zhedong Zheng, Pranamesh Chakraborty, Rama Chellappa

The ninth AI City Challenge continues to advance real-world applications of computer vision and AI in transportation, industrial automation, and public safety. The 2025 edition featured four tracks and saw a 17% increase in participation, with 245 teams from 15 countries registered on the evaluation server. Public release of challenge datasets led to over 30,000 downloads to date. Track 1 focused on multi-class 3D multi-camera tracking, involving people, humanoids, autonomous mobile robots, and forklifts, using detailed calibration and 3D bounding box annotations. Track 2 tackled video question answering in traffic safety, with multi-camera incident understanding enriched by 3D gaze labels. Track 3 addressed fine-grained spatial reasoning in dynamic warehouse environments, requiring AI systems to interpret RGB-D inputs and answer spatial questions that combine perception, geometry, and language. Both Track 1 and Track 3 datasets were generated in NVIDIA Omniverse. Track 4 emphasized efficient road object detection from fisheye cameras, supporting lightweight, real-time deployment on edge devices. The evaluation framework enforced submission limits and used a partially held-out test set to ensure fair benchmarking. Final rankings were revealed after the competition concluded, fostering reproducibility and mitigating overfitting. Several teams achieved top-tier results, setting new benchmarks in multiple tasks.

comment: Summary of the 9th AI City Challenge Workshop in conjunction with ICCV 2025

☆ Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

Yuchen Yang, Linfeng Dong, Wei Wang, Zhihang Zhong, Xiao Sun

In 3D human pose and shape estimation, SMPLify remains a robust baseline that solves inverse kinematics (IK) through iterative optimization. However, its high computational cost limits its practicality. Recent advances across domains have shown that replacing iterative optimization with data-driven neural networks can achieve significant runtime improvements without sacrificing accuracy. Motivated by this trend, we propose Learnable SMPLify, a neural framework that replaces the iterative fitting process in SMPLify with a single-pass regression model. The design of our framework targets two core challenges in neural IK: data construction and generalization. To enable effective training, we propose a temporal sampling strategy that constructs initialization-target pairs from sequential frames. To improve generalization across diverse motions and unseen poses, we propose a human-centric normalization scheme and residual learning to narrow the solution space. Learnable SMPLify supports both sequential inference and plug-in post-processing to refine existing image-based estimators. Extensive experiments demonstrate that our method establishes itself as a practical and simple baseline: it achieves nearly 200x faster runtime compared to SMPLify, generalizes well to unseen 3DPW and RICH, and operates in a model-agnostic manner when used as a plug-in tool on LucidAction. The code is available at https://github.com/Charrrrrlie/Learnable-SMPLify.

☆ DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup

Zhen Qu, Xian Tao, Xinyi Gong, ShiChen Qu, Xiaopei Zhang, Xingang Wang, Fei Shen, Zhengtao Zhang, Mukesh Prasad, Guiguang Ding

Recent vision-language models (e.g., CLIP) have demonstrated remarkable class-generalizable ability to unseen classes in few-shot anomaly segmentation (FSAS), leveraging supervised prompt learning or fine-tuning on seen classes. However, their cross-category generalization largely depends on prior knowledge of real seen anomaly samples. In this paper, we propose a novel framework, namely DictAS, which enables a unified model to detect visual anomalies in unseen object categories without any retraining on the target data, only employing a few normal reference images as visual prompts. The insight behind DictAS is to transfer dictionary lookup capabilities to the FSAS task for unseen classes via self-supervised learning, instead of merely memorizing the normal and abnormal feature patterns from the training set. Specifically, DictAS mainly consists of three components: (1) **Dictionary Construction** - to simulate the index and content of a real dictionary using features from normal reference images. (2) **Dictionary Lookup** - to retrieve queried region features from the dictionary via a sparse lookup strategy. When a query feature cannot be retrieved, it is classified as an anomaly. (3) **Query Discrimination Regularization**- to enhance anomaly discrimination by making abnormal features harder to retrieve from the dictionary. To achieve this, Contrastive Query Constraint and Text Alignment Constraint are further proposed. Extensive experiments on seven public industrial and medical datasets demonstrate that DictAS consistently outperforms state-of-the-art FSAS methods.

comment: Accepted by ICCV 2025, Project: https://github.com/xiaozhen228/DictAS

☆ Color Spike Data Generation via Bio-inspired Neuron-like Encoding with an Artificial Photoreceptor Layer

Hsieh Ching-Teng, Wang Yuan-Kai

In recent years, neuromorphic computing and spiking neural networks (SNNs) have ad-vanced rapidly through integration with deep learning. However, the performance of SNNs still lags behind that of convolutional neural networks (CNNs), primarily due to the limited information capacity of spike-based data. Although some studies have attempted to improve SNN performance by training them with non-spiking inputs such as static images, this approach deviates from the original intent of neuromorphic computing, which emphasizes spike-based information processing. To address this issue, we propose a Neuron-like Encoding method that generates spike data based on the intrinsic operational principles and functions of biological neurons. This method is further enhanced by the incorporation of an artificial pho-toreceptor layer, enabling spike data to carry both color and luminance information, thereby forming a complete visual spike signal. Experimental results using the Integrate-and-Fire neuron model demonstrate that this biologically inspired approach effectively increases the information content of spike signals and improves SNN performance, all while adhering to neuromorphic principles. We believe this concept holds strong potential for future development and may contribute to overcoming current limitations in neuro-morphic computing, facilitating broader applications of SNNs.

comment: 14 pages, 11 figures

☆ A Lightweight Dual-Mode Optimization for Generative Face Video Coding

Zihan Zhang, Shanzhi Yin, Bolin Chen, Ru-Ling Liao, Shiqi Wang, Yan Ye

Generative Face Video Coding (GFVC) achieves superior rate-distortion performance by leveraging the strong inference capabilities of deep generative models. However, its practical deployment is hindered by large model parameters and high computational costs. To address this, we propose a lightweight GFVC framework that introduces dual-mode optimization -- combining architectural redesign and operational refinement -- to reduce complexity whilst preserving reconstruction quality. Architecturally, we replace traditional 3 x 3 convolutions with slimmer and more efficient layers, reducing complexity without compromising feature expressiveness. Operationally, we develop a two-stage adaptive channel pruning strategy: (1) soft pruning during training identifies redundant channels via learnable thresholds, and (2) hard pruning permanently eliminates these channels post-training using a derived mask. This dual-phase approach ensures both training stability and inference efficiency. Experimental results demonstrate that the proposed lightweight dual-mode optimization for GFVC can achieve 90.4% parameter reduction and 88.9% computation saving compared to the baseline, whilst achieving superior performance compared to state-of-the-art video coding standard Versatile Video Coding (VVC) in terms of perceptual-level quality metrics. As such, the proposed method is expected to enable efficient GFVC deployment in resource-constrained environments such as mobile edge devices.

☆ GazeProphet: Software-Only Gaze Prediction for VR Foveated Rendering

Farhaan Ebadulla, Chiraag Mudlapur, Gaurav BV

Foveated rendering significantly reduces computational demands in virtual reality applications by concentrating rendering quality where users focus their gaze. Current approaches require expensive hardware-based eye tracking systems, limiting widespread adoption due to cost, calibration complexity, and hardware compatibility constraints. This paper presents GazeProphet, a software-only approach for predicting gaze locations in VR environments without requiring dedicated eye tracking hardware. The approach combines a Spherical Vision Transformer for processing 360-degree VR scenes with an LSTM-based temporal encoder that captures gaze sequence patterns. A multi-modal fusion network integrates spatial scene features with temporal gaze dynamics to predict future gaze locations with associated confidence estimates. Experimental evaluation on a comprehensive VR dataset demonstrates that GazeProphet achieves a median angular error of 3.83 degrees, outperforming traditional saliency-based baselines by 24% while providing reliable confidence calibration. The approach maintains consistent performance across different spatial regions and scene types, enabling practical deployment in VR systems without additional hardware requirements. Statistical analysis confirms the significance of improvements across all evaluation metrics. These results show that software-only gaze prediction can work for VR foveated rendering, making this performance boost more accessible to different VR platforms and apps.

comment: 8 pages, 3 figures

☆ FLAIR: Frequency- and Locality-Aware Implicit Neural Representations

Sukhun Ko, Dahyeon Kye, Kyle Min, Chanho Eom, Jihyong Oh

Implicit Neural Representations (INRs) leverage neural networks to map coordinates to corresponding signals, enabling continuous and compact representations. This paradigm has driven significant advances in various vision tasks. However, existing INRs lack frequency selectivity, spatial localization, and sparse representations, leading to an over-reliance on redundant signal components. Consequently, they exhibit spectral bias, tending to learn low-frequency components early while struggling to capture fine high-frequency details. To address these issues, we propose FLAIR (Frequency- and Locality-Aware Implicit Neural Representations), which incorporates two key innovations. The first is RC-GAUSS, a novel activation designed for explicit frequency selection and spatial localization under the constraints of the time-frequency uncertainty principle (TFUP). The second is Wavelet-Energy-Guided Encoding (WEGE), which leverages the discrete wavelet transform (DWT) to compute energy scores and explicitly guide frequency information to the network. Our method consistently outperforms existing INRs in 2D image representation and restoration, as well as 3D reconstruction.

comment: Please visit our project page at https://cmlab-korea.github.io/FLAIR/

☆ EAvatar: Expression-Aware Head Avatar Reconstruction with Generative Geometry Priors

Shikun Zhang, Cunjian Chen, Yiqun Wang, Qiuhong Ke, Yong Li

High-fidelity head avatar reconstruction plays a crucial role in AR/VR, gaming, and multimedia content creation. Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated effectiveness in modeling complex geometry with real-time rendering capability and are now widely used in high-fidelity head avatar reconstruction tasks. However, existing 3DGS-based methods still face significant challenges in capturing fine-grained facial expressions and preserving local texture continuity, especially in highly deformable regions. To mitigate these limitations, we propose a novel 3DGS-based framework termed EAvatar for head reconstruction that is both expression-aware and deformation-aware. Our method introduces a sparse expression control mechanism, where a small number of key Gaussians are used to influence the deformation of their neighboring Gaussians, enabling accurate modeling of local deformations and fine-scale texture transitions. Furthermore, we leverage high-quality 3D priors from pretrained generative models to provide a more reliable facial geometry, offering structural guidance that improves convergence stability and shape accuracy during training. Experimental results demonstrate that our method produces more accurate and visually coherent head reconstructions with improved expression controllability and detail fidelity.

comment: 20 pages, 11 figures

☆ MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondence

Chao Tang, Anxing Xiao, Yuhong Deng, Tianrun Hu, Wenlong Dong, Hanbo Zhang, David Hsu, Hong Zhang

Imitating tool manipulation from human videos offers an intuitive approach to teaching robots, while also providing a promising and scalable alternative to labor-intensive teleoperation data collection for visuomotor policy learning. While humans can mimic tool manipulation behavior by observing others perform a task just once and effortlessly transfer the skill to diverse tools for functionally equivalent tasks, current robots struggle to achieve this level of generalization. A key challenge lies in establishing function-level correspondences, considering the significant geometric variations among functionally similar tools, referred to as intra-function variations. To address this challenge, we propose MimicFunc, a framework that establishes functional correspondences with function frame, a function-centric local coordinate frame constructed with keypoint-based abstraction, for imitating tool manipulation skills. Experiments demonstrate that MimicFunc effectively enables the robot to generalize the skill from a single RGB-D human video to manipulating novel tools for functionally equivalent tasks. Furthermore, leveraging MimicFunc's one-shot generalization capability, the generated rollouts can be used to train visuomotor policies without requiring labor-intensive teleoperation data collection for novel objects. Our code and video are available at https://sites.google.com/view/mimicfunc.

comment: Accepted to CoRL 2025

☆ Evaluating Open-Source Vision Language Models for Facial Emotion Recognition against Traditional Deep Learning Models

Vamsi Krishna Mulukutla, Sai Supriya Pavarala, Srinivasa Raju Rudraraju, Sridevi Bonthu

Facial Emotion Recognition (FER) is crucial for applications such as human-computer interaction and mental health diagnostics. This study presents the first empirical comparison of open-source Vision-Language Models (VLMs), including Phi-3.5 Vision and CLIP, against traditional deep learning models VGG19, ResNet-50, and EfficientNet-B0 on the challenging FER-2013 dataset, which contains 35,887 low-resolution grayscale images across seven emotion classes. To address the mismatch between VLM training assumptions and the noisy nature of FER data, we introduce a novel pipeline that integrates GFPGAN-based image restoration with FER evaluation. Results show that traditional models, particularly EfficientNet-B0 (86.44%) and ResNet-50 (85.72%), significantly outperform VLMs like CLIP (64.07%) and Phi-3.5 Vision (51.66%), highlighting the limitations of VLMs in low-quality visual tasks. In addition to performance evaluation using precision, recall, F1-score, and accuracy, we provide a detailed computational cost analysis covering preprocessing, training, inference, and evaluation phases, offering practical insights for deployment. This work underscores the need for adapting VLMs to noisy environments and provides a reproducible benchmark for future research in emotion recognition.

☆ Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency

Yanbiao Ma, Wei Dai, Bowei Liu, Jiayi Chen, Wenke Huang, Guancheng Wan, Zhiwu Lu, Junchi Yan

Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for the causing of this gap e.g. sampling bias, noise etc. In the era of foundation models, we show that when leveraging the off-the-shelf (vision) foundation models (e.g., CLIP, DINOv2) for feature extraction, the geometric shapes of the resulting feature distributions exhibit remarkable transferability across domains and datasets. To verify its practical usefulness, we embody our geometric knowledge-guided distribution calibration framework in two popular and challenging settings: federated learning and long-tailed recognition. In the federated setting, we devise a technique of acquiring the global geometric shape under privacy constraints, then leverage this knowledge to generate new samples for clients, in the aim of bridging the gap between local and global observations. In long-tailed learning, it utilizes the geometric knowledge transferred from sample-rich categories to recover the true distribution for sample-scarce tail classes. Comprehensive experiments show that our proposed geometric knowledge-guided distribution calibration effectively overcomes information deficits caused by data heterogeneity and sample imbalance, with boosted performance across benchmarks.

comment: 15 pages, CVPR Oral

☆ 2D Gaussians Meet Visual Tokenizer

Yiang Shi, Xiaoyang Guo, Wei Yin, Mingkai Jia, Qian Zhang, Xiaolin Hu, Wenyu Liu, Xinggang Wan

The image tokenizer is a critical component in AR image generation, as it determines how rich and structured visual content is encoded into compact representations. Existing quantization-based tokenizers such as VQ-GAN primarily focus on appearance features like texture and color, often neglecting geometric structures due to their patch-based design. In this work, we explored how to incorporate more visual information into the tokenizer and proposed a new framework named Visual Gaussian Quantization (VGQ), a novel tokenizer paradigm that explicitly enhances structural modeling by integrating 2D Gaussians into traditional visual codebook quantization frameworks. Our approach addresses the inherent limitations of naive quantization methods such as VQ-GAN, which struggle to model structured visual information due to their patch-based design and emphasis on texture and color. In contrast, VGQ encodes image latents as 2D Gaussian distributions, effectively capturing geometric and spatial structures by directly modeling structure-related parameters such as position, rotation and scale. We further demonstrate that increasing the density of 2D Gaussians within the tokens leads to significant gains in reconstruction fidelity, providing a flexible trade-off between token efficiency and visual richness. On the ImageNet 256x256 benchmark, VGQ achieves strong reconstruction quality with an rFID score of 1.00. Furthermore, by increasing the density of 2D Gaussians within the tokens, VGQ gains a significant boost in reconstruction capability and achieves a state-of-the-art reconstruction rFID score of 0.556 and a PSNR of 24.93, substantially outperforming existing methods. Codes will be released soon.

☆ Bridging the Gap: Doubles Badminton Analysis with Singles-Trained Models

Seungheon Baek, Jinhyuk Yun

Badminton is known as one of the fastest racket sports in the world. Despite doubles matches being more prevalent in international tournaments than singles, previous research has mainly focused on singles due to the challenges in data availability and multi-person tracking. To address this gap, we designed an approach that transfers singles-trained models to doubles analysis. We extracted keypoints from the ShuttleSet single matches dataset using ViT-Pose and embedded them through a contrastive learning framework based on ST-GCN. To improve tracking stability, we incorporated a custom multi-object tracking algorithm that resolves ID switching issues from fast and overlapping player movements. A Transformer-based classifier then determines shot occurrences based on the learned embeddings. Our findings demonstrate the feasibility of extending pose-based shot recognition to doubles badminton, broadening analytics capabilities. This work establishes a foundation for doubles-specific datasets to enhance understanding of this predominant yet understudied format of the fast racket sport.

comment: 14 pages, 7 figures

☆ AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes

Tianyi Xu, Fan Zhang, Boxin Shi, Tianfan Xue, Yujin Wang

Mainstream high dynamic range imaging techniques typically rely on fusing multiple images captured with different exposure setups (shutter speed and ISO). A good balance between shutter speed and ISO is crucial for achieving high-quality HDR, as high ISO values introduce significant noise, while long shutter speeds can lead to noticeable motion blur. However, existing methods often overlook the complex interaction between shutter speed and ISO and fail to account for motion blur effects in dynamic scenes. In this work, we propose AdaptiveAE, a reinforcement learning-based method that optimizes the selection of shutter speed and ISO combinations to maximize HDR reconstruction quality in dynamic environments. AdaptiveAE integrates an image synthesis pipeline that incorporates motion blur and noise simulation into our training procedure, leveraging semantic information and exposure histograms. It can adaptively select optimal ISO and shutter speed sequences based on a user-defined exposure time budget, and find a better exposure schedule than traditional solutions. Experimental results across multiple datasets demonstrate that it achieves the state-of-the-art performance.

comment: Accepted to ICCV 2025

☆ Multi-view Clustering via Bi-level Decoupling and Consistency Learning

Shihao Dong, Yuhui Zheng, Huiying Xu, Xinzhong Zhu

Multi-view clustering has shown to be an effective method for analyzing underlying patterns in multi-view data. The performance of clustering can be improved by learning the consistency and complementarity between multi-view features, however, cluster-oriented representation learning is often overlooked. In this paper, we propose a novel Bi-level Decoupling and Consistency Learning framework (BDCL) to further explore the effective representation for multi-view data to enhance inter-cluster discriminability and intra-cluster compactness of features in multi-view clustering. Our framework comprises three modules: 1) The multi-view instance learning module aligns the consistent information while preserving the private features between views through reconstruction autoencoder and contrastive learning. 2) The bi-level decoupling of features and clusters enhances the discriminability of feature space and cluster space. 3) The consistency learning module treats the different views of the sample and their neighbors as positive pairs, learns the consistency of their clustering assignments, and further compresses the intra-cluster space. Experimental results on five benchmark datasets demonstrate the superiority of the proposed method compared with the SOTA methods. Our code is published on https://github.com/LouisDong95/BDCL.

☆ ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environments

Jingwen Yu, Jiayi Yang, Anjun Hu, Jiankun Wang, Ping Tan, Hong Zhang

Loop closure detection is important for simultaneous localization and mapping (SLAM), which associates current observations with historical keyframes, achieving drift correction and global relocalization. However, a falsely detected loop can be fatal, and this is especially difficult in repetitive environments where appearance-based features fail due to the high similarity. Therefore, verification of a loop closure is a critical step in avoiding false positive detections. Existing works in loop closure verification predominantly focus on learning invariant appearance features, neglecting the prior knowledge of the robot's spatial-temporal motion cue, i.e., trajectory. In this letter, we propose ROVER, a loop closure verification method that leverages the historical trajectory as a prior constraint to reject false loops in challenging repetitive environments. For each loop candidate, it is first used to estimate the robot trajectory with pose-graph optimization. This trajectory is then submitted to a scoring scheme that assesses its compliance with the trajectory without the loop, which we refer to as the trajectory prior, to determine if the loop candidate should be accepted. Benchmark comparisons and real-world experiments demonstrate the effectiveness of the proposed method. Furthermore, we integrate ROVER into state-of-the-art SLAM systems to verify its robustness and efficiency. Our source code and self-collected dataset are available at https://github.com/jarvisyjw/ROVER.

comment: 8 pages, 9 figures

☆ CORENet: Cross-Modal 4D Radar Denoising Network with LiDAR Supervision for Autonomous Driving

Fuyang Liu, Jilin Mei, Fangyuan Mao, Chen Min, Yan Xing, Yu Hu

4D radar-based object detection has garnered great attention for its robustness in adverse weather conditions and capacity to deliver rich spatial information across diverse driving scenarios. Nevertheless, the sparse and noisy nature of 4D radar point clouds poses substantial challenges for effective perception. To address the limitation, we present CORENet, a novel cross-modal denoising framework that leverages LiDAR supervision to identify noise patterns and extract discriminative features from raw 4D radar data. Designed as a plug-and-play architecture, our solution enables seamless integration into voxel-based detection frameworks without modifying existing pipelines. Notably, the proposed method only utilizes LiDAR data for cross-modal supervision during training while maintaining full radar-only operation during inference. Extensive evaluation on the challenging Dual-Radar dataset, which is characterized by elevated noise level, demonstrates the effectiveness of our framework in enhancing detection robustness. Comprehensive experiments validate that CORENet achieves superior performance compared to existing mainstream approaches.

comment: 8 pages, 5 figures, Accepted to IROS 2025

☆ FAMNet: Integrating 2D and 3D Features for Micro-expression Recognition via Multi-task Learning and Hierarchical Attention

Liangyu Fu, Xuecheng Wu, Danlei Huang, Xinyi Yin

Micro-expressions recognition (MER) has essential application value in many fields, but the short duration and low intensity of micro-expressions (MEs) bring considerable challenges to MER. The current MER methods in deep learning mainly include three data loading methods: static images, dynamic image sequence, and a combination of the two streams. How to effectively extract MEs' fine-grained and spatiotemporal features has been difficult to solve. This paper proposes a new MER method based on multi-task learning and hierarchical attention, which fully extracts MEs' omni-directional features by merging 2D and 3D CNNs. The fusion model consists of a 2D CNN AMNet2D and a 3D CNN AMNet3D, with similar structures consisting of a shared backbone network Resnet18 and attention modules. During training, the model adopts different data loading methods to adapt to two specific networks respectively, jointly trains on the tasks of MER and facial action unit detection (FAUD), and adopts the parameter hard sharing for information association, which further improves the effect of the MER task, and the final fused model is called FAMNet. Extensive experimental results show that our proposed FAMNet significantly improves task performance. On the SAMM, CASME II and MMEW datasets, FAMNet achieves 83.75% (UAR) and 84.03% (UF1). Furthermore, on the challenging CAS(ME)$^3$ dataset, FAMNet achieves 51% (UAR) and 43.42% (UF1).

comment: 8 pages, 6 figures. Accepted to IJCNN 2025

☆ Towards Understanding and Harnessing the Transferability of Prognostic Knowledge in Computational Pathology

Pei Liu, Luping Ji, Jiaxiang Gou, Xiangxiang Zeng

Whole-Slide Image (WSI) is an important tool for evaluating the prognosis of cancer patients. Present WSI-based prognosis studies generally follow a conventional paradigm -- cancer-specific model development -- where one cancer disease corresponds to one model and this model cannot make use of the prognostic knowledge from others. Despite its notable success in recent years, this paradigm has inherent limitations and has always been struggling with practical requirements: (i) scaling to the rare tumor diseases with very limited samples and (ii) benefiting from the generalizable prognostic knowledge in other cancers. To this end, this paper presents the first systematic study on Prognostic Knowledge Transfer in Pathology, called Path-PKT. It comprises three main parts. (1) We curate a large dataset (UNI2-h-DSS) with 13 cancers and use it to evaluate the transferability of prognostic knowledge between different cancers computationally. (2) We design experiments to understand what factors affect knowledge transfer and what causes positive transfers. (3) Motivated by empirical findings, we propose a new baseline approach (MoE-PKT) with a routing mechanism to utilize the generalizable prognostic knowledge in other cancers. Finally, we show the transferability of source models to rare tumor diseases. This study could lay solid foundations for the study of knowledge transfer in WSI-based cancer prognosis. Source code is available at https://github.com/liupei101/Path-PKT.

comment: 15 pages (13 figures and 5 tables)

☆ Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations

Wenyong Zhou, Yuxin Cheng, Zhengwu Liu, Taiqiang Wu, Chen Zhang, Ngai Wong

Implicit Neural Representations (INRs) encode discrete signals in a continuous manner using neural networks, demonstrating significant value across various multimedia applications. However, the vulnerability of INRs presents a critical challenge for their real-world deployments, as the network weights might be subjected to unavoidable perturbations. In this work, we investigate the robustness of INRs for the first time and find that even minor perturbations can lead to substantial performance degradation in the quality of signal reconstruction. To mitigate this issue, we formulate the robustness problem in INRs by minimizing the difference between loss with and without weight perturbations. Furthermore, we derive a novel robust loss function to regulate the gradient of the reconstruction loss with respect to weights, thereby enhancing the robustness. Extensive experiments on reconstruction tasks across multiple modalities demonstrate that our method achieves up to a 7.5~dB improvement in peak signal-to-noise ratio (PSNR) values compared to original INRs under noisy conditions.

comment: 4 pages, 7 figures

☆ AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results

Chao Wang, Francesco Banterle, Bin Ren, Radu Timofte, Xin Lu, Yufeng Peng, Chengjie Ge, Zhijing Sun, Ziang Zhou, Zihao Li, Zishun Liao, Qiyu Kang, Xueyang Fu, Zheng-Jun Zha, Zhijing Sun, Xingbo Wang, Kean Liu, Senyan Xu, Yang Qiu, Yifan Ding, Gabriel Eilertsen, Jonas Unger, Zihao Wang, Ke Wu, Jinshan Pan, Zhen Liu, Zhongyang Li, Shuaicheng Liu, S. M Nadim Uddin

This paper presents a comprehensive review of the AIM 2025 Challenge on Inverse Tone Mapping (ITM). The challenge aimed to push forward the development of effective ITM algorithms for HDR image reconstruction from single LDR inputs, focusing on perceptual fidelity and numerical consistency. A total of \textbf{67} participants submitted \textbf{319} valid results, from which the best five teams were selected for detailed analysis. This report consolidates their methodologies and performance, with the lowest PU21-PSNR among the top entries reaching 29.22 dB. The analysis highlights innovative strategies for enhancing HDR reconstruction quality and establishes strong benchmarks to guide future research in inverse tone mapping.

☆ Distribution-Aware Hadamard Quantization for Hardware-Efficient Implicit Neural Representations

Wenyong Zhou, Jiachen Ren, Taiqiang Wu, Yuxin Cheng, Zhengwu Liu, Ngai Wong

Implicit Neural Representations (INRs) encode discrete signals using Multi-Layer Perceptrons (MLPs) with complex activation functions. While INRs achieve superior performance, they depend on full-precision number representation for accurate computation, resulting in significant hardware overhead. Previous INR quantization approaches have primarily focused on weight quantization, offering only limited hardware savings due to the lack of activation quantization. To fully exploit the hardware benefits of quantization, we propose DHQ, a novel distribution-aware Hadamard quantization scheme that targets both weights and activations in INRs. Our analysis shows that the weights in the first and last layers have distributions distinct from those in the intermediate layers, while the activations in the last layer differ significantly from those in the preceding layers. Instead of customizing quantizers individually, we utilize the Hadamard transformation to standardize these diverse distributions into a unified bell-shaped form, supported by both empirical evidence and theoretical analysis, before applying a standard quantizer. To demonstrate the practical advantages of our approach, we present an FPGA implementation of DHQ that highlights its hardware efficiency. Experiments on diverse image reconstruction tasks show that DHQ outperforms previous quantization methods, reducing latency by 32.7\%, energy consumption by 40.1\%, and resource utilization by up to 98.3\% compared to full-precision counterparts.

comment: 6 pages, 7 figures

☆ MINR: Efficient Implicit Neural Representations for Multi-Image Encoding

Wenyong Zhou, Taiqiang Wu, Zhengwu Liu, Yuxin Cheng, Chen Zhang, Ngai Wong

Implicit Neural Representations (INRs) aim to parameterize discrete signals through implicit continuous functions. However, formulating each image with a separate neural network~(typically, a Multi-Layer Perceptron (MLP)) leads to computational and storage inefficiencies when encoding multi-images. To address this issue, we propose MINR, sharing specific layers to encode multi-image efficiently. We first compare the layer-wise weight distributions for several trained INRs and find that corresponding intermediate layers follow highly similar distribution patterns. Motivated by this, we share these intermediate layers across multiple images while preserving the input and output layers as input-specific. In addition, we design an extra novel projection layer for each image to capture its unique features. Experimental results on image reconstruction and super-resolution tasks demonstrate that MINR can save up to 60\% parameters while maintaining comparable performance. Particularly, MINR scales effectively to handle 100 images, maintaining an average peak signal-to-noise ratio (PSNR) of 34 dB. Further analysis of various backbones proves the robustness of the proposed MINR.

comment: 4 pages, 4 figures

☆ STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models

Tinh-Anh Nguyen-Nhu, Triet Dao Hoang Minh, Dat To-Thanh, Phuc Le-Gia, Tuan Vo-Lan, Tien-Huy Nguyen

Vision-language models (VLMs) have emerged as powerful tools for enabling automated traffic analysis; however, current approaches often demand substantial computational resources and struggle with fine-grained spatio-temporal understanding. This paper introduces STER-VLM, a computationally efficient framework that enhances VLM performance through (1) caption decomposition to tackle spatial and temporal information separately, (2) temporal frame selection with best-view filtering for sufficient temporal information, and (3) reference-driven understanding for capturing fine-grained motion and dynamic context and (4) curated visual/textual prompt techniques. Experimental results on the WTS \cite{kong2024wts} and BDD \cite{BDD} datasets demonstrate substantial gains in semantic richness and traffic scene interpretation. Our framework is validated through a decent test score of 55.655 in the AI City Challenge 2025 Track 2, showing its effectiveness in advancing resource-efficient and accurate traffic analysis for real-world applications.

comment: ICCV Workshop 2025

☆ Vision Transformers for Kidney Stone Image Classification: A Comparative Study with CNNs

Ivan Reyes-Amezcua, Francisco Lopez-Tiro, Clement Larose, Andres Mendez-Vazquez, Gilberto Ochoa-Ruiz, Christian Daul

Kidney stone classification from endoscopic images is critical for personalized treatment and recurrence prevention. While convolutional neural networks (CNNs) have shown promise in this task, their limited ability to capture long-range dependencies can hinder performance under variable imaging conditions. This study presents a comparative analysis between Vision Transformers (ViTs) and CNN-based models, evaluating their performance on two ex vivo datasets comprising CCD camera and flexible ureteroscope images. The ViT-base model pretrained on ImageNet-21k consistently outperformed a ResNet50 baseline across multiple imaging conditions. For instance, in the most visually complex subset (Section patches from endoscopic images), the ViT model achieved 95.2% accuracy and 95.1% F1-score, compared to 64.5% and 59.3% with ResNet50. In the mixed-view subset from CCD-camera images, ViT reached 87.1% accuracy versus 78.4% with CNN. These improvements extend across precision and recall as well. The results demonstrate that ViT-based architectures provide superior classification performance and offer a scalable alternative to conventional CNNs for kidney stone image analysis.

☆ Revisiting MLLM Token Technology through the Lens of Classical Visual Coding

Jinming Liu, Junyan Lin, Yuntao Wei, Kele Shao, Keda Tao, Jianguo Huang, Xudong Yang, Zhibo Chen, Huan Wang, Xin Jin

Classical visual coding and Multimodal Large Language Model (MLLM) token technology share the core objective - maximizing information fidelity while minimizing computational cost. Therefore, this paper reexamines MLLM token technology, including tokenization, token compression, and token reasoning, through the established principles of long-developed visual coding area. From this perspective, we (1) establish a unified formulation bridging token technology and visual coding, enabling a systematic, module-by-module comparative analysis; (2) synthesize bidirectional insights, exploring how visual coding principles can enhance MLLM token techniques' efficiency and robustness, and conversely, how token technology paradigms can inform the design of next-generation semantic visual codecs; (3) prospect for promising future research directions and critical unsolved challenges. In summary, this study presents the first comprehensive and structured technology comparison of MLLM token and visual coding, paving the way for more efficient multimodal models and more powerful visual codecs simultaneously.

☆ Hierarchy-Consistent Learning and Adaptive Loss Balancing for Hierarchical Multi-Label Classification

Ruobing Jiang, Mengzhe Liu, Haobing Liu, Yanwei Yu

Hierarchical Multi-Label Classification (HMC) faces critical challenges in maintaining structural consistency and balancing loss weighting in Multi-Task Learning (MTL). In order to address these issues, we propose a classifier called HCAL based on MTL integrated with prototype contrastive learning and adaptive task-weighting mechanisms. The most significant advantage of our classifier is semantic consistency including both prototype with explicitly modeling label and feature aggregation from child classes to parent classes. The other important advantage is an adaptive loss-weighting mechanism that dynamically allocates optimization resources by monitoring task-specific convergence rates. It effectively resolves the "one-strong-many-weak" optimization bias inherent in traditional MTL approaches. To further enhance robustness, a prototype perturbation mechanism is formulated by injecting controlled noise into prototype to expand decision boundaries. Additionally, we formalize a quantitative metric called Hierarchical Violation Rate (HVR) as to evaluate hierarchical consistency and generalization. Extensive experiments across three datasets demonstrate both the higher classification accuracy and reduced hierarchical violation rate of the proposed classifier over baseline models.

comment: 10 pages, 7 figures, accepted by CIKM 2025

☆ EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis

Shuai Tan, Bin Ji

Achieving disentangled control over multiple facial motions and accommodating diverse input modalities greatly enhances the application and entertainment of the talking head generation. This necessitates a deep exploration of the decoupling space for facial features, ensuring that they a) operate independently without mutual interference and b) can be preserved to share with different modal inputs, both aspects often neglected in existing methods. To address this gap, this paper proposes EDTalk++, a novel full disentanglement framework for controllable talking head generation. Our framework enables individual manipulation of mouth shape, head pose, eye movement, and emotional expression, conditioned on video or audio inputs. Specifically, we employ four lightweight modules to decompose the facial dynamics into four distinct latent spaces representing mouth, pose, eye, and expression, respectively. Each space is characterized by a set of learnable bases whose linear combinations define specific motions. To ensure independence and accelerate training, we enforce orthogonality among bases and devise an efficient training strategy to allocate motion responsibilities to each space without relying on external knowledge. The learned bases are then stored in corresponding banks, enabling shared visual priors with audio input. Furthermore, considering the properties of each space, we propose an Audio-to-Motion module for audio-driven talking head synthesis. Experiments are conducted to demonstrate the effectiveness of EDTalk++.

comment: 17 pages,15 figures. arXiv admin note: substantial text overlap with arXiv:2404.01647

♻ ☆ LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning

Chenjian Gao, Lihe Ding, Xin Cai, Zhanpeng Huang, Zibin Wang, Tianfan Xue

Video editing using diffusion models has achieved remarkable results in generating high-quality edits for videos. However, current methods often rely on large-scale pretraining, limiting flexibility for specific edits. First-frame-guided editing provides control over the first frame, but lacks flexibility over subsequent frames. To address this, we propose a mask-based LoRA (Low-Rank Adaptation) tuning method that adapts pretrained Image-to-Video (I2V) models for flexible video editing. Our key innovation is using a spatiotemporal mask to strategically guide the LoRA fine-tuning process. This teaches the model two distinct skills: first, to interpret the mask as a command to either preserve content from the source video or generate new content in designated regions. Second, for these generated regions, LoRA learns to synthesize either temporally consistent motion inherited from the video or novel appearances guided by user-provided reference frames. This dual-capability LoRA grants users control over the edit's entire temporal evolution, allowing complex transformations like an object rotating or a flower blooming. Experimental results show our method achieves superior video editing performance compared to baseline methods. Project Page: https://cjeen.github.io/LoRAEdit

comment: 9 pages

♻ ☆ Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

Zeren Jiang, Chuanxia Zheng, Iro Laina, Diane Larlus, Andrea Vedaldi

We introduce Geo4D, a method to repurpose video diffusion models for monocular 3D reconstruction of dynamic scenes. By leveraging the strong dynamic priors captured by large-scale pre-trained video models, Geo4D can be trained using only synthetic data while generalizing well to real data in a zero-shot manner. Geo4D predicts several complementary geometric modalities, namely point, disparity, and ray maps. We propose a new multi-modal alignment algorithm to align and fuse these modalities, as well as a sliding window approach at inference time, thus enabling robust and accurate 4D reconstruction of long videos. Extensive experiments across multiple benchmarks show that Geo4D significantly surpasses state-of-the-art video depth estimation methods.

comment: 17 pages, 6 figures, ICCV 2025 Highlight, Project page: https://geo4d.github.io/

♻ ☆ RadGPT: Constructing 3D Image-Text Tumor Datasets

Pedro R. A. S. Bassi, Mehmet Can Yavuz, Kang Wang, Xiaoxi Chen, Wenxuan Li, Sergio Decherchi, Andrea Cavalli, Yang Yang, Alan Yuille, Zongwei Zhou

Cancers identified in CT scans are usually accompanied by detailed radiology reports, but publicly available CT datasets often lack these essential reports. This absence limits their usefulness for developing accurate report generation AI. To address this gap, we present AbdomenAtlas 3.0, the first public, high-quality abdominal CT dataset with detailed, expert-reviewed radiology reports. All reports are paired with per-voxel masks and they describe liver, kidney and pancreatic tumors. AbdomenAtlas 3.0 has 9,262 triplets of CT, mask and report--3,955 with tumors. These CT scans come from 17 public datasets. Besides creating the reports for these datasets, we expanded their number of tumor masks by 4.2x, identifying 3,011 new tumor cases. Notably, the reports in AbdomenAtlas 3.0 are more standardized, and generated faster than traditional human-made reports. They provide details like tumor size, location, attenuation and surgical resectability. These reports were created by 12 board-certified radiologists using our proposed RadGPT, a novel framework that converted radiologist-revised tumor segmentation masks into structured and narrative reports. Besides being a dataset creation tool, RadGPT can also become a fully-automatic, segmentation-assisted report generation method. We benchmarked this method and 5 state-of-the-art report generation vision-language models. Our results show that segmentation strongly improves tumor detection in AI-made reports.

♻ ☆ DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting

Zeren Jiang, Shaofei Wang, Siyu Tang

Creating relightable and animatable human avatars from monocular videos is a rising research topic with a range of applications, e.g. virtual reality, sports, and video games. Previous works utilize neural fields together with physically based rendering (PBR), to estimate geometry and disentangle appearance properties of human avatars. However, one drawback of these methods is the slow rendering speed due to the expensive Monte Carlo ray tracing. To tackle this problem, we proposed to distill the knowledge from implicit neural fields (teacher) to explicit 2D Gaussian splatting (student) representation to take advantage of the fast rasterization property of Gaussian splatting. To avoid ray-tracing, we employ the split-sum approximation for PBR appearance. We also propose novel part-wise ambient occlusion probes for shadow computation. Shadow prediction is achieved by querying these probes only once per pixel, which paves the way for real-time relighting of avatars. These techniques combined give high-quality relighting results with realistic shadow effects. Our experiments demonstrate that the proposed student model achieves comparable or even better relighting results with our teacher model while being 370 times faster at inference time, achieving a 67 FPS rendering speed.

comment: 17 pages, 9 figures, ICCV 2025 Findings Oral, Project pages: https://jzr99.github.io/DNF-Avatar/

♻ ☆ Assessment of Using Synthetic Data in Brain Tumor Segmentation

Aditi Jahagirdar, Sameer Joshi

Manual brain tumor segmentation from MRI scans is challenging due to tumor heterogeneity, scarcity of annotated data, and class imbalance in medical imaging datasets. Synthetic data generated by generative models has the potential to mitigate these issues by improving dataset diversity. This study investigates, as a proof of concept, the impact of incorporating synthetic MRI data, generated using a pre-trained GAN model, into training a U-Net segmentation network. Experiments were conducted using real data from the BraTS 2020 dataset, synthetic data generated with the medigan library, and hybrid datasets combining real and synthetic samples in varying proportions. While overall quantitative performance (Dice coefficient, IoU, precision, recall, accuracy) was comparable between real-only and hybrid-trained models, qualitative inspection suggested that hybrid datasets, particularly with 40% real and 60% synthetic data, improved whole tumor boundary delineation. However, region-wise accuracy for the tumor core and the enhancing tumor remained lower, indicating a persistent class imbalance. The findings support the feasibility of synthetic data as an augmentation strategy for brain tumor segmentation, while highlighting the need for larger-scale experiments, volumetric data consistency, and mitigating class imbalance in future work.

comment: Updates include improved references, clearer table column title, and minor language corrections

♻ ☆ Slot Attention with Re-Initialization and Self-Distillation ACM MM 2025

Rongzhen Zhao, Yi Zhao, Juho Kannala, Joni Pajarinen

Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL typically aggregates object superpixels into slots by iteratively applying competitive cross attention, known as Slot Attention, with the slots as the query. However, once initialized, these slots are reused naively, causing redundant slots to compete with informative ones for representing objects. This often results in objects being erroneously segmented into parts. Additionally, mainstream methods derive supervision signals solely from decoding slots into the input's reconstruction, overlooking potential supervision based on internal information. To address these issues, we propose Slot Attention with re-Initialization and self-Distillation (DIAS): $\emph{i)}$ We reduce redundancy in the aggregated slots and re-initialize extra aggregation to update the remaining slots; $\emph{ii)}$ We drive the bad attention map at the first aggregation iteration to approximate the good at the last iteration to enable self-distillation. Experiments demonstrate that DIAS achieves state-of-the-art on OCL tasks like object discovery and recognition, while also improving advanced visual prediction and reasoning. Our source code and model checkpoints are available on https://github.com/Genera1Z/DIAS.

comment: Accepted by ACM MM 2025

♻ ☆ AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs

Yi-Ting Shen, Sungmin Eum, Doheon Lee, Rohit Shete, Chiao-Yi Wang, Heesung Kwon, Shuvra S. Bhattacharyya

Composed pose retrieval (CPR) enables users to search for human poses by specifying a reference pose and a transition description, but progress in this field is hindered by the scarcity and inconsistency of annotated pose transitions. Existing CPR datasets rely on costly human annotations or heuristic-based rule generation, both of which limit scalability and diversity. In this work, we introduce AutoComPose, the first framework that leverages multimodal large language models (MLLMs) to automatically generate rich and structured pose transition descriptions. Our method enhances annotation quality by structuring transitions into fine-grained body part movements and introducing mirrored/swapped variations, while a cyclic consistency constraint ensures logical coherence between forward and reverse transitions. To advance CPR research, we construct and release two dedicated benchmarks, AIST-CPR and PoseFixCPR, supplementing prior datasets with enhanced attributes. Extensive experiments demonstrate that training retrieval models with AutoComPose yields superior performance over human-annotated and heuristic-based methods, significantly reducing annotation costs while improving retrieval quality. Our work pioneers the automatic annotation of pose transitions, establishing a scalable foundation for future CPR research.

comment: ICCV 2025

♻ ☆ Fully Automated Segmentation of Fiber Bundles in Anatomic Tracing Data

Kyriaki-Margarita Bintsi, Yaël Balbastre, Jingjing Wu, Julia F. Lehman, Suzanne N. Haber, Anastasia Yendiki

Anatomic tracer studies are critical for validating and improving diffusion MRI (dMRI) tractography. However, large-scale analysis of data from such studies is hampered by the labor-intensive process of annotating fiber bundles manually on histological slides. Existing automated methods often miss sparse bundles or require complex post-processing across consecutive sections, limiting their flexibility and generalizability. We present a streamlined, fully automated framework for fiber bundle segmentation in macaque tracer data, based on a U-Net architecture with large patch sizes, foreground aware sampling, and semisupervised pre-training. Our approach eliminates common errors such as mislabeling terminals as bundles, improves detection of sparse bundles by over 20% and reduces the False Discovery Rate (FDR) by 40% compared to the state-of-the-art, all while enabling analysis of standalone slices. This new framework will facilitate the automated analysis of anatomic tracing data at a large scale, generating more ground-truth data that can be used to validate and optimize dMRI tractography methods.

comment: Accepted at CDMRI, MICCAI 2025

♻ ☆ HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model

Hieu T. Nguyen, Yiwen Chen, Vikram Voleti, Varun Jampani, Huaizu Jiang

We introduce HouseCrafter, a novel approach that can lift a floorplan into a complete large 3D indoor scene (e.g., a house). Our key insight is to adapt a 2D diffusion model, which is trained on web-scale images, to generate consistent multi-view color (RGB) and depth (D) images across different locations of the scene. Specifically, the RGB-D images are generated autoregressively in a batch-wise manner along sampled locations based on the floorplan, where previously generated images are used as condition to the diffusion model to produce images at nearby locations. The global floorplan and attention design in the diffusion model ensures the consistency of the generated images, from which a 3D scene can be reconstructed. Through extensive evaluation on the 3D-Front dataset, we demonstrate that HouseCraft can generate high-quality house-scale 3D scenes. Ablation studies also validate the effectiveness of different design choices. We will release our code and model weights. Project page: https://neu-vi.github.io/houseCrafter/

♻ ☆ UltraDfeGAN: Detail-Enhancing Generative Adversarial Networks for High-Fidelity Functional Ultrasound Synthesis

Zhuo Li, Xuhang Chen, Shuqiang Wang, Bin Yuan, Nou Sotheany, Ngeth Rithea

Functional ultrasound (fUS) is a neuroimaging technique known for its high spatiotemporal resolution, enabling non-invasive observation of brain activity through neurovascular coupling. Despite its potential in clinical applications such as neonatal monitoring and intraoperative guidance, the development of fUS faces challenges related to data scarcity and limitations in generating realistic fUS images. This paper explores the use of a generative adversarial network (GAN) framework tailored for fUS image synthesis. The proposed method incorporates architectural enhancements, including feature enhancement modules and normalization techniques, aiming to improve the fidelity and physiological plausibility of generated images. The study evaluates the performance of the framework against existing generative models, demonstrating its capability to produce high-quality fUS images under various experimental conditions. Additionally, the synthesized images are assessed for their utility in downstream tasks, showing improvements in classification accuracy when used for data augmentation. Experimental results are based on publicly available fUS datasets, highlighting the framework's effectiveness in addressing data limitations.

♻ ☆ Vision Backbone Efficient Selection for Image Classification in Low-Data Regimes

Joris Guerin, Shray Bansal, Amirreza Shaban, Paulo Mann, Harshvardhan Gazula

Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is crucial, especially for small datasets, since final performance depends heavily on the quality of the initial feature representations. While prior work has conducted benchmarks across various datasets to identify universal top-performing backbones, we demonstrate that backbone effectiveness is highly dataset-dependent, especially in low-data scenarios where no single backbone consistently excels. To overcome this limitation, we introduce dataset-specific backbone selection as a new research direction and investigate its practical viability in low-data regimes. Since exhaustive evaluation is computationally impractical for large backbone pools, we formalize Vision Backbone Efficient Selection (VIBES) as the problem of searching for high-performing backbones under computational constraints. We define the solution space, propose several heuristics, and demonstrate VIBES feasibility for low-data image classification by performing experiments on four diverse datasets. Our results show that even simple search strategies can find well-suited backbones within a pool of over $1300$ pretrained models, outperforming generic benchmark recommendations within just ten minutes of search time on a single GPU (NVIDIA RTX A5000).

comment: 16 pages, 8 figures, Accepted at BMVC 2025

♻ ☆ Blending 3D Geometry and Machine Learning for Multi-View Stereopsis

Vibhas Vats, Md. Alimoor Reza, David Crandall, Soon-heung Jung

Traditional multi-view stereo (MVS) methods primarily depend on photometric and geometric consistency constraints. In contrast, modern learning-based algorithms often rely on the plane sweep algorithm to infer 3D geometry, applying explicit geometric consistency (GC) checks only as a post-processing step, with no impact on the learning process itself. In this work, we introduce GC MVSNet plus plus, a novel approach that actively enforces geometric consistency of reference view depth maps across multiple source views (multi view) and at various scales (multi scale) during the learning phase (see Fig. 1). This integrated GC check significantly accelerates the learning process by directly penalizing geometrically inconsistent pixels, effectively halving the number of training iterations compared to other MVS methods. Furthermore, we introduce a densely connected cost regularization network with two distinct block designs simple and feature dense optimized to harness dense feature connections for enhanced regularization. Extensive experiments demonstrate that our approach achieves a new state of the art on the DTU and BlendedMVS datasets and secures second place on the Tanks and Temples benchmark. To our knowledge, GC MVSNet plus plus is the first method to enforce multi-view, multi-scale supervised geometric consistency during learning. Our code is available.

comment: A pre-print -- accepted at Neurocomputing. arXiv admin note: substantial text overlap with arXiv:2310.19583

♻ ☆ Vector-Quantized Vision Foundation Models for Object-Centric Learning ACM MM 2025

Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen

Object-Centric Learning (OCL) aggregates image or video feature maps into object-level feature vectors, termed \textit{slots}. It's self-supervision of reconstructing the input from slots struggles with complex object textures, thus Vision Foundation Model (VFM) representations are used as the aggregation input and reconstruction target. Existing methods leverage VFM representations in diverse ways yet fail to fully exploit their potential. In response, we propose a unified architecture, Vector-Quantized VFMs for OCL (VQ-VFM-OCL, or VVO). The key to our unification is simply shared quantizing VFM representations in OCL aggregation and decoding. Experiments show that across different VFMs, aggregators and decoders, our VVO consistently outperforms baselines in object discovery and recognition, as well as downstream visual prediction and reasoning. We also mathematically analyze why VFM representations facilitate OCL aggregation and why their shared quantization as reconstruction targets strengthens OCL supervision. Our source code and model checkpoints are available on https://github.com/Genera1Z/VQ-VFM-OCL.

comment: Accepted by ACM MM 2025

♻ ☆ Vehicle detection from GSV imagery: Predicting travel behaviour for cycling and motorcycling using Computer Vision

Kyriaki, Kokka, Rahul Goel, Ali Abbas, Kerry A. Nice, Luca Martial, SM Labib, Rihuan Ke, Carola Bibiane Schönlieb, James Woodcock

Transportation influence health by shaping exposure to physical activity, air pollution and injury risk. Comparative data on cycling and motorcycling behaviours is scarce, particularly at a global scale. Street view imagery, such as Google Street View (GSV), combined with computer vision, is a valuable resource for efficiently capturing travel behaviour data. This study demonstrates a novel approach using deep learning on street view images to estimate cycling and motorcycling levels across diverse cities worldwide. We utilized data from 185 global cities. The data on mode shares of cycling and motorcycling estimated using travel surveys or censuses. We used GSV images to detect cycles and motorcycles in sampled locations, using 8000 images per city. The YOLOv4 model, fine-tuned using images from six cities, achieved a mean average precision of 89% for detecting cycles and motorcycles. A global prediction model was developed using beta regression with city-level mode shares as outcome, with log transformed explanatory variables of counts of GSV-detected images with cycles and motorcycles, while controlling for population density. We found strong correlations between GSV motorcycle counts and motorcycle mode share (0.78) and moderate correlations between GSV cycle counts and cycling mode share (0.51). Beta regression models predicted mode shares with $R^2$ values of 0.614 for cycling and 0.612 for motorcycling, achieving median absolute errors (MDAE) of 1.3% and 1.4%, respectively. Scatterplots demonstrated consistent prediction accuracy, though cities like Utrecht and Cali were outliers. The model was applied to 60 cities globally for which we didn't have recent mode share data. We provided estimates for some cities in the Middle East, Latin America and East Asia. With computer vision, GSV images capture travel modes and activity, providing insights alongside traditional data sources.

♻ ☆ MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition

Kehua Chen, Haoyang Shen, Lifan Zhong, Mingyi Chen

Handwritten Mathematical Expression Recognition (HMER) methods have made remarkable progress, with most existing HMER approaches based on either a hybrid CNN/RNN-based with GRU architecture or Transformer architectures. Each of these has its strengths and weaknesses. Leveraging different model structures as viewers and effectively integrating their diverse capabilities presents an intriguing avenue for exploration. This involves addressing two key challenges: 1) How to fuse these two methods effectively, and 2) How to achieve higher performance under an appropriate level of complexity. This paper proposes an efficient CNN-Transformer multi-viewer, multi-task approach to enhance the model's recognition performance. Our MMHMER model achieves 63.96%, 62.51%, and 65.46% ExpRate on CROHME14, CROHME16, and CROHME19, outperforming Posformer with an absolute gain of 1.28%, 1.48%, and 0.58%. The main contribution of our approach is that we propose a new multi-view, multi-task framework that can effectively integrate the strengths of CNN and Transformer. By leveraging the feature extraction capabilities of CNN and the sequence modeling capabilities of Transformer, our model can better handle the complexity of handwritten mathematical expressions.

comment: 7 pages;2 figures

♻ ☆ SlotMatch: Distilling Temporally Consistent Object-Centric Representations for Unsupervised Video Segmentation

Diana-Nicoleta Grigore, Neelu Madan, Andreas Mogelmose, Thomas B. Moeslund, Radu Tudor Ionescu

Unsupervised video segmentation is a challenging computer vision task, especially due to the lack of supervisory signals coupled with the complexity of visual scenes. To overcome this challenge, state-of-the-art models based on slot attention often have to rely on large and computationally expensive neural architectures. To this end, we propose a simple knowledge distillation framework that effectively transfers object-centric representations to a lightweight student. The proposed framework, called SlotMatch, aligns corresponding teacher and student slots via the cosine similarity, requiring no additional distillation objectives or auxiliary supervision. The simplicity of SlotMatch is confirmed via theoretical and empirical evidence, both indicating that integrating additional losses is redundant. We conduct experiments on two datasets to compare the state-of-the-art teacher model, SlotContrast, with our distilled student. The results show that our student based on SlotMatch matches and even outperforms its teacher, while using 3.6x less parameters and running 1.9x faster. Moreover, our student surpasses previous unsupervised video segmentation models.

♻ ☆ LEGO: Learning and Graph-Optimized Modular Tracker for Online Multi-Object Tracking with Point Clouds

Zhenrong Zhang, Jianan Liu, Yuxuan Xia, Tao Huang, Qing-Long Han, Hongbin Liu

Online multi-object tracking (MOT) plays a pivotal role in autonomous systems. The state-of-the-art approaches usually employ a tracking-by-detection method, and data association plays a critical role. This paper proposes a learning and graph-optimized (LEGO) modular tracker to improve data association performance in the existing literature. The proposed LEGO tracker integrates graph optimization and self-attention mechanisms, which efficiently formulate the association score map, facilitating the accurate and efficient matching of objects across time frames. To further enhance the state update process, the Kalman filter is added to ensure consistent tracking by incorporating temporal coherence in the object states. Our proposed method utilizing LiDAR alone has shown exceptional performance compared to other online tracking approaches, including LiDAR-based and LiDAR-camera fusion-based methods. LEGO ranked 1st at the time of submitting results to KITTI object tracking evaluation ranking board and remains 2nd at the time of submitting this paper, among all online trackers in the KITTI MOT benchmark for cars1

♻ ☆ Disentangled Representation Learning with the Gromov-Monge Gap ICLR 2025

Théo Uscidda, Luca Eyring, Karsten Roth, Fabian Theis, Zeynep Akata, Marco Cuturi

Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. Although remarkably challenging to solve in theory, disentanglement is often achieved in practice through prior matching. Furthermore, recent works have shown that prior matching approaches can be enhanced by leveraging geometrical considerations, e.g., by learning representations that preserve geometric features of the data, such as distances or angles between points. However, matching the prior while preserving geometric features is challenging, as a mapping that fully preserves these features while aligning the data distribution with the prior does not exist in general. To address these challenges, we introduce a novel approach to disentangled representation learning based on quadratic optimal transport. We formulate the problem using Gromov-Monge maps that transport one distribution onto another with minimal distortion of predefined geometric features, preserving them as much as can be achieved. To compute such maps, we propose the Gromov-Monge-Gap (GMG), a regularizer quantifying whether a map moves a reference distribution with minimal geometry distortion. We demonstrate the effectiveness of our approach for disentanglement across four standard benchmarks, outperforming other methods leveraging geometric considerations.

comment: ICLR 2025

♻ ☆ Rethinking Weight-Averaged Model-merging

Hu Wang, Congbo Ma, Ibrahim Almakky, Ian Reid, Gustavo Carneiro, Mohammad Yaqub

Model merging, particularly through weight averaging, has shown surprising effectiveness in saving computations and improving model performance without any additional training. However, the interpretability of why and how this technique works remains unclear. In this work, we reinterpret weight-averaged model merging through the lens of interpretability and provide empirical insights into the underlying mechanisms that govern its behavior. We approach the problem from three perspectives: (1) we analyze the learned weight structures and demonstrate that model weights encode structured representations that help explain the compatibility of weight averaging; (2) we compare averaging in weight space and feature space across diverse model architectures (CNNs and ViTs) and datasets, aiming to expose under which circumstances what combination paradigm will work more effectively; (3) we study the effect of parameter scaling on prediction stability, highlighting how weight averaging acts as a form of regularization that contributes to robustness. By framing these analyses in an interpretability context, our work contributes to a more transparent and systematic understanding of model merging for stakeholders interested in the safety and reliability of untrained model combination methods. The code is available at https://github.com/billhhh/Rethink-Merge.

♻ ☆ SBP-YOLO:A Lightweight Real-Time Model for Detecting Speed Bumps and Potholes

Chuanqi Liang, Jie Fu, Miao Yu, Lei Luo

Reliable and real-time detection of road speed bumps and potholes is crucial for anticipatory perception in advanced suspension systems, enabling timely and adaptive damping control. Achieving high accuracy and efficiency on embedded platforms remains challenging due to limited computational resources and the small scale of distant targets. This paper presents SBP-YOLO, a lightweight and high-speed detection framework tailored for bump and pothole recognition. Based on YOLOv11n, the model integrates GhostConv and VoVGSCSPC modules into the backbone and neck to reduce computation while enhancing multi-scale semantic features. To improve small-object detection, a P2-level branch is introduced with a lightweight and efficient detection head LEDH mitigating the added computational overhead without compromising accuracy. A hybrid training strategy combining NWD loss, backbone-level knowledge distillation, and Albumentations-driven augmentation further enhances localization precision and robustness. Experiments show that SBP-YOLO achieves 87.0 percent mAP, outperforming the YOLOv11n baseline by 5.8 percent. After TensorRT FP16 quantization, it runs at 139.5 FPS on Jetson AGX Xavier, delivering a 12.4 percent speedup over the P2-enhanced YOLOv11. These results validate the effectiveness of the proposed method for fast and low-latency road condition perception in embedded suspension control systems.

comment: 14pages,10figures

♻ ☆ EmoSEM: Segment and Explain Emotion Stimuli in Visual Art

Jing Zhang, Dan Guo, Zhangbin Li, Meng Wang

This paper focuses on a key challenge in visual emotion understanding: given an art image, the model pinpoints pixel regions that trigger a specific human emotion, and generates linguistic explanations for it. Despite advances in general segmentation, pixel-level emotion understanding still faces a dual challenge: first, the subjectivity of emotion limits general segmentation models like SAM to adapt to emotion-oriented segmentation tasks; and second, the abstract nature of art expression makes it hard for captioning models to balance pixel-level semantics and emotion reasoning. To solve the above problems, this paper proposes the Emotion stimuli Segmentation and Explanation Model (EmoSEM) model to endow the segmentation framework with emotion comprehension capability. First, to enable the model to perform segmentation under the guidance of emotional intent well, we introduce an emotional prompt with a learnable mask token as the conditional input for segmentation decoding. Then, we design an emotion projector to establish the association between emotion and visual features. Next, more importantly, to address emotion-visual stimuli alignment, we develop a lightweight prefix adapter, a module that fuses the learned emotional mask with the corresponding emotion into a unified representation compatible with the language model. Finally, we input the joint visual, mask, and emotional tokens into the language model and output the emotional explanations. It ensures that the generated interpretations remain semantically and emotionally coherent with the visual stimuli. Our method realizes end-to-end modeling from low-level pixel features to high-level emotion interpretation, delivering the first interpretable fine-grained framework for visual emotion analysis. Extensive experiments validate the effectiveness of our model. Code will be made publicly available.

♻ ☆ BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification with Swin-HAFNet

Amirreza Fateh, Yasin Rezvani, Sara Moayedi, Sadjad Rezvani, Fatemeh Fateh, Mansoor Fateh

Accurate segmentation and classification of brain tumors from Magnetic Resonance Imaging (MRI) remain key challenges in medical image analysis. This is primarily due to the lack of high-quality, balanced, and diverse datasets. In this work, we present a newly developed MRI dataset named BRISC designed specifically for brain tumor segmentation and classification tasks. The dataset comprises 6,000 contrast-enhanced T1-weighted MRI scans annotated by certified radiologists and physicians. It includes three major tumor types, namely glioma, meningioma, and pituitary, as well as non-tumorous cases. Each sample includes high-resolution labels and is categorized across axial, sagittal, and coronal imaging planes to facilitate robust model development and cross-view generalization. To demonstrate the utility of the dataset, we propose a transformer-based segmentation model and benchmark it against established baselines. In this work, we propose a transformer-based model designed for both segmentation and classification of brain tumors, leveraging multi-scale feature representations from a Swin Transformer backbone. The model is benchmarked against established baselines to demonstrate the utility of the dataset, enabling accurate segmentation and robust classification across four diagnostic categories: glioma, meningioma, pituitary, and non-tumorous cases. In this work, our proposed transformer-based model demonstrates superior performance in both segmentation and classification tasks for brain tumor analysis. For the segmentation task, the method achieves the highest weighted mean Intersection-over-Union (IoU) of 82.3\%, with improvements observed across all tumor categories. For the classification task, the model attains an accuracy of 99.63\%, effectively distinguishing between glioma, meningioma, pituitary, and non-tumorous cases. https://www.kaggle.com/datasets/briscdataset/brisc2025/

♻ ☆ MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration

Cheng Liu, Daou Zhang, Tingxu Liu, Yuhan Wang, Jinyang Chen, Yuexuan Li, Xinying Xiao, Chenbo Xin, Ziru Wang, Weichao Wu

With the acceleration of urbanization, criminal behavior in public scenes poses an increasingly serious threat to social security. Traditional anomaly detection methods based on feature recognition struggle to capture high-level behavioral semantics from historical information, while generative approaches based on Large Language Models (LLMs) often fail to meet real-time requirements. To address these challenges, we propose MA-CBP, a criminal behavior prediction framework based on multi-agent asynchronous collaboration. This framework transforms real-time video streams into frame-level semantic descriptions, constructs causally consistent historical summaries, and fuses adjacent image frames to perform joint reasoning over long- and short-term contexts. The resulting behavioral decisions include key elements such as event subjects, locations, and causes, enabling early warning of potential criminal activity. In addition, we construct a high-quality criminal behavior dataset that provides multi-scale language supervision, including frame-level, summary-level, and event-level semantic annotations. Experimental results demonstrate that our method achieves superior performance on multiple datasets and offers a promising solution for risk warning in urban public safety scenarios.

♻ ☆ Enhancing Cost Efficiency in Active Learning with Candidate Set Query

Yeho Gwon, Sehyun Hwang, Hoyoung Kim, Jungseul Ok, Suha Kwak

This paper introduces a cost-efficient active learning (AL) framework for classification, featuring a novel query design called candidate set query. Unlike traditional AL queries requiring the oracle to examine all possible classes, our method narrows down the set of candidate classes likely to include the ground-truth class, significantly reducing the search space and labeling cost. Moreover, we leverage conformal prediction to dynamically generate small yet reliable candidate sets, adapting to model enhancement over successive AL rounds. To this end, we introduce an acquisition function designed to prioritize data points that offer high information gain at lower cost. Empirical evaluations on CIFAR-10, CIFAR-100, and ImageNet64x64 demonstrate the effectiveness and scalability of our framework. Notably, it reduces labeling cost by 48% on ImageNet64x64. The project page can be found at https://yehogwon.github.io/csq-al.

comment: Accepted to TMLR

♻ ☆ RAPNet: A Receptive-Field Adaptive Convolutional Neural Network for Pansharpening

Tao Tang, Chengxu Yang

Pansharpening refers to the process of integrating a high resolution panchromatic (PAN) image with a lower resolution multispectral (MS) image to generate a fused product, which is pivotal in remote sensing. Despite the effectiveness of CNNs in addressing this challenge, they are inherently constrained by the uniform application of convolutional kernels across all spatial positions, overlooking local content variations. To overcome this issue, we introduce RAPNet, a new architecture that leverages content-adaptive convolution. At its core, RAPNet employs the Receptive-field Adaptive Pansharpening Convolution (RAPConv), designed to produce spatially adaptive kernels responsive to local feature context, thereby enhancing the precision of spatial detail extraction. Additionally, the network integrates the Pansharpening Dynamic Feature Fusion (PAN-DFF) module, which incorporates an attention mechanism to achieve an optimal balance between spatial detail enhancement and spectral fidelity. Comprehensive evaluations on publicly available datasets confirm that RAPNet delivers superior performance compared to existing approaches, as demonstrated by both quantitative metrics and qualitative assessments. Ablation analyses further substantiate the effectiveness of the proposed adaptive components.

comment: Accepted by the 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2025). 5 pages, 6 figures

♻ ☆ ResFlow: Fine-tuning Residual Optical Flow for Event-based High Temporal Resolution Motion Estimation

Qianang Zhou, Zhiyu Zhu, Junhui Hou, Yongjian Deng, Youfu Li, Junlin Xiong

Event cameras hold significant promise for high-temporal-resolution (HTR) motion estimation. However, estimating event-based HTR optical flow faces two key challenges: the absence of HTR ground-truth data and the intrinsic sparsity of event data. Most existing approaches rely on the flow accumulation paradigms to indirectly supervise intermediate flows, often resulting in accumulation errors and optimization difficulties. To address these challenges, we propose a residual-based paradigm for estimating HTR optical flow with event data. Our approach separates HTR flow estimation into two stages: global linear motion estimation and HTR residual flow refinement. The residual paradigm effectively mitigates the impacts of event sparsity on optimization and is compatible with any LTR algorithm. Next, to address the challenge posed by the absence of HTR ground truth, we incorporate novel learning strategies. Specifically, we initially employ a shared refiner to estimate the residual flows, enabling both LTR supervision and HTR inference. Subsequently, we introduce regional noise to simulate the residual patterns of intermediate flows, facilitating the adaptation from LTR supervision to HTR inference. Additionally, we show that the noise-based strategy supports in-domain self-supervised training. Comprehensive experimental results demonstrate that our approach achieves state-of-the-art accuracy in both LTR and HTR metrics, highlighting its effectiveness and superiority.

comment: 12 pages, 9 figures

♻ ☆ Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation

Qianang Zhou, Junhui Hou, Meiyi Yang, Yongjian Deng, Youfu Li, Junlin Xiong

Current optical flow methods exploit the stable appearance of frame (or RGB) data to establish robust correspondences across time. Event cameras, on the other hand, provide high-temporal-resolution motion cues and excel in challenging scenarios. These complementary characteristics underscore the potential of integrating frame and event data for optical flow estimation. However, most cross-modal approaches fail to fully utilize the complementary advantages, relying instead on simply stacking information. This study introduces a novel approach that uses a spatially dense modality to guide the aggregation of the temporally dense event modality, achieving effective cross-modal fusion. Specifically, we propose an event-enhanced frame representation that preserves the rich texture of frames and the basic structure of events. We use the enhanced representation as the guiding modality and employ events to capture temporally dense motion information. The robust motion features derived from the guiding modality direct the aggregation of motion information from events. To further enhance fusion, we propose a transformer-based module that complements sparse event motion features with spatially rich frame information and enhances global information propagation. Additionally, a mix-fusion encoder is designed to extract comprehensive spatiotemporal contextual features from both modalities. Extensive experiments on the MVSEC and DSEC-Flow datasets demonstrate the effectiveness of our framework. Leveraging the complementary strengths of frames and events, our method achieves leading performance on the DSEC-Flow dataset. Compared to the event-only model, frame guidance improves accuracy by 10\%. Furthermore, it outperforms the state-of-the-art fusion-based method with a 4\% accuracy gain and a 45\% reduction in inference time.

comment: 11 pages, 8 figures, under review

♻ ☆ Regional quality estimation for echocardiography using deep learning

Gilles Van De Vyver, Svein-Erik Måsøy, Håvard Dalen, Bjørnar Leangen Grenne, Espen Holte, Sindre Hellum Olaisen, John Nyberg, Andreas Østvik, Lasse Løvstakken, Erik Smistad

Automatic estimation of cardiac ultrasound image quality can be beneficial for guiding operators and ensuring the accuracy of clinical measurements. Previous work often fails to distinguish the view correctness of the echocardiogram from the image quality. Additionally, previous studies only provide a global image quality value, which limits their practical utility. In this work, we developed and compared three methods to estimate image quality: 1) classic pixel-based metrics like the generalized contrast-to-noise ratio (gCNR) on myocardial segments as region of interest and left ventricle lumen as background, obtained using a U-Net segmentation 2) local image coherence derived from a U-Net model that predicts coherence from B-Mode images 3) a deep convolutional network that predicts the quality of each region directly in an end-to-end fashion. We evaluate each method against manual regional image quality annotations by three experienced cardiologists. The results indicate poor performance of the gCNR metric, with Spearman correlation to the annotations of rho = 0.24. The end-to-end learning model obtains the best result, rho = 0.69, comparable to the inter-observer correlation, rho = 0.63. Finally, the coherence-based method, with rho = 0.58, outperformed the classical metrics and is more generic than the end-to-end approach. The image quality prediction tool is available as an open source Python library at https://github.com/GillesVanDeVyver/arqee.

♻ ☆ A Versatile Pathology Co-pilot via Reasoning Enhanced Multimodal Large Language Model

Zhe Xu, Ziyi Liu, Junlin Hou, Jiabo Ma, Cheng Jin, Yihui Wang, Zhixuan Chen, Zhengyu Zhang, Fuxiang Huang, Zhengrui Guo, Fengtao Zhou, Yingxue Xu, Xi Wang, Ronald Cheong Kin Chan, Li Liang, Hao Chen

Multimodal large language models (MLLMs) have emerged as powerful tools for computational pathology, offering unprecedented opportunities to integrate pathological images with language context for comprehensive diagnostic analysis. These models hold particular promise for automating complex tasks that traditionally require expert interpretation of pathologists. However, current MLLM approaches in pathology demonstrate significantly constrained reasoning capabilities, primarily due to their reliance on expensive chain-of-thought annotations. Additionally, existing methods remain limited to simplex application of visual question answering (VQA) at the region-of-interest (ROI) level, failing to address the full spectrum of diagnostic needs such as ROI classification, detection, segmentation, whole-slide-image (WSI) classification and VQA in clinical practice. In this study, we present SmartPath-R1, a versatile MLLM capable of simultaneously addressing both ROI-level and WSI-level tasks while demonstrating robust pathological reasoning capability. Our framework combines scale-dependent supervised fine-tuning and task-aware reinforcement fine-tuning, which circumvents the requirement for chain-of-thought supervision by leveraging the intrinsic knowledge within MLLM. Furthermore, SmartPath-R1 integrates multiscale and multitask analysis through a mixture-of-experts mechanism, enabling dynamic processing for diverse tasks. We curate a large-scale dataset comprising 2.3M ROI samples and 188K WSI samples for training and evaluation. Extensive experiments across 72 tasks validate the effectiveness and superiority of the proposed approach. This work represents a significant step toward developing versatile, reasoning-enhanced AI systems for precision pathology.

♻ ☆ Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder

Jingchao Wang, Zhijian Wu, Dingjiang Huang, Yefeng Zheng, Hong Wang

Reference Expression Segmentation (RES) aims to segment image regions specified by referring expressions and has become popular with the rise of multimodal large models (MLLMs). While MLLMs excel in semantic understanding, their token-generation paradigm struggles with pixel-level dense prediction. Existing RES methods either couple MLLMs with the parameter-heavy Segment Anything Model (SAM) with 632M network parameters or adopt SAM-free lightweight pipelines that sacrifice accuracy. To address the trade-off between performance and cost, we specifically propose MLLMSeg, a novel framework that fully exploits the inherent visual detail features encoded in the MLLM vision encoder without introducing an extra visual encoder. Besides, we propose a detail-enhanced and semantic-consistent feature fusion module (DSFF) that fully integrates the detail-related visual feature with the semantic-related feature output by the large language model (LLM) of MLLM. Finally, we establish a light-weight mask decoder with only 34M network parameters that optimally leverages detailed spatial features from the visual encoder and semantic features from the LLM to achieve precise mask prediction. Extensive experiments demonstrate that our method generally surpasses both SAM-based and SAM-free competitors, striking a better balance between performance and cost. Code is available at https://github.com/jcwang0602/MLLMSeg.

comment: 9 pages, 4 figures

♻ ☆ Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation

Wenhao Li, Xiu Su, Jingyi Wu, Feng Yang, Yang Liu, Yi Chen, Shan You, Chang Xu

Large Vision-Language Models (LVLMs) have demonstrated remarkable advancements in numerous areas such as multimedia. However, hallucination issues significantly limit their credibility and application potential. Existing mitigation methods typically rely on external tools or the comparison of multi-round inference, which significantly increase inference time. In this paper, we propose \textbf{SE}lf-\textbf{E}volving \textbf{D}istillation (\textbf{SEED}), which identifies hallucinations within the inner knowledge of LVLMs, isolates and purges them, and then distills the purified knowledge back into the model, enabling self-evolution. Furthermore, we identified that traditional distillation methods are prone to inducing void spaces in the output space of LVLMs. To address this issue, we propose a Mode-Seeking Evolving approach, which performs distillation to capture the dominant modes of the purified knowledge distribution, thereby avoiding the chaotic results that could emerge from void spaces. Moreover, we introduce a Hallucination Elimination Adapter, which corrects the dark knowledge of the original model by learning purified knowledge. Extensive experiments on multiple benchmarks validate the superiority of our SEED, demonstrating substantial improvements in mitigating hallucinations for representative LVLM models such as LLaVA-1.5 and InternVL2. Remarkably, the F1 score of LLaVA-1.5 on the hallucination evaluation metric POPE-Random improved from 81.3 to 88.3.

comment: In Figure 2, the correlation coefficient and the scatter plot do not match. I calculated this correlation using two sets of settings. I used the scatter plot from setting A, but accidentally wrote the correlation coefficient, r, from setting B

♻ ☆ ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection

Ziying Song, Hongyu Pan, Feiyang Jia, Yongchang Zhang, Lin Liu, Lei Yang, Shaoqing Xu, Peiliang Wu, Caiyan Jia, Zheng Zhang, Yadan Luo

In the field of 3D object detection tasks, fusing heterogeneous features from LiDAR and camera sensors into a unified Bird's Eye View (BEV) representation is a widely adopted paradigm. However, existing methods often suffer from imprecise sensor calibration, leading to feature misalignment in LiDAR-camera BEV fusion. Moreover, such inaccuracies cause errors in depth estimation for the camera branch, aggravating misalignment between LiDAR and camera BEV features. In this work, we propose a novel ContrastAlign approach that utilizes contrastive learning to enhance the alignment of heterogeneous modalities, thereby improving the robustness of the fusion process. Specifically, our approach comprises three key components: (1) the L-Instance module, which extracts LiDAR instance features within the LiDAR BEV features; (2) the C-Instance module, which predicts camera instance features through Region of Interest (RoI) pooling on the camera BEV features; (3) the InstanceFusion module, which employs contrastive learning to generate consistent instance features across heFterogeneous modalities. Subsequently, we use graph matching to calculate the similarity between the neighboring camera instance features and the similarity instance features to complete the alignment of instance features. Our method achieves SOTA performance, with an mAP of 71.5%, surpassing GraphBEV by 1.4% on the nuScenes val set. Importantly, our method excels BEVFusion under conditions with spatial & temporal misalignment noise, improving mAP by 1.4% and 11.1% on nuScenes dataset. Notably, on the Argoverse2 dataset, ContrastAlign outperforms GraphBEV by 1.0% in mAP, indicating that the farther the distance, the more severe the feature misalignment and the more effective.

comment: 12 pages, 3 figures

♻ ☆ Automatic Image Colorization with Convolutional Neural Networks and Generative Adversarial Networks

Changyuan Qiu, Hangrui Cao, Qihan Ren, Ruiyu Li, Yuqing Qiu

Image colorization, the task of adding colors to grayscale images, has been the focus of significant research efforts in computer vision in recent years for its various application areas such as color restoration and automatic animation colorization [15, 1]. The colorization problem is challenging as it is highly ill-posed with two out of three image dimensions lost, resulting in large degrees of freedom. However, semantics of the scene as well as the surface texture could provide important cues for colors: the sky is typically blue, the clouds are typically white and the grass is typically green, and there are huge amounts of training data available for learning such priors since any colored image could serve as a training data point [20]. Colorization is initially formulated as a regression task[5], which ignores the multi-modal nature of color prediction. In this project, we explore automatic image colorization via classification and adversarial learning. We will build our models on prior works, apply modifications for our specific scenario and make comparisons.

comment: All authors have equal authorship and equal contribution, ranked in alphabetic order. First version of this paper was completed and published in 2021

♻ ☆ Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising AAAI 2025

Junyi Li, Zhilu Zhang, Wangmeng Zuo

Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID). However, most existing BSNs are conducted with convolution layers. Although transformers have shown the potential to overcome the limitations of convolutions in many image restoration tasks, the attention mechanisms may violate the blind-spot requirement, thereby restricting their applicability in BSN. To this end, we propose to analyze and redesign the channel and spatial attentions to meet the blind-spot requirement. Specifically, channel self-attention may leak the blind-spot information in multi-scale architectures, since the downsampling shuffles the spatial feature into channel dimensions. To alleviate this problem, we divide the channel into several groups and perform channel attention separately. For spatial selfattention, we apply an elaborate mask to the attention matrix to restrict and mimic the receptive field of dilated convolution. Based on the redesigned channel and window attentions, we build a Transformer-based Blind-Spot Network (TBSN), which shows strong local fitting and global perspective abilities. Furthermore, we introduce a knowledge distillation strategy that distills TBSN into smaller denoisers to improve computational efficiency while maintaining performance. Extensive experiments on real-world image denoising datasets show that TBSN largely extends the receptive field and exhibits favorable performance against state-of-theart SSID methods.

comment: AAAI 2025 Camera Ready, update Fig.4

♻ ☆ WIPES: Wavelet-based Visual Primitives

Wenhao Zhang, Hao Zhu, Delong Wu, Di Kang, Linchao Bao, Xun Cao, Zhan Ma

Pursuing a continuous visual representation that offers flexible frequency modulation and fast rendering speed has recently garnered increasing attention in the fields of 3D vision and graphics. However, existing representations often rely on frequency guidance or complex neural network decoding, leading to spectrum loss or slow rendering. To address these limitations, we propose WIPES, a universal Wavelet-based vIsual PrimitivES for representing multi-dimensional visual signals. Building on the spatial-frequency localization advantages of wavelets, WIPES effectively captures both the low-frequency "forest" and the high-frequency "trees." Additionally, we develop a wavelet-based differentiable rasterizer to achieve fast visual rendering. Experimental results on various visual tasks, including 2D image representation, 5D static and 6D dynamic novel view synthesis, demonstrate that WIPES, as a visual primitive, offers higher rendering quality and faster inference than INR-based methods, and outperforms Gaussian-based representations in rendering quality.

comment: IEEE/CVF International Conference on Computer Vision 2025

♻ ☆ Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline

Shiyi Mu, Zichong Gu, Hanqi Lyu, Yilin Gao, Shugong Xu

3D detection technology is widely used in the field of autonomous driving, with its application scenarios gradually expanding from enclosed highways to open conventional roads. For rare anomaly categories that appear on the road, 3D detection models trained on closed sets often misdetect or fail to detect anomaly objects. To address this risk, it is necessary to enhance the generalization ability of 3D detection models for targets of arbitrary shapes and to possess the capability to filter out anomalies. The generalization of 3D detection is limited by two factors: the coupled training of 2D and 3D, and the insufficient diversity in the scale distribution of training samples. This paper proposes a Stereo-based 3D Anomaly object Detection (S3AD) algorithm, which decouples the training strategy of 3D and 2D to release the generalization ability for arbitrary 3D foreground detection, and proposes an anomaly scoring algorithm based on foreground confidence prediction, achieving target-level anomaly scoring. In order to further verify and enhance the generalization of anomaly detection, we use a 3D rendering method to synthesize two augmented reality binocular stereo 3D detection datasets which named KITTI-AR. KITTI-AR extends upon KITTI by adding 97 new categories, totaling 6k pairs of stereo images. The KITTI-AR-ExD subset includes 39 common categories as extra training data to address the sparse sample distribution issue. Additionally, 58 rare categories form the KITTI-AR-OoD subset, which are not used in training to simulate zero-shot scenarios in real-world settings, solely for evaluating 3D anomaly detection. Finally, the performance of the algorithm and the dataset is verified in the experiments. (Code and dataset can be obtained at https://github.com/shiyi-mu/S3AD-Code).

comment: under review

♻ ☆ Rapid Urban Visibility Hotspots: Quantifying Building Vertex Visibility from Connected Vehicle Trajectories using Spatial Indexing

Artur Grigorev, Adriana-Simona Mihaita

Effective placement of Out-of-Home advertising and street furniture requires accurate identification of locations offering maximum visual exposure to target audiences, particularly vehicular traffic. Traditional site selection methods often rely on static traffic counts or subjective assessments. This research introduces a data-driven methodology to objectively quantify location visibility by analyzing large-scale connected vehicle trajectory data (sourced from Compass IoT) within urban environments. We model the dynamic driver field-of-view using a forward-projected visibility area for each vehicle position derived from interpolated trajectories. By integrating this with building vertex locations extracted from OpenStreetMap, we quantify the cumulative visual exposure, or ``visibility count'', for thousands of potential points of interest near roadways. The analysis reveals that visibility is highly concentrated, identifying specific ``visual hotspots'' that receive disproportionately high exposure compared to average locations. The core technical contribution involves the construction of a BallTree spatial index over building vertices. This enables highly efficient (O(logN) complexity) radius queries to determine which vertices fall within the viewing circles of millions of trajectory points across numerous trips, significantly outperforming brute-force geometric checks. Analysis reveals two key findings: 1) Visibility is highly concentrated, identifying distinct 'visual hotspots' receiving disproportionately high exposure compared to average locations. 2) The aggregated visibility counts across vertices conform to a Log-Normal distribution.

♻ ☆ Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder

Tao Sun, Lu Pang, Weimin Lyu, Chao Chen, Haibin Ling

Deep neural networks are vulnerable to backdoor attacks, where an adversary manipulates the model behavior through overlaying images with special triggers. Existing backdoor defense methods often require accessing a few validation data and model parameters, which is impractical in many real-world applications, e.g., when the model is provided as a cloud service. In this paper, we address the practical task of blind backdoor defense at test time, in particular for local attacks and black-box models. The true label of every test image needs to be recovered on the fly from a suspicious model regardless of image benignity. We consider test-time image purification that incapacitates local triggers while keeping semantic contents intact. Due to diverse trigger patterns and sizes, the heuristic trigger search can be unscalable. We circumvent such barrier by leveraging the strong reconstruction power of generative models, and propose Blind Defense with Masked AutoEncoder (BDMAE). BDMAE detects possible local triggers using image structural similarity and label consistency between the test image and MAE restorations. The detection results are then refined by considering trigger topology. Finally, we fuse MAE restorations adaptively into a purified image for making prediction. Extensive experiments under different backdoor settings validate its effectiveness and generalizability.

♻ ☆ SRMA-Mamba: Spatial Reverse Mamba Attention Network for Pathological Liver Segmentation in MRI Volumes

Jun Zeng, Yannan Huang, Elif Keles, Halil Ertugrul Aktas, Gorkem Durak, Nikhil Kumar Tomar, Quoc-Huy Trinh, Deepak Ranjan Nayak, Ulas Bagci, Debesh Jha

Liver Cirrhosis plays a critical role in the prognosis of chronic liver disease. Early detection and timely intervention are critical in significantly reducing mortality rates. However, the intricate anatomical architecture and diverse pathological changes of liver tissue complicate the accurate detection and characterization of lesions in clinical settings. Existing methods underutilize the spatial anatomical details in volumetric MRI data, thereby hindering their clinical effectiveness and explainability. To address this challenge, we introduce a novel Mamba-based network, SRMA-Mamba, designed to model the spatial relationships within the complex anatomical structures of MRI volumes. By integrating the Spatial Anatomy-Based Mamba module (SABMamba), SRMA-Mamba performs selective Mamba scans within liver cirrhotic tissues and combines anatomical information from the sagittal, coronal, and axial planes to construct a global spatial context representation, enabling efficient volumetric segmentation of pathological liver structures. Furthermore, we introduce the Spatial Reverse Attention module (SRMA), designed to progressively refine cirrhotic details in the segmentation map, utilizing both the coarse segmentation map and hierarchical encoding features. Extensive experiments demonstrate that SRMA-Mamba surpasses state-of-the-art methods, delivering exceptional performance in 3D pathological liver segmentation. Our code is available for public: https://github.com/JunZengz/SRMA-Mamba.

comment: 9 pages, 4 figures

♻ ☆ MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation

Tianchen Deng, Guole Shen, Xun Chen, Shenghai Yuan, Hongming Shen, Guohao Peng, Zhenyu Wu, Jingchuan Wang, Lihua Xie, Danwei Wang, Hesheng Wang, Weidong Chen

Neural implicit scene representations have recently shown promising results in dense visual SLAM. However, existing implicit SLAM algorithms are constrained to single-agent scenarios, and fall difficulties in large-scale scenes and long sequences. Existing NeRF-based multi-agent SLAM frameworks cannot meet the constraints of communication bandwidth. To this end, we propose the first distributed multi-agent collaborative neural SLAM framework with hybrid scene representation, distributed camera tracking, intra-to-inter loop closure, and online distillation for multiple submap fusion. A novel triplane-grid joint scene representation method is proposed to improve scene reconstruction. A novel intra-to-inter loop closure method is designed to achieve local (single-agent) and global (multi-agent) consistency. We also design a novel online distillation method to fuse the information of different submaps to achieve global consistency. Furthermore, to the best of our knowledge, there is no real-world dataset for NeRF-based/GS-based SLAM that provides both continuous-time trajectories groundtruth and high-accuracy 3D meshes groundtruth. To this end, we propose the first real-world Dense slam (DES) dataset covering both single-agent and multi-agent scenarios, ranging from small rooms to large-scale outdoor scenes, with high-accuracy ground truth for both 3D mesh and continuous-time camera trajectory. This dataset can advance the development of the research in both SLAM, 3D reconstruction, and visual foundation model. Experiments on various datasets demonstrate the superiority of the proposed method in both mapping, tracking, and communication. The dataset and code will open-source on https://github.com/dtc111111/mcnslam.

♻ ☆ ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains

Guillaume Vray, Devavrat Tomar, Xufeng Gao, Jean-Philippe Thiran, Evan Shelhamer, Behzad Bozorgtabar

This paper introduces ReservoirTTA, a novel plug-in framework designed for prolonged test-time adaptation (TTA) in scenarios where the test domain continuously shifts over time, including cases where domains recur or evolve gradually. At its core, ReservoirTTA maintains a reservoir of domain-specialized models -- an adaptive test-time model ensemble -- that both detects new domains via online clustering over style features of incoming samples and routes each sample to the appropriate specialized model, and thereby enables domain-specific adaptation. This multi-model strategy overcomes key limitations of single model adaptation, such as catastrophic forgetting, inter-domain interference, and error accumulation, ensuring robust and stable performance on sustained non-stationary test distributions. Our theoretical analysis reveals key components that bound parameter variance and prevent model collapse, while our plug-in TTA module mitigates catastrophic forgetting of previously encountered domains. Extensive experiments on the classification corruption benchmarks, including ImageNet-C and CIFAR-10/100-C, as well as the Cityscapes$\rightarrow$ACDC semantic segmentation task, covering recurring and continuously evolving domain shifts, demonstrate that ReservoirTTA significantly improves adaptation accuracy and maintains stable performance across prolonged, recurring shifts, outperforming state-of-the-art methods. Our code is publicly available at https://github.com/LTS5/ReservoirTTA.

♻ ☆ WHALES: A Multi-Agent Scheduling Dataset for Enhanced Cooperation in Autonomous Driving

Yinsong Wang, Siwei Chen, Ziyi Song, Sheng Zhou

Cooperative perception research is hindered by the limited availability of datasets that capture the complexity of real-world Vehicle-to-Everything (V2X) interactions, particularly under dynamic communication constraints. To address this gap, we introduce WHALES (Wireless enhanced Autonomous vehicles with Large number of Engaged agents), the first large-scale V2X dataset explicitly designed to benchmark communication-aware agent scheduling and scalable cooperative perception. WHALES introduces a new benchmark that enables state-of-the-art (SOTA) research in communication-aware cooperative perception, featuring an average of 8.4 cooperative agents per scene and 2.01 million annotated 3D objects across diverse traffic scenarios. It incorporates detailed communication metadata to emulate real-world communication bottlenecks, enabling rigorous evaluation of scheduling strategies. To further advance the field, we propose the Coverage-Aware Historical Scheduler (CAHS), a novel scheduling baseline that selects agents based on historical viewpoint coverage, improving perception performance over existing SOTA methods. WHALES bridges the gap between simulated and real-world V2X challenges, providing a robust framework for exploring perception-scheduling co-design, cross-data generalization, and scalability limits. The WHALES dataset and code are available at https://github.com/chensiweiTHU/WHALES.

♻ ☆ VoiceCloak: A Multi-Dimensional Defense Framework against Unauthorized Diffusion-based Voice Cloning

Qianyue Hu, Junyan Wu, Wei Lu, Xiangyang Luo

♻ ☆ MR-EEGWaveNet: Multiresolutional EEGWaveNet for Seizure Detection from Long EEG Recordings

Kazi Mahmudul Hassan, Xuyang Zhao, Hidenori Sugano, Toshihisa Tanaka

Feature engineering for generalized seizure detection models remains a significant challenge. Recently proposed models show variable performance depending on the training data and remain ineffective at accurately distinguishing artifacts from seizure data. In this study, we propose a novel end-to-end model, "Multiresolutional EEGWaveNet (MR-EEGWaveNet)," which efficiently distinguishes seizure events from background electroencephalogram (EEG) and artifacts/noise by capturing both temporal dependencies across different time frames and spatial relationships between channels. The model has three modules: convolution, feature extraction, and predictor. The convolution module extracts features through depth-wise and spatio-temporal convolution. The feature extraction module individually reduces the feature dimension extracted from EEG segments and their sub-segments. Subsequently, the extracted features are concatenated into a single vector for classification using a fully connected classifier called the predictor module. In addition, an anomaly score-based post-classification processing technique is introduced to reduce the false-positive rates of the model. Experimental results are reported and analyzed using different parameter settings and datasets (Siena (public) and Juntendo (private)). The proposed MR-EEGWaveNet significantly outperformed the conventional non-multiresolution approach, improving the F1 scores from 0.177 to 0.336 on Siena and 0.327 to 0.488 on Juntendo, with precision gains of 15.9% and 20.62%, respectively.

comment: 33 pages, 10 figures, 18 tables

♻ ☆ FreqDGT: Frequency-Adaptive Dynamic Graph Networks with Transformer for Cross-subject EEG Emotion Recognition

Yueyang Li, Shengyu Gong, Weiming Zeng, Nizhuan Wang, Wai Ting Siok

Electroencephalography (EEG) serves as a reliable and objective signal for emotion recognition in affective brain-computer interfaces, offering unique advantages through its high temporal resolution and ability to capture authentic emotional states that cannot be consciously controlled. However, cross-subject generalization remains a fundamental challenge due to individual variability, cognitive traits, and emotional responses. We propose FreqDGT, a frequency-adaptive dynamic graph transformer that systematically addresses these limitations through an integrated framework. FreqDGT introduces frequency-adaptive processing (FAP) to dynamically weight emotion-relevant frequency bands based on neuroscientific evidence, employs adaptive dynamic graph learning (ADGL) to learn input-specific brain connectivity patterns, and implements multi-scale temporal disentanglement network (MTDN) that combines hierarchical temporal transformers with adversarial feature disentanglement to capture both temporal dynamics and ensure cross-subject robustness. Comprehensive experiments demonstrate that FreqDGT significantly improves cross-subject emotion recognition accuracy, confirming the effectiveness of integrating frequency-adaptive, spatial-dynamic, and temporal-hierarchical modeling while ensuring robustness to individual differences. The code is available at https://github.com/NZWANG/FreqDGT.

♻ ☆ Boosting Adversarial Transferability for Hyperspectral Image Classification Using 3D Structure-invariant Transformation and Weighted Intermediate Feature Divergence

Chun Liu, Bingqian Zhu, Tao Xu, Zheng Zheng, Zheng Li, Wei Yang, Zhigang Han, Jiayao Wang

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, which pose security challenges to hyperspectral image (HSI) classification based on DNNs. Numerous adversarial attack methods have been designed in the domain of natural images. However, different from natural images, HSIs contains high-dimensional rich spectral information, which presents new challenges for generating adversarial examples. Based on the specific characteristics of HSIs, this paper proposes a novel method to enhance the transferability of the adversarial examples for HSI classification using 3D structure-invariant transformation and weighted intermediate feature divergence. While keeping the HSIs structure invariant, the proposed method divides the image into blocks in both spatial and spectral dimensions. Then, various transformations are applied on each block to increase input diversity and mitigate the overfitting to substitute models. Moreover, a weighted intermediate feature divergence loss is also designed by leveraging the differences between the intermediate features of original and adversarial examples. It constrains the perturbation direction by enlarging the feature maps of the original examples, and assigns different weights to different feature channels to destroy the features that have a greater impact on HSI classification. Extensive experiments demonstrate that the adversarial examples generated by the proposed method achieve more effective adversarial transferability on three public HSI datasets. Furthermore, the method maintains robust attack performance even under defense strategies.

♻ ☆ Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer

Wenxuan Liu, Zhuo Zhou, Xuemei Jia, Siyuan Yang, Wenxin Huang, Xian Zhong, Chia-Wen Lin

Action recognition in unmanned aerial vehicles (UAVs) poses unique challenges due to significant view variations along the vertical spatial axis. Unlike traditional ground-based settings, UAVs capture actions at a wide range of altitudes, resulting in considerable appearance discrepancies. We introduce a multi-view formulation tailored to varying UAV altitudes and empirically observe a partial order among views, where recognition accuracy consistently decreases as altitude increases. This observation motivates a novel approach that explicitly models the hierarchical structure of UAV views to improve recognition performance across altitudes. To this end, we propose the Partial Order Guided Multi-View Network (POG-MVNet), designed to address drastic view variations by effectively leveraging view-dependent information across different altitude levels. The framework comprises three key components: a View Partition (VP) module, which uses the head-to-body ratio to group views by altitude; an Order-aware Feature Decoupling (OFD) module, which disentangles action-relevant and view-specific features under partial order guidance; and an Action Partial Order Guide (APOG), which uses the partial order to transfer informative knowledge from easier views to more challenging ones. We conduct experiments on Drone-Action, MOD20, and UAV, demonstrating that POG-MVNet significantly outperforms competing methods. For example, POG-MVNet achieves a 4.7% improvement on Drone-Action and a 3.5% improvement on UAV compared to state-of-the-art methods ASAT and FAR. Code will be released soon.

comment: 11 pages

♻ ☆ MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation

Gurucharan Marthi Krishna Kumar, Aman Chadha, Janine Mendola, Amir Shmuel

Large Language Models (LLMs), known for their versatility in textual data, are increasingly being explored for their potential to enhance medical image segmentation, a crucial task for accurate diagnostic imaging. This study explores enhancing Vision Transformers (ViTs) for medical image segmentation by integrating pre-trained LLM transformer blocks. Our approach, which incorporates a frozen LLM transformer block into the encoder of a ViT-based model, leads to substantial improvements in segmentation performance across various medical imaging modalities. We propose a Hybrid Attention Mechanism that combines global and local feature learning with a Multi-Scale Fusion Block for aggregating features across different scales. The enhanced model shows significant performance gains, including an average Dice score increase from 0.74 to 0.79 and improvements in accuracy, precision, and the Jaccard Index. These results demonstrate the effectiveness of LLM-based transformers in refining medical image segmentation, highlighting their potential to significantly boost model accuracy and robustness. The source code and our implementation are available at: https://github.com/AS-Lab/Marthi-et-al-2025-MedVisionLlama-Pre-Trained-LLM-Layers-to-Enhance-Medical-Image-Segmentation

comment: Accepted to the CVAMD Workshop (Computer Vision for Automated Medical Diagnosis) at the 2025 IEEE/CVF International Conference on Computer Vision (ICCVW 2025)

♻ ☆ Refinement Module based on Parse Graph for Human Pose Estimation

Shibang Liu, Xuemei Xie, Guangming Shi

Parse graphs have been widely used in human pose estimation (HPE) to model the hierarchical structure and context relations of the human body, which has been shown to effectively improve robustness and accuracy. But most methods rely on parse graphs built from predefined skeletons, causing two key issues: poor integratability with other models, and complex designs with redundant parameters for hierarchy and context relation modeling of body. To address these issues, we propose a novel Refinement Module based on Parse Graph (RMPG). RMPG abandons skeleton connections and refines features by building implicit hierarchical structures and context relations between sub-feature maps, with strong integratability. Furthermore, our hierarchical network design demonstrates that RMPG can model the body's hierarchical structure and context relations with a simpler architecture and fewer parameters. RMPG operates in two stages: the top-down decomposition recursively partitions the feature map into a tree-structured hierarchy, where each node corresponds to a sub-feature map; the bottom-up composition aggregates context information to progressively refine the feature representation. Extensive experiments show that RMPG can be flexibly embedded into various methods, including our hierarchical networks, and consistently improves performance across multiple mainstream HPE benchmarks. The code will be released.

♻ ☆ Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

Wongi Jeong, Kyungryeol Lee, Hoigi Seo, Se Young Chun

Diffusion transformers have emerged as an alternative to U-net-based diffusion models for high-fidelity image and video generation, offering superior scalability. However, their heavy computation remains a major obstacle to real-world deployment. Existing acceleration methods primarily exploit the temporal dimension such as reusing cached features across diffusion timesteps. Here, we propose Region-Adaptive Latent Upsampling (RALU), a training-free framework that accelerates inference along spatial dimension. RALU performs mixed-resolution sampling across three stages: 1) low-resolution denoising latent diffusion to efficiently capture global semantic structure, 2) region-adaptive upsampling on specific regions prone to artifacts at full-resolution, and 3) all latent upsampling at full-resolution for detail refinement. To stabilize generations across resolution transitions, we leverage noise-timestep rescheduling to adapt the noise level across varying resolutions. Our method significantly reduces computation while preserving image quality by achieving up to 7.0$\times$ speed-up on FLUX and 3.0$\times$ on Stable Diffusion 3 with minimal degradation. Furthermore, RALU is complementary to existing temporal accelerations such as caching methods, thus can be seamlessly integrated to further reduce inference latency without compromising generation quality.

♻ ☆ Segment Anything in Pathology Images with Natural Language

Zhixuan Chen, Junlin Hou, Liqi Lin, Yihui Wang, Yequan Bie, Xi Wang, Yanning Zhou, Ronald Cheong Kin Chan, Hao Chen

Pathology image segmentation is crucial in computational pathology for analyzing histological features relevant to cancer diagnosis and prognosis. However, current methods face major challenges in clinical applications due to limited annotated data and restricted category definitions. To address these limitations, we propose PathSegmentor, the first text-prompted segmentation foundation model designed specifically for pathology images. We also introduce PathSeg, the largest and most comprehensive dataset for pathology segmentation, built from 21 public sources and containing 275k image-mask-label triples across 160 diverse categories. With PathSegmentor, users can perform semantic segmentation using natural language prompts, eliminating the need for laborious spatial inputs such as points or boxes. Extensive experiments demonstrate that PathSegmentor outperforms specialized models with higher accuracy and broader applicability, while maintaining a compact architecture. It significantly surpasses existing spatial- and text-prompted models by 0.145 and 0.429 in overall Dice scores, respectively, showing strong robustness in segmenting complex structures and generalizing to external datasets. Moreover, PathSegmentor's outputs enhance the interpretability of diagnostic models through feature importance estimation and imaging biomarker discovery, offering pathologists evidence-based support for clinical decision-making. This work advances the development of explainable AI in precision oncology.

♻ ☆ Image Augmentation Agent for Weakly Supervised Semantic Segmentation

Wangyu Wu, Xianglin Qiu, Siqi Song, Zhenhong Chen, Xiaowei Huang, Fei Ma, Jimin Xiao

Weakly-supervised semantic segmentation (WSSS) has achieved remarkable progress using only image-level labels. However, most existing WSSS methods focus on designing new network structures and loss functions to generate more accurate dense labels, overlooking the limitations imposed by fixed datasets, which can constrain performance improvements. We argue that more diverse trainable images provides WSSS richer information and help model understand more comprehensive semantic pattern. Therefore in this paper, we introduce a novel approach called Image Augmentation Agent (IAA) which shows that it is possible to enhance WSSS from data generation perspective. IAA mainly design an augmentation agent that leverages large language models (LLMs) and diffusion models to automatically generate additional images for WSSS. In practice, to address the instability in prompt generation by LLMs, we develop a prompt self-refinement mechanism. It allow LLMs to re-evaluate the rationality of generated prompts to produce more coherent prompts. Additionally, we insert an online filter into diffusion generation process to dynamically ensure the quality and balance of generated images. Experimental results show that our method significantly surpasses state-of-the-art WSSS approaches on the PASCAL VOC 2012 and MS COCO 2014 datasets.

comment: Accepted at Neurocomputing 2025

♻ ☆ Advancing Toward Robust and Scalable Fingerprint Orientation Estimation: From Gradients to Deep Learning

Amit Kumar Trivedi, Jasvinder Pal Singh

The study identifies a clear evolution from traditional methods to more advanced machine learning approaches. Current algorithms face persistent challenges, including degraded image quality, damaged ridge structures, and background noise, which impact performance. To overcome these limitations, future research must focus on developing efficient algorithms with lower computational complexity while maintaining robust performance across varied conditions. Hybrid methods that combine the simplicity and efficiency of gradient-based techniques with the adaptability and robustness of machine learning are particularly promising for advancing fingerprint recognition systems. Fingerprint orientation estimation plays a crucial role in improving the reliability and accuracy of biometric systems. This study highlights the limitations of current approaches and underscores the importance of designing next-generation algorithms that can operate efficiently across diverse application domains. By addressing these challenges, future developments could enhance the scalability, reliability, and applicability of biometric systems, paving the way for broader use in security and identification technologies.

♻ ☆ Always Skip Attention

Yiping Ji, Hemanth Saratchandran, Peyman Moghadam, Simon Lucey

We highlight a curious empirical result within modern Vision Transformers (ViTs). Specifically, self-attention catastrophically fails to train unless it is used in conjunction with a skip connection. This is in contrast to other elements of a ViT that continue to exhibit good performance (albeit suboptimal) when skip connections are removed. Further, we show that this critical dependence on skip connections is a relatively new phenomenon, with previous deep architectures (\eg, CNNs) exhibiting good performance in their absence. In this paper, we theoretically characterize that the self-attention mechanism is fundamentally ill-conditioned and is, therefore, uniquely dependent on skip connections for regularization. Additionally, we propose Token Graying -- a simple yet effective complement (to skip connections) that further improves the condition of input tokens. We validate our approach in both supervised and self-supervised training methods.

comment: This work has just been accepted by ICCV 2025

♻ ☆ Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models

Nanxing Hu, Xiaoyue Duan, Jinchao Zhang, Guoliang Kang

Large Vision-Language Models (LVLMs) usually generate texts which satisfy context coherence but don't match the visual input. Such a hallucination issue hinders LVLMs' applicability in the real world. The key to solving hallucination in LVLM is to make the text generation rely more on the visual content. Most previous works choose to enhance/adjust the features/output of a specific modality (i.e., visual or textual) to alleviate hallucinations in LVLM, which do not explicitly or systematically enhance the visual reliance. In this paper, we comprehensively investigate the factors which may degenerate the visual reliance in text generation of LVLM from a Bayesian perspective. Based on our observations, we propose to mitigate hallucination in LVLM from three aspects. Firstly, we observe that not all visual tokens are informative in generating meaningful texts. We propose to evaluate and remove redundant visual tokens to avoid their disturbance. Secondly, LVLM may encode inappropriate prior information, making it lean toward generating unexpected words. We propose a simple yet effective way to rectify the prior from a Bayesian perspective. Thirdly, we observe that starting from certain steps, the posterior of next-token prediction conditioned on visual tokens may collapse to a prior distribution which does not depend on any informative visual tokens at all. Thus, we propose to stop further text generation to avoid hallucination. Extensive experiments on three benchmarks including POPE, CHAIR, and MME demonstrate that our method can consistently mitigate the hallucination issue of LVLM and performs favorably against previous state-of-the-arts.

♻ ☆ Diffusion Noise Feature: Accurate and Fast Generated Image Detection

Yichi Zhang, Xiaogang Xu

Generative models now produce images with such stunning realism that they can easily deceive the human eye. While this progress unlocks vast creative potential, it also presents significant risks, such as the spread of misinformation. Consequently, detecting generated images has become a critical research challenge. However, current detection methods are often plagued by low accuracy and poor generalization. In this paper, to address these limitations and enhance the detection of generated images, we propose a novel representation, Diffusion Noise Feature (DNF). Derived from the inverse process of diffusion models, DNF effectively amplifies the subtle, high-frequency artifacts that act as fingerprints of artificial generation. Our key insight is that real and generated images exhibit distinct DNF signatures, providing a robust basis for differentiation. By training a simple classifier such as ResNet-50 on DNF, our approach achieves remarkable accuracy, robustness, and generalization in detecting generated images, including those from unseen generators or with novel content. Extensive experiments across four training datasets and five test sets confirm that DNF establishes a new state-of-the-art in generated image detection. The code is available at https://github.com/YichiCS/Diffusion-Noise-Feature.

comment: Accepted by ECAI 2025

♻ ☆ Dataset Condensation with Color Compensation

Huyu Wu, Duo Su, Junjie Hou, Guang Li

Dataset condensation always faces a constitutive trade-off: balancing performance and fidelity under extreme compression. Existing methods struggle with two bottlenecks: image-level selection methods (Coreset Selection, Dataset Quantization) suffer from inefficiency condensation, while pixel-level optimization (Dataset Distillation) introduces semantic distortion due to over-parameterization. With empirical observations, we find that a critical problem in dataset condensation is the oversight of color's dual role as an information carrier and a basic semantic representation unit. We argue that improving the colorfulness of condensed images is beneficial for representation learning. Motivated by this, we propose DC3: a Dataset Condensation framework with Color Compensation. After a calibrated selection strategy, DC3 utilizes the latent diffusion model to enhance the color diversity of an image rather than creating a brand-new one. Extensive experiments demonstrate the superior performance and generalization of DC3 that outperforms SOTA methods across multiple benchmarks. To the best of our knowledge, besides focusing on downstream tasks, DC3 is the first research to fine-tune pre-trained diffusion models with condensed datasets. The FID results prove that training networks with our high-quality datasets is feasible without model collapse or other degradation issues. Code and generated data are available at https://github.com/528why/Dataset-Condensation-with-Color-Compensation.

♻ ☆ Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation

SeungBum Ha, Taehwan Lee, Jiyoun Lim, Sung Whan Yoon

Federated learning (FL) enables decentralized training while preserving data privacy, yet existing FL benchmarks address relatively simple classification tasks, where each sample is annotated with a one-hot label. However, little attention has been paid to demonstrating an FL benchmark that handles complicated semantics, where each sample encompasses diverse semantic information, such as relations between objects. Because the existing benchmarks are designed to distribute data in a narrow view of a single semantic, managing the complicated semantic heterogeneity across clients when formalizing FL benchmarks is non-trivial. In this paper, we propose a benchmark process to establish an FL benchmark with controllable semantic heterogeneity across clients: two key steps are (i) data clustering with semantics and (ii) data distributing via controllable semantic heterogeneity across clients. As a proof of concept, we construct a federated PSG benchmark, demonstrating the efficacy of the existing PSG methods in an FL setting with controllable semantic heterogeneity of scene graphs. We also present the effectiveness of our benchmark by applying robust federated learning algorithms to data heterogeneity to show increased performance. To our knowledge, this is the first benchmark framework that enables federated learning and its evaluation for multi-semantic vision tasks under the controlled semantic heterogeneity. Our code is available at https://github.com/Seung-B/FL-PSG.

comment: This work has been accepted for publication in Pattern Recognition Letters

2025-08-18

Sound 6

☆ FoleySpace: Vision-Aligned Binaural Spatial Audio Generation

Lei Zhao, Rujin Chen, Chi Zhang, Xiao-Lei Zhang, Xuelong Li

Recently, with the advancement of AIGC, deep learning-based video-to-audio (V2A) technology has garnered significant attention. However, existing research mostly focuses on mono audio generation that lacks spatial perception, while the exploration of binaural spatial audio generation technologies, which can provide a stronger sense of immersion, remains insufficient. To solve this problem, we propose FoleySpace, a framework for video-to-binaural audio generation that produces immersive and spatially consistent stereo sound guided by visual information. Specifically, we develop a sound source estimation method to determine the sound source 2D coordinates and depth in each video frame, and then employ a coordinate mapping mechanism to convert the 2D source positions into a 3D trajectory. This 3D trajectory, together with the monaural audio generated by a pre-trained V2A model, serves as a conditioning input for a diffusion model to generate spatially consistent binaural audio. To support the generation of dynamic sound fields, we constructed a training dataset based on recorded Head-Related Impulse Responses that includes various sound source movement scenarios. Experimental results demonstrate that the proposed method outperforms existing approaches in spatial perception consistency, effectively enhancing the immersive quality of the audio-visual experience.

☆ MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning

Aurian Quelennec, Pierre Chouteau, Geoffroy Peeters, Slim Essid

Masked latent prediction has emerged as a leading paradigm in self-supervised learning (SSL), especially for general audio and music representation learning. While recent methods have demonstrated strong performance, the role of the predictor module used at the output of such SSL systems remains mainly overlooked, despite being crucial for solving the pretext task at hand. In particular, this module should be able to deal with the ambiguity inherent in audio content, especially when it is composed of multiple sound sources. This work proposes a novel enhancement: integrating Multiple Choice Learning (MCL) to explicitly model prediction ambiguity and improve representation quality. We build on top of the recently proposed MATPAC system, improving its prediction and unsupervised classification pretext tasks with MCL. We extensively evaluate our method, MATPAC++, through both linear probing across multiple downstream tasks and fine-tuning on AudioSet, employing a unified protocol that enables rigorous and fair comparisons with state-of-the-art SSL approaches. Results show that our proposal achieves state-of-the-art when fine-tuned on AudioSet and overall state-of-the-art scores on downstream tasks. Additionally, we examine domain specialisation by training exclusively on music data, where our model achieves state-of-the-art performance with significantly improved efficiency.

comment: Under review

☆ Exploring the Feasibility of LLMs for Automated Music Emotion Annotation

Meng Yang, Jon McCormack, Maria Teresa Llano, Wanchao Su

Current approaches to music emotion annotation remain heavily reliant on manual labelling, a process that imposes significant resource and labour burdens, severely limiting the scale of available annotated data. This study examines the feasibility and reliability of employing a large language model (GPT-4o) for music emotion annotation. In this study, we annotated GiantMIDI-Piano, a classical MIDI piano music dataset, in a four-quadrant valence-arousal framework using GPT-4o, and compared against annotations provided by three human experts. We conducted extensive evaluations to assess the performance and reliability of GPT-generated music emotion annotations, including standard accuracy, weighted accuracy that accounts for inter-expert agreement, inter-annotator agreement metrics, and distributional similarity of the generated labels. While GPT's annotation performance fell short of human experts in overall accuracy and exhibited less nuance in categorizing specific emotional states, inter-rater reliability metrics indicate that GPT's variability remains within the range of natural disagreement among experts. These findings underscore both the limitations and potential of GPT-based annotation: despite its current shortcomings relative to human performance, its cost-effectiveness and efficiency render it a promising scalable alternative for music emotion annotation.

comment: Accepted to be published at ISMIR 2025

☆ Beyond Modality Limitations: A Unified MLLM Approach to Automated Speaking Assessment with Effective Curriculum Learning

Yu-Hsuan Fang, Tien-Hong Lo, Yao-Ting Sung, Berlin Chen

Traditional Automated Speaking Assessment (ASA) systems exhibit inherent modality limitations: text-based approaches lack acoustic information while audio-based methods miss semantic context. Multimodal Large Language Models (MLLM) offer unprecedented opportunities for comprehensive ASA by simultaneously processing audio and text within unified frameworks. This paper presents a very first systematic study of MLLM for comprehensive ASA, demonstrating the superior performance of MLLM across the aspects of content and language use . However, assessment on the delivery aspect reveals unique challenges, which is deemed to require specialized training strategies. We thus propose Speech-First Multimodal Training (SFMT), leveraging a curriculum learning principle to establish more robust modeling foundations of speech before cross-modal synergetic fusion. A series of experiments on a benchmark dataset show MLLM-based systems can elevate the holistic assessment performance from a PCC value of 0.783 to 0.846. In particular, SFMT excels in the evaluation of the delivery aspect, achieving an absolute accuracy improvement of 4% over conventional training approaches, which also paves a new avenue for ASA.

comment: Accepted at IEEE ASRU 2025

♻ ☆ USAD: Universal Speech and Audio Representation via Distillation

Heng-Jui Chang, Saurabhchand Bhati, James Glass, Alexander H. Liu

Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a unified approach to audio representation learning that integrates diverse audio types - speech, sound, and music - into a single model. USAD employs efficient layer-to-layer distillation from domain-specific SSL models to train a student on a comprehensive audio dataset. USAD offers competitive performance across various benchmarks and datasets, including frame and instance-level speech processing tasks, audio tagging, and sound classification, achieving near state-of-the-art results with a single encoder on SUPERB and HEAR benchmarks.

comment: Accepted to ASRU 2025

♻ ☆ S2Cap: A Benchmark and a Baseline for Singing Style Captioning

Hyunjong Ok, Jaeho Lee

Singing voices contain much richer information than common voices, including varied vocal and acoustic properties. However, current open-source audio-text datasets for singing voices capture only a narrow range of attributes and lack acoustic features, leading to limited utility towards downstream tasks, such as style captioning. To fill this gap, we formally define the singing style captioning task and present S2Cap, a dataset of singing voices with detailed descriptions covering diverse vocal, acoustic, and demographic characteristics. Using this dataset, we develop an efficient and straightforward baseline algorithm for singing style captioning. The dataset is available at https://zenodo.org/records/15673764.

comment: CIKM 2025 Resource Paper

Audio and Speech Processing 5

☆ Arabic ASR on the SADA Large-Scale Arabic Speech Corpus with Transformer-Based Models

Branislav Gerazov, Marcello Politi, Sébastien Bratières

We explore the performance of several state-of-the-art automatic speech recognition (ASR) models on a large-scale Arabic speech dataset, the SADA (Saudi Audio Dataset for Arabic), which contains 668 hours of high-quality audio from Saudi television shows. The dataset includes multiple dialects and environments, specifically a noisy subset that makes it particularly challenging for ASR. We evaluate the performance of the models on the SADA test set, and we explore the impact of fine-tuning, language models, as well as noise and denoising on their performance. We find that the best performing model is the MMS 1B model finetuned on SADA with a 4-gram language model that achieves a WER of 40.9\% and a CER of 17.6\% on the SADA test clean set.

☆ Cryfish: On deep audio analysis with Large Language Models

Anton Mitrofanov, Sergei Novoselov, Tatiana Prisyach, Vladislav Marchevskiy, Arseniy Karelin, Nikita Khmelev, Dmitry Dutov, Stepan Malykh, Igor Agafonov, Aleksandr Nikitin, Oleg Petrov

The recent revolutionary progress in text-based large language models (LLMs) has contributed to the growth of interest in extending capabilities of such models to multimodal perception and understanding tasks. Hearing is an essential capability that is highly desired to be integrated into LLMs. However, effective integrating listening capabilities into LLMs is a significant challenge lying in generalizing complex auditory tasks across speech and sounds. To address these issues, we introduce Cryfish, our version of auditory-capable LLM. The model integrates WavLM audio-encoder features into Qwen2 model using a transformer-based connector. Cryfish is adapted to various auditory tasks through a specialized training strategy. We evaluate the model on the new Dynamic SUPERB Phase-2 comprehensive multitask benchmark specifically designed for auditory-capable models. The paper presents an in-depth analysis and detailed comparison of Cryfish with the publicly available models.

☆ Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts

Ashi Garg, Zexin Cai, Henry Li Xinyuan, Leibny Paola García-Perera, Kevin Duh, Sanjeev Khudanpur, Matthew Wiesner, Nicholas Andrews

We address the challenge of detecting synthesized speech under distribution shifts -- arising from unseen synthesis methods, speakers, languages, or audio conditions -- relative to the training data. Few-shot learning methods are a promising way to tackle distribution shifts by rapidly adapting on the basis of a few in-distribution samples. We propose a self-attentive prototypical network to enable more robust few-shot adaptation. To evaluate our approach, we systematically compare the performance of traditional zero-shot detectors and the proposed few-shot detectors, carefully controlling training conditions to introduce distribution shifts at evaluation time. In conditions where distribution shifts hamper the zero-shot performance, our proposed few-shot adaptation technique can quickly adapt using as few as 10 in-distribution samples -- achieving upto 32% relative EER reduction on deepfakes in Japanese language and 20% relative reduction on ASVspoof 2021 Deepfake dataset.

♻ ☆ USAD: Universal Speech and Audio Representation via Distillation

Heng-Jui Chang, Saurabhchand Bhati, James Glass, Alexander H. Liu

comment: Accepted to ASRU 2025

♻ ☆ S2Cap: A Benchmark and a Baseline for Singing Style Captioning

Hyunjong Ok, Jaeho Lee

comment: CIKM 2025 Resource Paper

Computer Vision and Pattern Recognition 143

☆ 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

Zhaoxi Chen, Tianqi Liu, Long Zhuo, Jiawei Ren, Zeng Tao, He Zhu, Fangzhou Hong, Liang Pan, Ziwei Liu

We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) to alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) we introduce a unified 6D video representation that jointly models RGB and XYZ sequences, facilitating structured learning of both appearance and geometry. 3) we propose a set of simple yet effective adaptation strategies to repurpose pretrained video diffusion models for 4D modeling. 4DNeX produces high-quality dynamic point clouds that enable novel-view video synthesis. Extensive experiments demonstrate that 4DNeX outperforms existing 4D generation methods in efficiency and generalizability, offering a scalable solution for image-to-4D modeling and laying the foundation for generative 4D world models that simulate dynamic scene evolution.

comment: Project Page: https://4dnex.github.io/

☆ IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion

Wenhao Hu, Zesheng Li, Haonan Zhou, Liu Liu, Xuexiang Wen, Zhizhong Su, Xi Li, Gaoang Wang

Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Multiview observations from a single scene scan often fail to capture the full structural details. Existing approaches typically rely on multi stage pipelines, such as segmentation, background completion, and inpainting or require per-object dense scanning, both of which are error-prone, and not easily scalable. We propose IGFuse, a novel framework that reconstructs interactive Gaussian scene by fusing observations from multiple scans, where natural object rearrangement between captures reveal previously occluded regions. Our method constructs segmentation aware Gaussian fields and enforces bi-directional photometric and semantic consistency across scans. To handle spatial misalignments, we introduce a pseudo-intermediate scene state for unified alignment, alongside collaborative co-pruning strategies to refine geometry. IGFuse enables high fidelity rendering and object level scene manipulation without dense observations or complex pipelines. Extensive experiments validate the framework's strong generalization to novel scene configurations, demonstrating its effectiveness for real world 3D reconstruction and real-to-simulation transfer. Our project page is available online.

comment: Project page: https://whhu7.github.io/IGFuse

☆ Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

Zhongang Cai, Yubo Wang, Qingping Sun, Ruisi Wang, Chenyang Gu, Wanqi Yin, Zhiqian Lin, Zhitao Yang, Chen Wei, Xuanke Shi, Kewang Deng, Xiaoyang Han, Zukai Chen, Jiaqi Li, Xiangyu Fan, Hanming Deng, Lewei Lu, Bo Li, Ziwei Liu, Quan Wang, Dahua Lin, Lei Yang

Multi-modal models have achieved remarkable progress in recent years. Nevertheless, they continue to exhibit notable limitations in spatial understanding and reasoning, which are fundamental capabilities to achieving artificial general intelligence. With the recent release of GPT-5, allegedly the most powerful AI model to date, it is timely to examine where the leading models stand on the path toward spatial intelligence. First, we propose a comprehensive taxonomy of spatial tasks that unifies existing benchmarks and discuss the challenges in ensuring fair evaluation. We then evaluate state-of-the-art proprietary and open-source models on eight key benchmarks, at a cost exceeding one billion total tokens. Our empirical study reveals that (1) GPT-5 demonstrates unprecedented strength in spatial intelligence, yet (2) still falls short of human performance across a broad spectrum of tasks. Moreover, we (3) identify the more challenging spatial intelligence problems for multi-modal models, and (4) proprietary models do not exhibit a decisive advantage when facing the most difficult problems. In addition, we conduct a qualitative evaluation across a diverse set of scenarios that are intuitive for humans yet fail even the most advanced multi-modal models.

☆ Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

Ling-Hao Chen, Yuhong Zhang, Zixin Yin, Zhiyang Dou, Xin Chen, Jingbo Wang, Taku Komura, Lei Zhang

This work studies the challenge of transfer animations between characters whose skeletal topologies differ substantially. While many techniques have advanced retargeting techniques in decades, transfer motions across diverse topologies remains less-explored. The primary obstacle lies in the inherent topological inconsistency between source and target skeletons, which restricts the establishment of straightforward one-to-one bone correspondences. Besides, the current lack of large-scale paired motion datasets spanning different topological structures severely constrains the development of data-driven approaches. To address these limitations, we introduce Motion2Motion, a novel, training-free framework. Simply yet effectively, Motion2Motion works with only one or a few example motions on the target skeleton, by accessing a sparse set of bone correspondences between the source and target skeletons. Through comprehensive qualitative and quantitative evaluations, we demonstrate that Motion2Motion achieves efficient and reliable performance in both similar-skeleton and cross-species skeleton transfer scenarios. The practical utility of our approach is further evidenced by its successful integration in downstream applications and user interfaces, highlighting its potential for industrial applications. Code and data are available at https://lhchen.top/Motion2Motion.

comment: SIGGRAPH Asia 2025

☆ Precise Action-to-Video Generation Through Visual Action Prompts

Yuang Wang, Chao Wen, Haoyu Guo, Sida Peng, Minghan Qin, Hujun Bao, Xiaowei Zhou, Ruizhen Hu

We present visual action prompts, a unified action representation for action-to-video generation of complex high-DoF interactions while maintaining transferable visual dynamics across domains. Action-driven video generation faces a precision-generality trade-off: existing methods using text, primitive actions, or coarse masks offer generality but lack precision, while agent-centric action signals provide precision at the cost of cross-domain transferability. To balance action precision and dynamic transferability, we propose to "render" actions into precise visual prompts as domain-agnostic representations that preserve both geometric precision and cross-domain adaptability for complex actions; specifically, we choose visual skeletons for their generality and accessibility. We propose robust pipelines to construct skeletons from two interaction-rich data sources - human-object interactions (HOI) and dexterous robotic manipulation - enabling cross-domain training of action-driven generative models. By integrating visual skeletons into pretrained video generation models via lightweight fine-tuning, we enable precise action control of complex interaction while preserving the learning of cross-domain dynamics. Experiments on EgoVid, RT-1 and DROID demonstrate the effectiveness of our proposed approach. Project page: https://zju3dv.github.io/VAP/.

comment: Accepted to ICCV 2025. Project page: https://zju3dv.github.io/VAP/

☆ Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy

Tianyi Zhang, Haonan Duan, Haoran Hao, Yu Qiao, Jifeng Dai, Zhi Hou

Vision-Language-Action (VLA) models frequently encounter challenges in generalizing to real-world environments due to inherent discrepancies between observation and action spaces. Although training data are collected from diverse camera perspectives, the models typically predict end-effector poses within the robot base coordinate frame, resulting in spatial inconsistencies. To mitigate this limitation, we introduce the Observation-Centric VLA (OC-VLA) framework, which grounds action predictions directly in the camera observation space. Leveraging the camera's extrinsic calibration matrix, OC-VLA transforms end-effector poses from the robot base coordinate system into the camera coordinate system, thereby unifying prediction targets across heterogeneous viewpoints. This lightweight, plug-and-play strategy ensures robust alignment between perception and action, substantially improving model resilience to camera viewpoint variations. The proposed approach is readily compatible with existing VLA architectures, requiring no substantial modifications. Comprehensive evaluations on both simulated and real-world robotic manipulation tasks demonstrate that OC-VLA accelerates convergence, enhances task success rates, and improves cross-view generalization. The code will be publicly available.

☆ Real-Time Beach Litter Detection and Counting: A Comparative Analysis of RT-DETR Model Variants

Miftahul Huda, Arsyiah Azahra, Putri Maulida Chairani, Dimas Rizky Ramadhani, Nabila Azhari, Ade Lailani

Coastal pollution is a pressing global environmental issue, necessitating scalable and automated solutions for monitoring and management. This study investigates the efficacy of the Real-Time Detection Transformer (RT-DETR), a state-of-the-art, end-to-end object detection model, for the automated detection and counting of beach litter. A rigorous comparative analysis is conducted between two model variants, RT-DETR-Large (RT-DETR-L) and RT-DETR-Extra-Large (RT-DETR-X), trained on a publicly available dataset of coastal debris. The evaluation reveals that the RT-DETR-X model achieves marginally superior accuracy, with a mean Average Precision at 50\% IoU (mAP@50) of 0.816 and a mAP@50-95 of 0.612, compared to the RT-DETR-L model's 0.810 and 0.606, respectively. However, this minor performance gain is realized at a significant computational cost; the RT-DETR-L model demonstrates a substantially faster inference time of 20.1 ms versus 34.5 ms for the RT-DETR-X. The findings suggest that the RT-DETR-L model offers a more practical and efficient solution for real-time, in-field deployment due to its superior balance of processing speed and detection accuracy. This research provides valuable insights into the application of advanced Transformer-based detectors for environmental conservation, highlighting the critical trade-offs between model complexity and operational viability.

☆ DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation

Zihua Liu, Yizhou Li, Songyan Zhang, Masatoshi Okutomi

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require further investigation. A primary challenge arises from ambiguity introduced during photometric reconstruction, particularly due to missing corresponding pixels in ill-posed regions of the target view, such as occlusions and out-of-frame areas. To address this and establish explicit photometric correspondences, we propose DMS, a model-agnostic approach that utilizes geometric priors from diffusion models to synthesize novel views along the epipolar direction, guided by directional prompts. Specifically, we finetune a Stable Diffusion model to simulate perspectives at key positions: left-left view shifted from the left camera, right-right view shifted from the right camera, along with an additional novel view between the left and right cameras. These synthesized views supplement occluded pixels, enabling explicit photometric reconstruction. Our proposed DMS is a cost-free, ''plug-and-play'' method that seamlessly enhances self-supervised stereo matching and monocular depth estimation, and relies solely on unlabeled stereo image pairs for both training and synthesizing. Extensive experiments demonstrate the effectiveness of our approach, with up to 35% outlier reduction and state-of-the-art performance across multiple benchmark datasets.

☆ Checkmate: interpretable and explainable RSVQA is the endgame

Lucrezia Tosato, Christel Tartini Chappuis, Syrielle Montariol, Flora Weissgerber, Sylvain Lobry, Devis Tuia

Remote Sensing Visual Question Answering (RSVQA) presents unique challenges in ensuring that model decisions are both understandable and grounded in visual content. Current models often suffer from a lack of interpretability and explainability, as well as from biases in dataset distributions that lead to shortcut learning. In this work, we tackle these issues by introducing a novel RSVQA dataset, Chessboard, designed to minimize biases through 3'123'253 questions and a balanced answer distribution. Each answer is linked to one or more cells within the image, enabling fine-grained visual reasoning. Building on this dataset, we develop an explainable and interpretable model called Checkmate that identifies the image cells most relevant to its decisions. Through extensive experiments across multiple model architectures, we show that our approach improves transparency and supports more trustworthy decision-making in RSVQA systems.

☆ ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset

Qingwen Zeng, Juan E. Tapia, Izan Garcia, Juan M. Espin, Christoph Busch

Nowadays, the development of a Presentation Attack Detection (PAD) system for ID cards presents a challenge due to the lack of images available to train a robust PAD system and the increase in diversity of possible attack instrument species. Today, most algorithms focus on generating attack samples and do not take into account the limited number of bona fide images. This work is one of the first to propose a method for mimicking bona fide images by generating synthetic versions of them using Stable Diffusion, which may help improve the generalisation capabilities of the detector. Furthermore, the new images generated are evaluated in a system trained from scratch and in a commercial solution. The PAD system yields an interesting result, as it identifies our images as bona fide, which has a positive impact on detection performance and data restrictions.

☆ Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation

Tanjim Islam Riju, Shuchismita Anwar, Saman Sarker Joy, Farig Sadeque, Swakkhar Shatabda

We propose a two-stage multimodal framework that enhances disease classification and region-aware radiology report generation from chest X-rays, leveraging the MIMIC-Eye dataset. In the first stage, we introduce a gaze-guided contrastive learning architecture for disease classification. It integrates visual features, clinical labels, bounding boxes, and radiologist eye-tracking signals and is equipped with a novel multi-term gaze-attention loss combining MSE, KL divergence, correlation, and center-of-mass alignment. Incorporating fixations improves F1 score from 0.597 to 0.631 (+5.70%) and AUC from 0.821 to 0.849 (+3.41%), while also improving precision and recall, highlighting the effectiveness of gaze-informed attention supervision. In the second stage, we present a modular report generation pipeline that extracts confidence-weighted diagnostic keywords, maps them to anatomical regions using a curated dictionary constructed from domain-specific priors, and generates region-aligned sentences via structured prompts. This pipeline improves report quality as measured by clinical keyword recall and ROUGE overlap. Our results demonstrate that integrating gaze data improves both classification performance and the interpretability of generated medical reports.

☆ Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping

Siddharth Khandelwal, Sridhar Kamath, Arjun Jain

Human shape editing enables controllable transformation of a person's body shape, such as thin, muscular, or overweight, while preserving pose, identity, clothing, and background. Unlike human pose editing, which has advanced rapidly, shape editing remains relatively underexplored. Current approaches typically rely on 3D morphable models or image warping, often introducing unrealistic body proportions, texture distortions, and background inconsistencies due to alignment errors and deformations. A key limitation is the lack of large-scale, publicly available datasets for training and evaluating body shape manipulation methods. In this work, we introduce the first large-scale dataset of 18,573 images across 1523 subjects, specifically designed for controlled human shape editing. It features diverse variations in body shape, including fat, muscular and thin, captured under consistent identity, clothing, and background conditions. Using this dataset, we propose Odo, an end-to-end diffusion-based method that enables realistic and intuitive body reshaping guided by simple semantic attributes. Our approach combines a frozen UNet that preserves fine-grained appearance and background details from the input image with a ControlNet that guides shape transformation using target SMPL depth maps. Extensive experiments demonstrate that our method outperforms prior approaches, achieving per-vertex reconstruction errors as low as 7.5mm, significantly lower than the 13.6mm observed in baseline methods, while producing realistic results that accurately match the desired target shapes.

☆ XR-NPE: High-Throughput Mixed-precision SIMD Neural Processing Engine for Extended Reality Perception Workloads

Tejas Chaudhari, Akarsh J., Tanushree Dewangan, Mukul Lokhande, Santosh Kumar Vishvakarma

This work proposes XR-NPE, a high-throughput Mixed-precision SIMD Neural Processing Engine, designed for extended reality (XR) perception workloads like visual inertial odometry (VIO), object classification, and eye gaze extraction. XR-NPE is first to support FP4, Posit (4,1), Posit (8,0), and Posit (16,1) formats, with layer adaptive hybrid-algorithmic implementation supporting ultra-low bit precision to significantly reduce memory bandwidth requirements, and accompanied by quantization-aware training for minimal accuracy loss. The proposed Reconfigurable Mantissa Multiplication and Exponent processing Circuitry (RMMEC) reduces dark silicon in the SIMD MAC compute engine, assisted by selective power gating to reduce energy consumption, providing 2.85x improved arithmetic intensity. XR-NPE achieves a maximum operating frequency of 1.72 GHz, area 0.016 mm2 , and arithmetic intensity 14 pJ at CMOS 28nm, reducing 42% area, 38% power compared to the best of state-of-the-art MAC approaches. The proposed XR-NPE based AXI-enabled Matrix-multiplication co-processor consumes 1.4x fewer LUTs, 1.77x fewer FFs, and provides 1.2x better energy efficiency compared to SoTA accelerators on VCU129. The proposed co-processor provides 23% better energy efficiency and 4% better compute density for VIO workloads. XR-NPE establishes itself as a scalable, precision-adaptive compute engine for future resource-constrained XR devices. The complete set for codes for results reproducibility are released publicly, enabling designers and researchers to readily adopt and build upon them. https://github.com/mukullokhande99/XR-NPE.

☆ IntelliCap: Intelligent Guidance for Consistent View Sampling

Ayaka Yasunaga, Hideo Saito, Dieter Schmalstieg, Shohei Mori

Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in collecting the input images for these rendering algorithms has received much less attention. High-quality view synthesis requires uniform and dense view sampling. Unfortunately, these requirements are not easily addressed by human camera operators, who are in a hurry, impatient, or lack understanding of the scene structure and the photographic process. Existing approaches to guide humans during image acquisition concentrate on single objects or neglect view-dependent material characteristics. We propose a novel situated visualization technique for scanning at multiple scales. During the scanning of a scene, our method identifies important objects that need extended image coverage to properly represent view-dependent appearance. To this end, we leverage semantic segmentation and category identification, ranked by a vision-language model. Spherical proxies are generated around highly ranked objects to guide the user during scanning. Our results show superior performance in real scenes compared to conventional view sampling strategies.

comment: This work is a pre-print version of a paper that has been accepted to the IEEE International Symposium on Mixed and Augmented Reality for future publication. Project Page: https://mediated-reality.github.io/projects/yasunaga_ismar25/

☆ HierAdaptMR: Cross-Center Cardiac MRI Reconstruction with Hierarchical Feature Adapters

Ruru Xu, Ilkay Oksuz

Deep learning-based cardiac MRI reconstruction faces significant domain shift challenges when deployed across multiple clinical centers with heterogeneous scanner configurations and imaging protocols. We propose HierAdaptMR, a hierarchical feature adaptation framework that addresses multi-level domain variations through parameter-efficient adapters. Our method employs Protocol-Level Adapters for sequence-specific characteristics and Center-Level Adapters for scanner-dependent variations, built upon a variational unrolling backbone. A Universal Adapter enables generalization to entirely unseen centers through stochastic training that learns center-invariant adaptations. The framework utilizes multi-scale SSIM loss with frequency domain enhancement and contrast-adaptive weighting for robust optimization. Comprehensive evaluation on the CMRxRecon2025 dataset spanning 5+ centers, 10+ scanners, and 9 modalities demonstrates superior cross-center generalization while maintaining reconstruction quality. code: https://github.com/Ruru-Xu/HierAdaptMR

comment: MICCAI 2025, CMRxRecon2025 Challenge paper

☆ EgoTwin: Dreaming Body and View in First Person

Jingqiao Xiu, Fangzhou Hong, Yicong Li, Mengze Li, Wentao Wang, Sirui Han, Liang Pan, Ziwei Liu

While exocentric video synthesis has achieved great progress, egocentric video generation remains largely underexplored, which requires modeling first-person view content along with camera motion patterns induced by the wearer's body movements. To bridge this gap, we introduce a novel task of joint egocentric video and human motion generation, characterized by two key challenges: 1) Viewpoint Alignment: the camera trajectory in the generated video must accurately align with the head trajectory derived from human motion; 2) Causal Interplay: the synthesized human motion must causally align with the observed visual dynamics across adjacent video frames. To address these challenges, we propose EgoTwin, a joint video-motion generation framework built on the diffusion transformer architecture. Specifically, EgoTwin introduces a head-centric motion representation that anchors the human motion to the head joint and incorporates a cybernetics-inspired interaction mechanism that explicitly captures the causal interplay between video and motion within attention operations. For comprehensive evaluation, we curate a large-scale real-world dataset of synchronized text-video-motion triplets and design novel metrics to assess video-motion consistency. Extensive experiments demonstrate the effectiveness of the EgoTwin framework.

☆ Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

Xianglong He, Chunli Peng, Zexiang Liu, Boyang Wang, Yifan Zhang, Qi Cui, Fei Kang, Biao Jiang, Mengyin An, Yangyang Ren, Baixin Xu, Hao-Xiang Guo, Kaixiong Gong, Cyrus Wu, Wei Li, Xuchen Song, Yang Liu, Eric Li, Yahui Zhou

Recent advances in interactive video generations have demonstrated diffusion model's potential as world models by capturing complex physical dynamics and interactive behaviors. However, existing interactive world models depend on bidirectional attention and lengthy inference steps, severely limiting real-time performance. Consequently, they are hard to simulate real-world dynamics, where outcomes must update instantaneously based on historical context and current actions. To address this, we present Matrix-Game 2.0, an interactive world model generates long videos on-the-fly via few-step auto-regressive diffusion. Our framework consists of three key components: (1) A scalable data production pipeline for Unreal Engine and GTA5 environments to effectively produce massive amounts (about 1200 hours) of video data with diverse interaction annotations; (2) An action injection module that enables frame-level mouse and keyboard inputs as interactive conditions; (3) A few-step distillation based on the casual architecture for real-time and streaming video generation. Matrix Game 2.0 can generate high-quality minute-level videos across diverse scenes at an ultra-fast speed of 25 FPS. We open-source our model weights and codebase to advance research in interactive world modeling.

comment: Project Page: https://matrix-game-v2.github.io

☆ SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception

Melih Yazgan, Qiyuan Wu, Iramm Hamdard, Shiqi Li, J. Marius Zoellner

Collaborative perception allows connected autonomous vehicles (CAVs) to overcome occlusion and limited sensor range by sharing intermediate features. Yet transmitting dense Bird's-Eye-View (BEV) feature maps can overwhelm the bandwidth available for inter-vehicle communication. We present SlimComm, a communication-efficient framework that integrates 4D radar Doppler with a query-driven sparse scheme. SlimComm builds a motion-centric dynamic map to distinguish moving from static objects and generates two query types: (i) reference queries on dynamic and high-confidence regions, and (ii) exploratory queries probing occluded areas via a two-stage offset. Only query-specific BEV features are exchanged and fused through multi-scale gated deformable attention, reducing payload while preserving accuracy. For evaluation, we release OPV2V-R and Adver-City-R, CARLA-based datasets with per-point Doppler radar. SlimComm achieves up to 90% lower bandwidth than full-map sharing while matching or surpassing prior baselines across varied traffic densities and occlusions. Dataset and code will be available at: https://url.fzi.de/SlimComm.

comment: Accepted by ICCV - Drive2X Workshop

☆ Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learning

Jiawen Xu, Odej Kao

Open set recognition (OSR) and continual learning are two critical challenges in machine learning, focusing respectively on detecting novel classes at inference time and updating models to incorporate the new classes. While many recent approaches have addressed these problems, particularly OSR, by heuristically promoting feature diversity, few studies have directly examined the role that feature diversity plays in tackling them. In this work, we provide empirical evidence that enhancing feature diversity improves the recognition of open set samples. Moreover, increased feature diversity also facilitates both the retention of previously learned data and the integration of new data in continual learning. We hope our findings can inspire further research into both practical methods and theoretical understanding in these domains.

☆ Omni Survey for Multimodality Analysis in Visual Object Tracking

Zhangyong Tang, Tianyang Xu, Xuefeng Zhu, Hui Li, Shaochuan Zhao, Tao Zhou, Chunyang Cheng, Xiaojun Wu, Josef Kittler

The development of smart cities has led to the generation of massive amounts of multi-modal data in the context of a range of tasks that enable a comprehensive monitoring of the smart city infrastructure and services. This paper surveys one of the most critical tasks, multi-modal visual object tracking (MMVOT), from the perspective of multimodality analysis. Generally, MMVOT differs from single-modal tracking in four key aspects, data collection, modality alignment and annotation, model designing, and evaluation. Accordingly, we begin with an introduction to the relevant data modalities, laying the groundwork for their integration. This naturally leads to a discussion of challenges of multi-modal data collection, alignment, and annotation. Subsequently, existing MMVOT methods are categorised, based on different ways to deal with visible (RGB) and X modalities: programming the auxiliary X branch with replicated or non-replicated experimental configurations from the RGB branch. Here X can be thermal infrared (T), depth (D), event (E), near infrared (NIR), language (L), or sonar (S). The final part of the paper addresses evaluation and benchmarking. In summary, we undertake an omni survey of all aspects of multi-modal visual object tracking (VOT), covering six MMVOT tasks and featuring 338 references in total. In addition, we discuss the fundamental rhetorical question: Is multi-modal tracking always guaranteed to provide a superior solution to unimodal tracking with the help of information fusion, and if not, in what circumstances its application is beneficial. Furthermore, for the first time in this field, we analyse the distributions of the object categories in the existing MMVOT datasets, revealing their pronounced long-tail nature and a noticeable lack of animal categories when compared with RGB datasets.

comment: The first comprehensive survey for multi-modal visual object tracking; 6 multi-modal tasks; 338 references

☆ Vitamin N: Benefits of Different Forms of Public Greenery for Urban Health

Sanja Šćepanović, Sagar Joglekar, Stephen Law, Daniele Quercia, Ke Zhou, Alice Battiston, Rossano Schifanella

Urban greenery is often linked to better health, yet findings from past research have been inconsistent. One reason is that official greenery metrics measure the amount or nearness of greenery but ignore how often people actually may potentially see or use it in daily life. To address this gap, we introduced a new classification that separates on-road greenery, which people see while walking through streets, from off-road greenery, which requires planned visits. We did so by combining aerial imagery of Greater London and greenery data from OpenStreetMap with quantified greenery from over 100,000 Google Street View images and accessibility estimates based on 160,000 road segments. We linked these measures to 7.45 billion medical prescriptions issued by the National Health Service and processed through our methodology. These prescriptions cover five conditions: diabetes, hypertension, asthma, depression, and anxiety, as well as opioid use. As hypothesized, we found that green on-road was more strongly linked to better health than four widely used official measures. For example, hypertension prescriptions dropped by 3.68% in wards with on-road greenery above the median citywide level compared to those below it. If all below-median wards reached the citywide median in on-road greenery, prescription costs could fall by up to {\pounds}3.15 million each year. These results suggest that greenery seen in daily life may be more relevant than public yet secluded greenery, and that official metrics commonly used in the literature have important limitations.

☆ Point upsampling networks for single-photon sensing

Jinyi Liu, Guoyang Zhao, Lijun Liu, Yiguang Hong, Weiping Zhang, Shuming Cheng

Single-photon sensing has generated great interest as a prominent technique of long-distance and ultra-sensitive imaging, however, it tends to yield sparse and spatially biased point clouds, thus limiting its practical utility. In this work, we propose using point upsampling networks to increase point density and reduce spatial distortion in single-photon point cloud. Particularly, our network is built on the state space model which integrates a multi-path scanning mechanism to enrich spatial context, a bidirectional Mamba backbone to capture global geometry and local details, and an adaptive upsample shift module to correct offset-induced distortions. Extensive experiments are implemented on commonly-used datasets to confirm its high reconstruction accuracy and strong robustness to the distortion noise, and also on real-world data to demonstrate that our model is able to generate visually consistent, detail-preserving, and noise suppressed point clouds. Our work is the first to establish the upsampling framework for single-photon sensing, and hence opens a new avenue for single-photon sensing and its practical applications in the downstreaming tasks.

comment: 13 pages, 8 figures, any comments are welcome

☆ Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature

Rohan Asthana, Joschua Conrad, Maurits Ortmanns, Vasileios Belagiannis

Zero-shot Neural Architecture Search (NAS) typically optimises the architecture search process by exploiting the network or gradient properties at initialisation through zero-cost proxies. The existing proxies often rely on labelled data, which is usually unavailable in real-world settings. Furthermore, the majority of the current methods focus either on optimising the convergence and generalisation attributes or solely on the expressivity of the network architectures. To address both limitations, we first demonstrate how channel collinearity affects the convergence and generalisation properties of a neural network. Then, by incorporating the convergence, generalisation and expressivity in one approach, we propose a zero-cost proxy that omits the requirement of labelled data for its computation. In particular, we leverage the Singular Value Decomposition (SVD) of the neural network layer features and the extrinsic curvature of the network output to design our proxy. %As a result, the proposed proxy is formulated as the simplified harmonic mean of the logarithms of two key components: the sum of the inverse of the feature condition number and the extrinsic curvature of the network output. Our approach enables accurate prediction of network performance on test data using only a single label-free data sample. Our extensive evaluation includes a total of six experiments, including the Convolutional Neural Network (CNN) search space, i.e. DARTS and the Transformer search space, i.e. AutoFormer. The proposed proxy demonstrates a superior performance on multiple correlation benchmarks, including NAS-Bench-101, NAS-Bench-201, and TransNAS-Bench-101-micro; as well as on the NAS task within the DARTS and the AutoFormer search space, all while being notably efficient. The code is available at https://github.com/rohanasthana/Dextr.

comment: Accepted at Transactions on Machine Learning Research (TMLR)

☆ Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation

Qirui Li, Guangcong Zheng, Qi Zhao, Jie Li, Bin Dong, Yiwu Yao, Xi Li

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse patterns, fail to fully exploit the inherent spatio-temporal redundancies in video data. Through systematic analysis of video diffusion transformers (DiT), we uncover a key insight: Attention matrices exhibit structured, yet heterogeneous sparsity patterns, where specialized heads dynamically attend to distinct spatiotemporal regions (e.g., local pattern, cross-shaped pattern, or global pattern). Existing sparse attention methods either impose rigid constraints or introduce significant overhead, limiting their effectiveness. To address this, we propose Compact Attention, a hardware-aware acceleration framework featuring three innovations: 1) Adaptive tiling strategies that approximate diverse spatial interaction patterns via dynamic tile grouping, 2) Temporally varying windows that adjust sparsity levels based on frame proximity, and 3) An automated configuration search algorithm that optimizes sparse patterns while preserving critical attention pathways. Our method achieves 1.6~2.5x acceleration in attention computation on single-GPU setups while maintaining comparable visual quality with full-attention baselines. This work provides a principled approach to unlocking efficient long-form video generation through structured sparsity exploitation. Project Page: https://yo-ava.github.io/Compact-Attention.github.io/

☆ GazeDETR: Gaze Detection using Disentangled Head and Gaze Representations

Ryan Anthony Jalova de Belen, Gelareh Mohammadi, Arcot Sowmya

Gaze communication plays a crucial role in daily social interactions. Quantifying this behavior can help in human-computer interaction and digital phenotyping. While end-to-end models exist for gaze target detection, they only utilize a single decoder to simultaneously localize human heads and predict their corresponding gaze (e.g., 2D points or heatmap) in a scene. This multitask learning approach generates a unified and entangled representation for human head localization and gaze location prediction. Herein, we propose GazeDETR, a novel end-to-end architecture with two disentangled decoders that individually learn unique representations and effectively utilize coherent attentive fields for each subtask. More specifically, we demonstrate that its human head predictor utilizes local information, while its gaze decoder incorporates both local and global information. Our proposed architecture achieves state-of-the-art results on the GazeFollow, VideoAttentionTarget and ChildPlay datasets. It outperforms existing end-to-end models with a notable margin.

☆ Multi-Phase Automated Segmentation of Dental Structures in CBCT Using a Lightweight Auto3DSeg and SegResNet Implementation

Dominic LaBella, Keshav Jha, Jared Robbins, Esther Yu

Cone-beam computed tomography (CBCT) has become an invaluable imaging modality in dentistry, enabling 3D visualization of teeth and surrounding structures for diagnosis and treatment planning. Automated segmentation of dental structures in CBCT can efficiently assist in identifying pathology (e.g., pulpal or periapical lesions) and facilitate radiation therapy planning in head and neck cancer patients. We describe the DLaBella29 team's approach for the MICCAI 2025 ToothFairy3 Challenge, which involves a deep learning pipeline for multi-class tooth segmentation. We utilized the MONAI Auto3DSeg framework with a 3D SegResNet architecture, trained on a subset of the ToothFairy3 dataset (63 CBCT scans) with 5-fold cross-validation. Key preprocessing steps included image resampling to 0.6 mm isotropic resolution and intensity clipping. We applied an ensemble fusion using Multi-Label STAPLE on the 5-fold predictions to infer a Phase 1 segmentation and then conducted tight cropping around the easily segmented Phase 1 mandible to perform Phase 2 segmentation on the smaller nerve structures. Our method achieved an average Dice of 0.87 on the ToothFairy3 challenge out-of-sample validation set. This paper details the clinical context, data preparation, model development, results of our approach, and discusses the relevance of automated dental segmentation for improving patient care in radiation oncology.

comment: MICCAI. ToothFairy3, 16 pages, 5 figures, 1 table

☆ Breaking Reward Collapse: Adaptive Reinforcement for Open-ended Medical Reasoning with Enhanced Semantic Discrimination

Yizhou Liu, Jingwei Wei, Zizhi Chen, Minghao Han, Xukun Zhang, Keliang Liu, Lihua Zhang

Reinforcement learning (RL) with rule-based rewards has demonstrated strong potential in enhancing the reasoning and generalization capabilities of vision-language models (VLMs) and large language models (LLMs), while reducing computational overhead. However, its application in medical imaging remains underexplored. Existing reinforcement fine-tuning (RFT) approaches in this domain primarily target closed-ended visual question answering (VQA), limiting their applicability to real-world clinical reasoning. In contrast, open-ended medical VQA better reflects clinical practice but has received limited attention. While some efforts have sought to unify both formats via semantically guided RL, we observe that model-based semantic rewards often suffer from reward collapse, where responses with significant semantic differences receive similar scores. To address this, we propose ARMed (Adaptive Reinforcement for Medical Reasoning), a novel RL framework for open-ended medical VQA. ARMed first incorporates domain knowledge through supervised fine-tuning (SFT) on chain-of-thought data, then applies reinforcement learning with textual correctness and adaptive semantic rewards to enhance reasoning quality. We evaluate ARMed on six challenging medical VQA benchmarks. Results show that ARMed consistently boosts both accuracy and generalization, achieving a 32.64% improvement on in-domain tasks and an 11.65% gain on out-of-domain benchmarks. These results highlight the critical role of reward discriminability in medical RL and the promise of semantically guided rewards for enabling robust and clinically meaningful multimodal reasoning.

☆ MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation

Wei Wei, Shaojie Zhang, Yonghao Dang, Jianqin Yin

Human action recognition is a crucial task for intelligent robotics, particularly within the context of human-robot collaboration research. In self-supervised skeleton-based action recognition, the mask-based reconstruction paradigm learns the spatial structure and motion patterns of the skeleton by masking joints and reconstructing the target from unlabeled data. However, existing methods focus on a limited set of joints and low-order motion patterns, limiting the model's ability to understand complex motion patterns. To address this issue, we introduce MaskSem, a novel semantic-guided masking method for learning 3D hybrid high-order motion representations. This novel framework leverages Grad-CAM based on relative motion to guide the masking of joints, which can be represented as the most semantically rich temporal orgions. The semantic-guided masking process can encourage the model to explore more discriminative features. Furthermore, we propose using hybrid high-order motion as the reconstruction target, enabling the model to learn multi-order motion patterns. Specifically, low-order motion velocity and high-order motion acceleration are used together as the reconstruction target. This approach offers a more comprehensive description of the dynamic motion process, enhancing the model's understanding of motion patterns. Experiments on the NTU60, NTU120, and PKU-MMD datasets show that MaskSem, combined with a vanilla transformer, improves skeleton-based action recognition, making it more suitable for applications in human-robot interaction.

comment: Accepted to IROS 2025

☆ Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

Jianshu Zeng, Yuxuan Liu, Yutong Feng, Chenxuan Miao, Zixiang Gao, Jiwang Qu, Jianzhang Zhang, Bin Wang, Kun Yuan

Video relighting is a challenging yet valuable task, aiming to replace the background in videos while correspondingly adjusting the lighting in the foreground with harmonious blending. During translation, it is essential to preserve the original properties of the foreground, e.g., albedo, and propagate consistent relighting among temporal frames. In this paper, we propose Lumen, an end-to-end video relighting framework developed on large-scale video generative models, receiving flexible textual description for instructing the control of lighting and background. Considering the scarcity of high-qualified paired videos with the same foreground in various lighting conditions, we construct a large-scale dataset with a mixture of realistic and synthetic videos. For the synthetic domain, benefiting from the abundant 3D assets in the community, we leverage advanced 3D rendering engine to curate video pairs in diverse environments. For the realistic domain, we adapt a HDR-based lighting simulation to complement the lack of paired in-the-wild videos. Powered by the aforementioned dataset, we design a joint training curriculum to effectively unleash the strengths of each domain, i.e., the physical consistency in synthetic videos, and the generalized domain distribution in realistic videos. To implement this, we inject a domain-aware adapter into the model to decouple the learning of relighting and domain appearance distribution. We construct a comprehensive benchmark to evaluate Lumen together with existing methods, from the perspectives of foreground preservation and video consistency assessment. Experimental results demonstrate that Lumen effectively edit the input into cinematic relighted videos with consistent lighting and strict foreground preservation. Our project page: https://lumen-relight.github.io/

comment: 15 pages, 7 figures

☆ Fully Automated Segmentation of Fiber Bundles in Anatomic Tracing Data

Kyriaki-Margarita Bintsi, Yaël Balbastre, Jingjing Wu, Julia F. Lehman, Suzanne N. Haber, Anastasia Yendiki

comment: Accepted at CDMRI, MICCAI 2025

☆ SEDEG:Sequential Enhancement of Decoder and Encoder's Generality for Class Incremental Learning with Small Memory

Hongyang Chen, Shaoling Pu, Lingyu Zheng, Zhongwu Sun

In incremental learning, enhancing the generality of knowledge is crucial for adapting to dynamic data inputs. It can develop generalized representations or more balanced decision boundaries, preventing the degradation of long-term knowledge over time and thus mitigating catastrophic forgetting. Some emerging incremental learning methods adopt an encoder-decoder architecture and have achieved promising results. In the encoder-decoder achitecture, improving the generalization capabilities of both the encoder and decoder is critical, as it helps preserve previously learned knowledge while ensuring adaptability and robustness to new, diverse data inputs. However, many existing continual methods focus solely on enhancing one of the two components, which limits their effectiveness in mitigating catastrophic forgetting. And these methods perform even worse in small-memory scenarios, where only a limited number of historical samples can be stored. To mitigate this limitation, we introduces SEDEG, a two-stage training framework for vision transformers (ViT), focusing on sequentially improving the generality of both Decoder and Encoder. Initially, SEDEG trains an ensembled encoder through feature boosting to learn generalized representations, which subsequently enhance the decoder's generality and balance the classifier. The next stage involves using knowledge distillation (KD) strategies to compress the ensembled encoder and develop a new, more generalized encoder. This involves using a balanced KD approach and feature KD for effective knowledge transfer. Extensive experiments on three benchmark datasets show SEDEG's superior performance, and ablation studies confirm the efficacy of its components. The code is available at https://github.com/ShaolingPu/CIL.

comment: Accepted by ICONIP2025

☆ Towards High-Resolution Industrial Image Anomaly Detection

Ximiao Zhang, Min Xu, Xiuzhuang Zhou

Current anomaly detection methods primarily focus on low-resolution scenarios. For high-resolution images, conventional downsampling often results in missed detections of subtle anomalous regions due to the loss of fine-grained discriminative information. Despite some progress, recent studies have attempted to improve detection resolution by employing lightweight networks or using simple image tiling and ensemble methods. However, these approaches still struggle to meet the practical demands of industrial scenarios in terms of detection accuracy and efficiency. To address the above issues, we propose HiAD, a general framework for high-resolution anomaly detection. HiAD is capable of detecting anomalous regions of varying sizes in high-resolution images under limited computational resources. Specifically, HiAD employs a dual-branch architecture that integrates anomaly cues across different scales to comprehensively capture both subtle and large-scale anomalies. Furthermore, it incorporates a multi-resolution feature fusion strategy to tackle the challenges posed by fine-grained texture variations in high-resolution images. To enhance both adaptability and efficiency, HiAD utilizes a detector pool in conjunction with various detector assignment strategies, enabling detectors to be adaptively assigned based on patch features, ensuring detection performance while effectively controlling computational costs. We conduct extensive experiments on our specifically constructed high-resolution anomaly detection benchmarks, including MVTec-HD, VisA-HD, and the real-world benchmark RealIAD-HD, demonstrating the superior performance of HiAD. The code is available at https://github.com/cnulab/HiAD.

☆ 7Bench: a Comprehensive Benchmark for Layout-guided Text-to-image Models

Elena Izzo, Luca Parolari, Davide Vezzaro, Lamberto Ballan

Layout-guided text-to-image models offer greater control over the generation process by explicitly conditioning image synthesis on the spatial arrangement of elements. As a result, their adoption has increased in many computer vision applications, ranging from content creation to synthetic data generation. A critical challenge is achieving precise alignment between the image, textual prompt, and layout, ensuring semantic fidelity and spatial accuracy. Although recent benchmarks assess text alignment, layout alignment remains overlooked, and no existing benchmark jointly evaluates both. This gap limits the ability to evaluate a model's spatial fidelity, which is crucial when using layout-guided generation for synthetic data, as errors can introduce noise and degrade data quality. In this work, we introduce 7Bench, the first benchmark to assess both semantic and spatial alignment in layout-guided text-to-image generation. It features text-and-layout pairs spanning seven challenging scenarios, investigating object generation, color fidelity, attribute recognition, inter-object relationships, and spatial control. We propose an evaluation protocol that builds on existing frameworks by incorporating the layout alignment score to assess spatial accuracy. Using 7Bench, we evaluate several state-of-the-art diffusion models, uncovering their respective strengths and limitations across diverse alignment tasks. The benchmark is available at https://github.com/Elizzo/7Bench.

comment: Accepted to ICIAP 2025

☆ CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Prediction

Zhiwei Ning, Zhaojiang Liu, Xuanang Gao, Yifan Zuo, Jie Yang, Yuming Fang, Wei Liu

Multi-modal methods based on camera and LiDAR sensors have garnered significant attention in the field of 3D detection. However, many prevalent works focus on single or partial stage fusion, leading to insufficient feature extraction and suboptimal performance. In this paper, we introduce a multi-stage cross-modal fusion 3D detection framework, termed CMF-IOU, to effectively address the challenge of aligning 3D spatial and 2D semantic information. Specifically, we first project the pixel information into 3D space via a depth completion network to get the pseudo points, which unifies the representation of the LiDAR and camera information. Then, a bilateral cross-view enhancement 3D backbone is designed to encode LiDAR points and pseudo points. The first sparse-to-distant (S2D) branch utilizes an encoder-decoder structure to reinforce the representation of sparse LiDAR points. The second residual view consistency (ResVC) branch is proposed to mitigate the influence of inaccurate pseudo points via both the 3D and 2D convolution processes. Subsequently, we introduce an iterative voxel-point aware fine grained pooling module, which captures the spatial information from LiDAR points and textural information from pseudo points in the proposal refinement stage. To achieve more precise refinement during iteration, an intersection over union (IoU) joint prediction branch integrated with a novel proposals generation technique is designed to preserve the bounding boxes with both high IoU and classification scores. Extensive experiments show the superior performance of our method on the KITTI, nuScenes and Waymo datasets.

comment: The Paper is Accepted by TCSVT

☆ CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis

Jiayi Wang, Hadrien Reynaud, Franciskus Xaverius Erick, Bernhard Kainz

Generative modelling of entire CT volumes conditioned on clinical reports has the potential to accelerate research through data augmentation, privacy-preserving synthesis and reducing regulator-constraints on patient data while preserving diagnostic signals. With the recent release of CT-RATE, a large-scale collection of 3D CT volumes paired with their respective clinical reports, training large text-conditioned CT volume generation models has become achievable. In this work, we introduce CTFlow, a 0.5B latent flow matching transformer model, conditioned on clinical reports. We leverage the A-VAE from FLUX to define our latent space, and rely on the CT-Clip text encoder to encode the clinical reports. To generate consistent whole CT volumes while keeping the memory constraints tractable, we rely on a custom autoregressive approach, where the model predicts the first sequence of slices of the volume from text-only, and then relies on the previously generated sequence of slices and the text, to predict the following sequence. We evaluate our results against state-of-the-art generative CT model, and demonstrate the superiority of our approach in terms of temporal coherence, image diversity and text-image alignment, with FID, FVD, IS scores and CLIP score.

☆ ONG: One-Shot NMF-based Gradient Masking for Efficient Model Sparsification

Sankar Behera, Yamuna Prasad

Deep Neural Networks (DNNs) have achieved remarkable success but their large size poses deployment challenges. While various pruning techniques exist, many involve complex iterative processes, specialized criteria, or struggle to maintain sparsity effectively during training. We introduce ONG (One-shot NMF-based Gradient Masking), a novel sparsification strategy that identifies salient weight structures using Non-negative Matrix Factorization (NMF) for one-shot pruning at the outset of training. Subsequently, ONG employs a precise gradient masking mechanism to ensure that only unpruned weights are updated, strictly preserving the target sparsity throughout the training phase. We integrate ONG into the BIMP comparative framework and evaluate it on CIFAR-10 and CIFAR-100 with ResNet56, ResNet34, and ResNet18 against established stable sparsification methods. Our experiments demonstrate ONG's ability to achieve comparable or superior performance at various sparsity levels while maintaining structural integrity post-pruning and offering a clear mechanism for targeting desired sparsities.

comment: 7 pages

☆ S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

Chubin Chen, Jiashu Zhu, Xiaokun Feng, Nisha Huang, Meiqi Wu, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Xiu Li

Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Gaussian mixture modeling with a closed-form solution, we observe a discrepancy between the suboptimal results produced by CFG and the ground truth. The model's excessive reliance on these suboptimal predictions often leads to semantic incoherence and low-quality outputs. To address this issue, we first empirically demonstrate that the model's suboptimal predictions can be effectively refined using sub-networks of the model itself. Building on this insight, we propose S^2-Guidance, a novel method that leverages stochastic block-dropping during the forward process to construct stochastic sub-networks, effectively guiding the model away from potential low-quality predictions and toward high-quality outputs. Extensive qualitative and quantitative experiments on text-to-image and text-to-video generation tasks demonstrate that S^2-Guidance delivers superior performance, consistently surpassing CFG and other advanced guidance strategies. Our code will be released.

☆ Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning

Dexia Chen, Qianjie Zhu, Weibing Li, Yue Yu, Tong Zhang, Ruixuan Wang

Pretrained vision-language models (VLMs), such as CLIP, have shown remarkable potential in few-shot image classification and led to numerous effective transfer learning strategies. These methods leverage the pretrained knowledge of VLMs to enable effective domain adaptation while mitigating overfitting through parameter-efficient tuning or instance-based consistency constraints. However, such regularizations often neglect the geometric structure of data distribution, which may lead to distortion of the overall semantic representation. To overcome this limitation, we propose a novel fine-tuning method, Manifold-Preserving and Sculpting Tuning (MPS-Tuning). Regarding the data distribution in feature space as a semantic manifold, MPS-Tuning explicitly constrains the intrinsic geometry of this manifold while further sculpting it to enhance class separability. Specifically, MPS-Tuning preserves both macroscopic and microscopic topological structures of the original manifold by aligning Gram matrices of features before and after fine-tuning. Theoretically, this constraint is shown to approximate an upper bound of the Gromov-Wasserstein distance. Furthermore, features from the image and text modalities are paired, and pairwise similarities are optimized to enhance the manifold's class discriminability. Extensive experiments demonstrate that MPS-Tuning significantly improves model performance while effectively preserving the structure of the semantic manifold. The code will be released.

☆ Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models

Dexia Chen, Wentao Zhang, Qianjie Zhu, Ping Hu, Weibing Li, Tong Zhang, Ruixuan Wang

Vision-language models (VLMs) pre-trained on natural image and language data, such as CLIP, have exhibited significant potential in few-shot image recognition tasks, leading to development of various efficient transfer learning methods. These methods exploit inherent pre-learned knowledge in VLMs and have achieved strong performance on standard image datasets. However, their effectiveness is often limited when confronted with cross-domain tasks where imaging domains differ from natural images. To address this limitation, we propose Consistency-guided Multi-view Collaborative Optimization (CoMuCo), a novel fine-tuning strategy for VLMs. This strategy employs two functionally complementary expert modules to extract multi-view features, while incorporating prior knowledge-based consistency constraints and information geometry-based consensus mechanisms to enhance the robustness of feature learning. Additionally, a new cross-domain few-shot benchmark is established to help comprehensively evaluate methods on imaging domains distinct from natural images. Extensive empirical evaluations on both existing and newly proposed benchmarks suggest CoMuCo consistently outperforms current methods in few-shot tasks. The code and benchmark will be released.

☆ E3RG: Building Explicit Emotion-driven Empathetic Response Generation System with Multimodal Large Language Model ACM MM 2025

Ronghao Lin, Shuai Shen, Weipeng Hu, Qiaolin He, Aolin Xiong, Li Huang, Haifeng Hu, Yap-peng Tan

Multimodal Empathetic Response Generation (MERG) is crucial for building emotionally intelligent human-computer interactions. Although large language models (LLMs) have improved text-based ERG, challenges remain in handling multimodal emotional content and maintaining identity consistency. Thus, we propose E3RG, an Explicit Emotion-driven Empathetic Response Generation System based on multimodal LLMs which decomposes MERG task into three parts: multimodal empathy understanding, empathy memory retrieval, and multimodal response generation. By integrating advanced expressive speech and video generative models, E3RG delivers natural, emotionally rich, and identity-consistent responses without extra training. Experiments validate the superiority of our system on both zero-shot and few-shot settings, securing Top-1 position in the Avatar-based Multimodal Empathy Challenge on ACM MM 25. Our code is available at https://github.com/RH-Lin/E3RG.

comment: Accepted at ACM MM 2025 Grand Challenge

☆ Multi-source Multimodal Progressive Domain Adaption for Audio-Visual Deception Detection ACM MM 2025

Ronghao Lin, Sijie Mai, Ying Zeng, Qiaolin He, Aolin Xiong, Haifeng Hu

This paper presents the winning approach for the 1st MultiModal Deception Detection (MMDD) Challenge at the 1st Workshop on Subtle Visual Computing (SVC). Aiming at the domain shift issue across source and target domains, we propose a Multi-source Multimodal Progressive Domain Adaptation (MMPDA) framework that transfers the audio-visual knowledge from diverse source domains to the target domain. By gradually aligning source and the target domain at both feature and decision levels, our method bridges domain shifts across diverse multimodal datasets. Extensive experiments demonstrate the effectiveness of our approach securing Top-2 place. Our approach reaches 60.43% on accuracy and 56.99\% on F1-score on competition stage 2, surpassing the 1st place team by 5.59% on F1-score and the 3rd place teams by 6.75% on accuracy. Our code is available at https://github.com/RH-Lin/MMPDA.

comment: Accepted at ACM MM 2025 SVC Workshop

☆ DEEP-SEA: Deep-Learning Enhancement for Environmental Perception in Submerged Aquatics

Shuang Chen, Ronald Thenius, Farshad Arvin, Amir Atapour-Abarghouei

Continuous and reliable underwater monitoring is essential for assessing marine biodiversity, detecting ecological changes and supporting autonomous exploration in aquatic environments. Underwater monitoring platforms rely on mainly visual data for marine biodiversity analysis, ecological assessment and autonomous exploration. However, underwater environments present significant challenges due to light scattering, absorption and turbidity, which degrade image clarity and distort colour information, which makes accurate observation difficult. To address these challenges, we propose DEEP-SEA, a novel deep learning-based underwater image restoration model to enhance both low- and high-frequency information while preserving spatial structures. The proposed Dual-Frequency Enhanced Self-Attention Spatial and Frequency Modulator aims to adaptively refine feature representations in frequency domains and simultaneously spatial information for better structural preservation. Our comprehensive experiments on EUVP and LSUI datasets demonstrate the superiority over the state of the art in restoring fine-grained image detail and structural consistency. By effectively mitigating underwater visual degradation, DEEP-SEA has the potential to improve the reliability of underwater monitoring platforms for more accurate ecological observation, species identification and autonomous navigation.

☆ Learning to Steer: Input-dependent Steering for Multimodal LLMs

Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Arnaud Dapogny, Alasdair Newson, Matthieu Cord

Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such as mean steering, rely on a single steering vector, applied independently of the input query. This paradigm faces limitations when the desired behavior is dependent on the example at hand. For example, a safe answer may consist in abstaining from answering when asked for an illegal activity, or may point to external resources or consultation with an expert when asked about medical advice. In this paper, we investigate a fine-grained steering that uses an input-specific linear shift. This shift is computed using contrastive input-specific prompting. However, the input-specific prompts required for this approach are not known at test time. Therefore, we propose to train a small auxiliary module to predict the input-specific steering vector. Our approach, dubbed as L2S (Learn-to-Steer), demonstrates that it reduces hallucinations and enforces safety in MLLMs, outperforming other static baselines.

☆ SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshop

Friedhelm Hamann, Emil Mededovic, Fabian Gülhan, Yuli Wu, Johannes Stegmaier, Jing He, Yiqing Wang, Kexin Zhang, Lingling Li, Licheng Jiao, Mengru Ma, Hongxiang Huang, Yuhao Yan, Hongwei Ren, Xiaopeng Lin, Yulong Huang, Bojun Cheng, Se Hyun Lee, Gyu Sung Ham, Kanghan Oh, Gi Hyun Lim, Boxuan Yang, Bowen Du, Guillermo Gallego

We present an overview of the Spatio-temporal Instance Segmentation (SIS) challenge held in conjunction with the CVPR 2025 Event-based Vision Workshop. The task is to predict accurate pixel-level segmentation masks of defined object classes from spatio-temporally aligned event camera and grayscale camera data. We provide an overview of the task, dataset, challenge details and results. Furthermore, we describe the methods used by the top-5 ranking teams in the challenge. More resources and code of the participants' methods are available here: https://github.com/tub-rip/MouseSIS/blob/main/docs/challenge_results.md

comment: 13 pages, 7 figures, 7 tables

☆ Next Visual Granularity Generation

Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy

We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different level of visual granularity. Image generation is carried out through our newly introduced Next Visual Granularity (NVG) generation framework, which generates a visual granularity sequence beginning from an empty image and progressively refines it, from global layout to fine details, in a structured manner. This iterative process encodes a hierarchical, layered representation that offers fine-grained control over the generation process across multiple granularity levels. We train a series of NVG models for class-conditional image generation on the ImageNet dataset and observe clear scaling behavior. Compared to the VAR series, NVG consistently outperforms it in terms of FID scores (3.30 -> 3.03, 2.57 ->2.44, 2.09 -> 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models will be released.

☆ Morphological classification of eclipsing binary stars using computer vision methods

Štefan Parimucha, Maksim Gabdeev, Yanna Markus, Martin Vaňko, Pavol Gajdoš

We present an application of computer vision methods to classify the light curves of eclipsing binaries (EB). We have used pre-trained models based on convolutional neural networks ($\textit{ResNet50}$) and vision transformers ($\textit{vit\_base\_patch16\_224}$), which were fine-tuned on images created from synthetic datasets. To improve model generalisation and reduce overfitting, we developed a novel image representation by transforming phase-folded light curves into polar coordinates combined with hexbin visualisation. Our hierarchical approach in the first stage classifies systems into detached and overcontact types, and in the second stage identifies the presence or absence of spots. The binary classification models achieved high accuracy ($>96\%$) on validation data across multiple passbands (Gaia~$G$, $I$, and $TESS$) and demonstrated strong performance ($>94\%$, up to $100\%$ for $TESS$) when tested on extensive observational data from the OGLE, DEBCat, and WUMaCat catalogues. While the primary binary classification was highly successful, the secondary task of automated spot detection performed poorly, revealing a significant limitation of our models for identifying subtle photometric features. This study highlights the potential of computer vision for EB morphological classification in large-scale surveys, but underscores the need for further research into robust, automated spot detection.

comment: 19 pages, 4 figures, 4 tables

☆ A Shift in Perspective on Causality in Domain Generalization

Damian Machlanski, Stephanie Riley, Edward Moroshko, Kurt Butler, Panagiotis Dimitrakopoulos, Thomas Melistas, Akchunya Chanchal, Steven McDonagh, Ricardo Silva, Sotirios A. Tsaftaris

The promise that causal modelling can lead to robust AI generalization has been challenged in recent work on domain generalization (DG) benchmarks. We revisit the claims of the causality and DG literature, reconciling apparent contradictions and advocating for a more nuanced theory of the role of causality in generalization. We also provide an interactive demo at https://chai-uk.github.io/ukairs25-causal-predictors/.

comment: 2 pages, 1 figure, to be presented at the UK AI Research Symposium (UKAIRS) 2025

☆ Vehicle detection from GSV imagery: Predicting travel behaviour for cycling and motorcycling using Computer Vision

Kyriaki, Kokka, Rahul Goel, Ali Abbas, Kerry A. Nice, Luca Martial, SM Labib, Rihuan Ke, Carola Bibiane Schönlieb, James Woodcock

Transportation influence health by shaping exposure to physical activity, air pollution and injury risk.Comparative data on cycling and motorcycling behaviours is scarce, particularly at a global scale.Street view imagery, such as Google Street View (GSV), combined with computer vision, is a valuable resource for efficiently capturing travel behaviour data.This study demonstrates a novel approach using deep learning on street view images to estimate cycling and motorcycling levels across diverse cities worldwide.We utilized data from 185 global cities.The data on mode shares of cycling and motorcycling estimated using travel surveys or censuses.We used GSV images to detect cycles and motorcycles in sampled locations, using 8000 images per city.The YOLOv4 model, fine-tuned using images from six cities, achieved a mean average precision of 89% for detecting cycles and motorcycles in GSV images.A global prediction model was developed using beta regression with city-level mode shares as outcome, with log transformed explanatory variables of counts of GSV-detected images with cycles and motorcycles, while controlling for population density.We found strong correlations between GSV motorcycle counts and motorcycle mode share (0.78) and moderate correlations between GSV cycle counts and cycling mode share (0.51).Beta regression models predicted mode shares with $R^2$ values of 0.614 for cycling and 0.612 for motorcycling, achieving median absolute errors (MDAE) of 1.3% and 1.4%, respectively.Scatterplots demonstrated consistent prediction accuracy, though cities like Utrecht and Cali were outliers.The model was applied to 60 cities globally for which we didn't have recent mode share data.We provided estimates for some cities in the Middle East, Latin America and East Asia.With computer vision, GSV images capture travel modes and activity, providing insights alongside traditional data sources.

☆ Leveraging Diffusion Models for Stylization using Multiple Style Images

Dan Ruta, Abdelaziz Djelouah, Raphael Ortiz, Christopher Schroers

Recent advances in latent diffusion models have enabled exciting progress in image style transfer. However, several key issues remain. For example, existing methods still struggle to accurately match styles. They are often limited in the number of style images that can be used. Furthermore, they tend to entangle content and style in undesired ways. To address this, we propose leveraging multiple style images which helps better represent style features and prevent content leaking from the style images. We design a method that leverages both image prompt adapters and statistical alignment of the features during the denoising process. With this, our approach is designed such that it can intervene both at the cross-attention and the self-attention layers of the denoising UNet. For the statistical alignment, we employ clustering to distill a small representative set of attention features from the large number of attention values extracted from the style samples. As demonstrated in our experimental section, the resulting method achieves state-of-the-art results for stylization.

☆ SocialTrack: Multi-Object Tracking in Complex Urban Traffic Scenes Inspired by Social Behavior

Wenguang Tao, Xiaotian Wang, Tian Yan, Jie Yan, Guodong Li, Kun Bai

As a key research direction in the field of multi-object tracking (MOT), UAV-based multi-object tracking has significant application value in the analysis and understanding of urban intelligent transportation systems. However, in complex UAV perspectives, challenges such as small target scale variations, occlusions, nonlinear crossing motions, and motion blur severely hinder the stability of multi-object tracking. To address these challenges, this paper proposes a novel multi-object tracking framework, SocialTrack, aimed at enhancing the tracking accuracy and robustness of small targets in complex urban traffic environments. The specialized small-target detector enhances the detection performance by employing a multi-scale feature enhancement mechanism. The Velocity Adaptive Cubature Kalman Filter (VACKF) improves the accuracy of trajectory prediction by incorporating a velocity dynamic modeling mechanism. The Group Motion Compensation Strategy (GMCS) models social group motion priors to provide stable state update references for low-quality tracks, significantly improving the target association accuracy in complex dynamic environments. Furthermore, the Spatio-Temporal Memory Prediction (STMP) leverages historical trajectory information to predict the future state of low-quality tracks, effectively mitigating identity switching issues. Extensive experiments on the UAVDT and MOT17 datasets demonstrate that SocialTrack outperforms existing state-of-the-art (SOTA) methods across several key metrics. Significant improvements in MOTA and IDF1, among other core performance indicators, highlight its superior robustness and adaptability. Additionally, SocialTrack is highly modular and compatible, allowing for seamless integration with existing trackers to further enhance performance.

☆ Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductors

Peihao Li, Yan Fang, Man Liu, Huihui Bai, Anhong Wang, Yunchao Wei, Yao Zhao

Labeling Cadmium Zinc Telluride (CdZnTe) semiconductor images is challenging due to the low-contrast defect boundaries, necessitating annotators to cross-reference multiple views. These views share a single ground truth (GT), forming a unique ``many-to-one'' relationship. This characteristic renders advanced semi-supervised semantic segmentation (SSS) methods suboptimal, as they are generally limited by a ``one-to-one'' relationship, where each image is independently associated with its GT. Such limitation may lead to error accumulation in low-contrast regions, further exacerbating confirmation bias. To address this issue, we revisit the SSS pipeline from a group-oriented perspective and propose a human-inspired solution: the Intra-group Consistency Augmentation Framework (ICAF). First, we experimentally validate the inherent consistency constraints within CdZnTe groups, establishing a group-oriented baseline using the Intra-group View Sampling (IVS). Building on this insight, we introduce the Pseudo-label Correction Network (PCN) to enhance consistency representation, which consists of two key modules. The View Augmentation Module (VAM) improves boundary details by dynamically synthesizing a boundary-aware view through the aggregation of multiple views. In the View Correction Module (VCM), this synthesized view is paired with other views for information interaction, effectively emphasizing salient regions while minimizing noise. Extensive experiments demonstrate the effectiveness of our solution for CdZnTe materials. Leveraging DeepLabV3+ with a ResNet-101 backbone as our segmentation model, we achieve a 70.6\% mIoU on the CdZnTe dataset using only 2 group-annotated data (5\textperthousand). The code is available at \href{https://github.com/pipixiapipi/ICAF}{https://github.com/pipixiapipi/ICAF}.

☆ CLAIRE-DSA: Fluoroscopic Image Classification for Quality Assurance of Computer Vision Pipelines in Acute Ischemic Stroke

Cristo J. van den Berg, Frank G. te Nijenhuis, Mirre J. Blaauboer, Daan T. W. van Erp, Carlijn M. Keppels, Matthijs van der Sluijs, Bob Roozenbeek, Wim van Zwam, Sandra Cornelissen, Danny Ruijters, Ruisheng Su, Theo van Walsum

Computer vision models can be used to assist during mechanical thrombectomy (MT) for acute ischemic stroke (AIS), but poor image quality often degrades performance. This work presents CLAIRE-DSA, a deep learning--based framework designed to categorize key image properties in minimum intensity projections (MinIPs) acquired during MT for AIS, supporting downstream quality control and workflow optimization. CLAIRE-DSA uses pre-trained ResNet backbone models, fine-tuned to predict nine image properties (e.g., presence of contrast, projection angle, motion artefact severity). Separate classifiers were trained on an annotated dataset containing $1,758$ fluoroscopic MinIPs. The model achieved excellent performance on all labels, with ROC-AUC ranging from $0.91$ to $0.98$, and precision ranging from $0.70$ to $1.00$. The ability of CLAIRE-DSA to identify suitable images was evaluated on a segmentation task by filtering poor quality images and comparing segmentation performance on filtered and unfiltered datasets. Segmentation success rate increased from $42%$ to $69%$, $p < 0.001$. CLAIRE-DSA demonstrates strong potential as an automated tool for accurately classifying image properties in DSA series of acute ischemic stroke patients, supporting image annotation and quality control in clinical and research applications. Source code is available at https://gitlab.com/icai-stroke-lab/wp3_neurointerventional_ai/claire-dsa.

comment: 10 pages, 4 figures, workshop paper accepted at https://switchmiccai.github.io/switch/

☆ D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal

Linhao Li, Boya Jin, Zizhe Li, Lanqing Guo, Hao Cheng, Bo Li, Yongfeng Dong

Shadow removal aims to restore images that are partially degraded by shadows, where the degradation is spatially localized and non-uniform. Unlike general restoration tasks that assume global degradation, shadow removal can leverage abundant information from non-shadow regions for guidance. However, the transformation required to correct shadowed areas often differs significantly from that of well-lit regions, making it challenging to apply uniform correction strategies. This necessitates the effective integration of non-local contextual cues and adaptive modeling of region-specific transformations. To this end, we propose a novel Mamba-based network featuring dual-scale fusion and dual-path scanning to selectively propagate contextual information based on transformation similarity across regions. Specifically, the proposed Dual-Scale Fusion Mamba Block (DFMB) enhances multi-scale feature representation by fusing original features with low-resolution features, effectively reducing boundary artifacts. The Dual-Path Mamba Group (DPMG) captures global features via horizontal scanning and incorporates a mask-aware adaptive scanning strategy, which improves structural continuity and fine-grained region modeling. Experimental results demonstrate that our method significantly outperforms existing state-of-the-art approaches on shadow removal benchmarks.

comment: Paper Under Review

☆ DCSCR: A Class-Specific Collaborative Representation based Network for Image Set Classification

Xizhan Gao, Wei Hu

Image set classification (ISC), which can be viewed as a task of comparing similarities between sets consisting of unordered heterogeneous images with variable quantities and qualities, has attracted growing research attention in recent years. How to learn effective feature representations and how to explore the similarities between different image sets are two key yet challenging issues in this field. However, existing traditional ISC methods classify image sets based on raw pixel features, ignoring the importance of feature learning. Existing deep ISC methods can learn deep features, but they fail to adaptively adjust the features when measuring set distances, resulting in limited performance in few-shot ISC. To address the above issues, this paper combines traditional ISC methods with deep models and proposes a novel few-shot ISC approach called Deep Class-specific Collaborative Representation (DCSCR) network to simultaneously learn the frame- and concept-level feature representations of each image set and the distance similarities between different sets. Specifically, DCSCR consists of a fully convolutional deep feature extractor module, a global feature learning module, and a class-specific collaborative representation-based metric learning module. The deep feature extractor and global feature learning modules are used to learn (local and global) frame-level feature representations, while the class-specific collaborative representation-based metric learning module is exploit to adaptively learn the concept-level feature representation of each image set and thus obtain the distance similarities between different sets by developing a new CSCR-based contrastive loss function. Extensive experiments on several well-known few-shot ISC datasets demonstrate the effectiveness of the proposed method compared with some state-of-the-art image set classification algorithms.

☆ On the Importance of Behavioral Nuances: Amplifying Non-Obvious Motor Noise Under True Empirical Considerations May Lead to Briefer Assays and Faster Classification Processes

Theodoros Bermperidis, Joe Vero, Elizabeth B Torres

There is a tradeoff between attaining statistical power with large, difficult to gather data sets, and producing highly scalable assays that register brief data samples. Often, as grand-averaging techniques a priori assume normally-distributed parameters and linear, stationary processes in biorhythmic, time series data, important information is lost, averaged out as gross data. We developed an affective computing platform that enables taking brief data samples while maintaining personalized statistical power. This is achieved by combining a new data type derived from the micropeaks present in time series data registered from brief (5-second-long) face videos with recent advances in AI-driven face-grid estimation methods. By adopting geometric and nonlinear dynamical systems approaches to analyze the kinematics, especially the speed data, the new methods capture all facial micropeaks. These include as well the nuances of different affective micro expressions. We offer new ways to differentiate dynamical and geometric patterns present in autistic individuals from those found more commonly in neurotypical development.

comment: This paper is under review in IEEE Transactions on Affective Computing

☆ Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring

Ying Zhang, Xiongxin Tang, Chongyi Li, Qiao Chen, Yuquan Wu

Single image defocus deblurring aims to recover an all-in-focus image from a defocus counterpart, where accurately modeling spatially varying blur kernels remains a key challenge. Most existing methods rely on spatial features for kernel estimation, but their performance degrades in severely blurry regions where local high-frequency details are missing. To address this, we propose a Frequency-Driven Inverse Kernel Prediction network (FDIKP) that incorporates frequency-domain representations to enhance structural identifiability in kernel modeling. Given the superior discriminative capability of the frequency domain for blur modeling, we design a Dual-Branch Inverse Kernel Prediction (DIKP) strategy that improves the accuracy of kernel estimation while maintaining stability. Moreover, considering the limited number of predicted inverse kernels, we introduce a Position Adaptive Convolution (PAC) to enhance the adaptability of the deconvolution process. Finally, we propose a Dual-Domain Scale Recurrent Module (DSRM) to fuse deconvolution results and progressively improve deblurring quality from coarse to fine. Extensive experiments demonstrate that our method outperforms existing approaches. Code will be made publicly available.

☆ Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting

Kangjie Chen, Yingji Zhong, Zhihao Li, Jiaqi Lin, Youyu Chen, Minghan Qin, Haoqian Wang

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in novel view synthesis under dense-view settings. However, in sparse-view scenarios, despite the realistic renderings in training views, 3DGS occasionally manifests appearance artifacts in novel views. This paper investigates the appearance artifacts in sparse-view 3DGS and uncovers a core limitation of current approaches: the optimized Gaussians are overly-entangled with one another to aggressively fit the training views, which leads to a neglect of the real appearance distribution of the underlying scene and results in appearance artifacts in novel views. The analysis is based on a proposed metric, termed Co-Adaptation Score (CA), which quantifies the entanglement among Gaussians, i.e., co-adaptation, by computing the pixel-wise variance across multiple renderings of the same viewpoint, with different random subsets of Gaussians. The analysis reveals that the degree of co-adaptation is naturally alleviated as the number of training views increases. Based on the analysis, we propose two lightweight strategies to explicitly mitigate the co-adaptation in sparse-view 3DGS: (1) random gaussian dropout; (2) multiplicative noise injection to the opacity. Both strategies are designed to be plug-and-play, and their effectiveness is validated across various methods and benchmarks. We hope that our insights into the co-adaptation effect will inspire the community to achieve a more comprehensive understanding of sparse-view 3DGS.

comment: Under review. Project page: https://chenkangjie1123.github.io/Co-Adaptation-3DGS/

☆ Single-Reference Text-to-Image Manipulation with Dual Contrastive Denoising Score

Syed Muhmmad Israr, Feng Zhao

Large-scale text-to-image generative models have shown remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is difficult for users to come up with a perfect text prompt that accurately describes every visual detail in the input image. Second, while existing models can introduce desirable changes in certain regions, they often dramatically alter the input content and introduce unexpected changes in unwanted regions. To address these challenges, we present Dual Contrastive Denoising Score, a simple yet powerful framework that leverages the rich generative prior of text-to-image diffusion models. Inspired by contrastive learning approaches for unpaired image-to-image translation, we introduce a straightforward dual contrastive loss within the proposed framework. Our approach utilizes the extensive spatial information from the intermediate representations of the self-attention layers in latent diffusion models without depending on auxiliary networks. Our method achieves both flexible content modification and structure preservation between input and output images, as well as zero-shot image-to-image translation. Through extensive experiments, we show that our approach outperforms existing methods in real image editing while maintaining the capability to directly utilize pretrained text-to-image diffusion models without further training.

☆ Real-Time Sign Language Gestures to Speech Transcription using Deep Learning

Brandone Fonya

Communication barriers pose significant challenges for individuals with hearing and speech impairments, often limiting their ability to effectively interact in everyday environments. This project introduces a real-time assistive technology solution that leverages advanced deep learning techniques to translate sign language gestures into textual and audible speech. By employing convolution neural networks (CNN) trained on the Sign Language MNIST dataset, the system accurately classifies hand gestures captured live via webcam. Detected gestures are instantaneously translated into their corresponding meanings and transcribed into spoken language using text-to-speech synthesis, thus facilitating seamless communication. Comprehensive experiments demonstrate high model accuracy and robust real-time performance with some latency, highlighting the system's practical applicability as an accessible, reliable, and user-friendly tool for enhancing the autonomy and integration of sign language users in diverse social settings.

comment: Course related research project

☆ Argos: A Decentralized Federated System for Detection of Traffic Signs in CAVs

Seyed Mahdi Haji Seyed Hossein, Alireza Hosseini, Soheil Hajian Manesh, Amirali Shahriary

Connected and automated vehicles generate vast amounts of sensor data daily, raising significant privacy and communication challenges for centralized machine learning approaches in perception tasks. This study presents a decentralized, federated learning framework tailored for traffic sign detection in vehicular networks to enable collaborative model training without sharing raw data. The framework partitioned traffic sign classes across vehicles for specialized local training using lightweight object detectors, aggregated model parameters via algorithms like FedProx, FedAdam and FedAVG in a simulated environment with the Flower framework, and evaluated multiple configurations including varying server rounds, local epochs, client participation fractions, and data distributions. Experiments demonstrated that increasing server rounds from 2 to 20 boosted accuracy from below 0.1 to over 0.8, moderate local epochs (8-10) provided optimal efficiency with accuracies around 0.67, higher client participation fractions enhanced generalization up to 0.83, FedProx outperformed other aggregators in handling heterogeneity, non-IID data distributions reduced performance compared to IID, and training duration primarily scaled with the number of rounds rather than aggregation strategy. We conclude that this federated approach may offer a scalable, privacy-preserving solution for real-world vehicular deployments, potentially guiding future integrations of robust aggregation and communication optimizations to advance intelligent transportation systems.

comment: 7 pages, 10 figures

☆ Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection

Fanxiao Li, Jiaying Wu, Tingchao Fu, Yunyun Dong, Bingbing Song, Wei Zhou

The proliferation of multimodal misinformation poses growing threats to public discourse and societal trust. While Large Vision-Language Models (LVLMs) have enabled recent progress in multimodal misinformation detection (MMD), the rise of generative AI (GenAI) tools introduces a new challenge: GenAI-driven news diversity, characterized by highly varied and complex content. We show that this diversity induces multi-level drift, comprising (1) model-level misperception drift, where stylistic variations disrupt a model's internal reasoning, and (2) evidence-level drift, where expression diversity degrades the quality or relevance of retrieved external evidence. These drifts significantly degrade the robustness of current LVLM-based MMD systems. To systematically study this problem, we introduce DriftBench, a large-scale benchmark comprising 16,000 news instances across six categories of diversification. We design three evaluation tasks: (1) robustness of truth verification under multi-level drift; (2) susceptibility to adversarial evidence contamination generated by GenAI; and (3) analysis of reasoning consistency across diverse inputs. Experiments with six state-of-the-art LVLM-based detectors show substantial performance drops (average F1 -14.8%) and increasingly unstable reasoning traces, with even more severe failures under adversarial evidence injection. Our findings uncover fundamental vulnerabilities in existing MMD systems and suggest an urgent need for more resilient approaches in the GenAI era.

☆ Neural Rendering for Sensor Adaptation in 3D Object Detection

Felix Embacher, David Holtz, Jonas Uhrig, Marius Cordts, Markus Enzweiler

Autonomous vehicles often have varying camera sensor setups, which is inevitable due to restricted placement options for different vehicle types. Training a perception model on one particular setup and evaluating it on a new, different sensor setup reveals the so-called cross-sensor domain gap, typically leading to a degradation in accuracy. In this paper, we investigate the impact of the cross-sensor domain gap on state-of-the-art 3D object detectors. To this end, we introduce CamShift, a dataset inspired by nuScenes and created in CARLA to specifically simulate the domain gap between subcompact vehicles and sport utility vehicles (SUVs). Using CamShift, we demonstrate significant cross-sensor performance degradation, identify robustness dependencies on model architecture, and propose a data-driven solution to mitigate the effect. On the one hand, we show that model architectures based on a dense Bird's Eye View (BEV) representation with backward projection, such as BEVFormer, are the most robust against varying sensor configurations. On the other hand, we propose a novel data-driven sensor adaptation pipeline based on neural rendering, which can transform entire datasets to match different camera sensor setups. Applying this approach improves performance across all investigated 3D object detectors, mitigating the cross-sensor domain gap by a large margin and reducing the need for new data collection by enabling efficient data reusability across vehicles with different sensor setups. The CamShift dataset and the sensor adaptation benchmark are available at https://dmholtz.github.io/camshift/.

comment: Accepted at IEEE Intelligent Vehicles Symposium (IV) 2025

☆ Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning

Taeheon Kim, San Kim, Minhyuk Seo, Dongjae Jeon, Wonje Jeong, Jonghyun Choi

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen classes. CIR assumes that we can easily access abundant unlabeled data from external sources, such as the Internet. Therefore, we propose two components that efficiently use the unlabeled data to ensure the high stability and the plasticity of models trained in CIR setup. First, we introduce multi-level knowledge distillation (MLKD) that distills knowledge from multiple previous models across multiple perspectives, including features and logits, so the model can maintain much various previous knowledge. Moreover, we implement dynamic self-supervised loss (SSL) to utilize the unlabeled data that accelerates the learning of new classes, while dynamic weighting of SSL keeps the focus of training to the primary task. Both of our proposed components significantly improve the performance in CIR setup, achieving 2nd place in the CVPR 5th CLVISION Challenge.

☆ MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration

Yuanxin Wei, Lansong Diao, Bujiao Chen, Shenggan Cheng, Zhengping Qian, Wenyuan Yu, Nong Xiao, Wei Lin, Jiangsu Du

Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality video generation. However, their multi-step iterative denoising process incurs high computational cost and inference latency. Caching, a widely adopted optimization method in DiT models, leverages the redundancy in the diffusion process to skip computations in different granularities (e.g., step, cfg, block). Nevertheless, existing caching methods are limited to single-granularity strategies, struggling to balance generation quality and inference speed in a flexible manner. In this work, we propose MixCache, a training-free caching-based framework for efficient video DiT inference. It first distinguishes the interference and boundary between different caching strategies, and then introduces a context-aware cache triggering strategy to determine when caching should be enabled, along with an adaptive hybrid cache decision strategy for dynamically selecting the optimal caching granularity. Extensive experiments on diverse models demonstrate that, MixCache can significantly accelerate video generation (e.g., 1.94$\times$ speedup on Wan 14B, 1.97$\times$ speedup on HunyuanVideo) while delivering both superior generation quality and inference efficiency compared to baseline methods.

comment: 7 pages, 10 figures

☆ TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions

Dongjae Jeon, Taeheon Kim, Seongwon Cho, Minhyuk Seo, Jonghyun Choi

Test-time Adaptation (TTA) poses a challenge, requiring models to dynamically adapt and perform optimally on shifting target domains. This task is particularly emphasized in real-world driving scenes, where weather domain shifts occur frequently. To address such dynamic changes, our proposed method, TTA-DAME, leverages source domain data augmentation into target domains. Additionally, we introduce a domain discriminator and a specialized domain detector to mitigate drastic domain shifts, especially from daytime to nighttime conditions. To further improve adaptability, we train multiple detectors and consolidate their predictions through Non-Maximum Suppression (NMS). Our empirical validation demonstrates the effectiveness of our method, showing significant performance enhancements on the SHIFT Benchmark.

☆ EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding

Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar, Nishit Anand, Sonal Kumar, Sreyan Ghosh, Ramani Duraiswami, Chirag Agarwal, Dinesh Manocha

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in complex multimodal tasks. While MLLMs excel at visual perception and reasoning in third-person and egocentric videos, they are prone to hallucinations, generating coherent yet inaccurate responses. We present EgoIllusion, a first benchmark to evaluate MLLM hallucinations in egocentric videos. EgoIllusion comprises 1,400 videos paired with 8,000 human-annotated open and closed-ended questions designed to trigger hallucinations in both visual and auditory cues in egocentric videos. Evaluations across ten MLLMs reveal significant challenges, including powerful models like GPT-4o and Gemini, achieving only 59% accuracy. EgoIllusion lays the foundation in developing robust benchmarks to evaluate the effectiveness of MLLMs and spurs the development of better egocentric MLLMs with reduced hallucination rates. Our benchmark will be open-sourced for reproducibility.

☆ Refine-and-Contrast: Adaptive Instance-Aware BEV Representations for Multi-UAV Collaborative Object Detection

Zhongyao Li, Peirui Cheng, Liangjin Zhao, Chen Chen, Yundu Li, Zhechao Wang, Xue Yang, Xian Sun, Zhirui Wang

Multi-UAV collaborative 3D detection enables accurate and robust perception by fusing multi-view observations from aerial platforms, offering significant advantages in coverage and occlusion handling, while posing new challenges for computation on resource-constrained UAV platforms. In this paper, we present AdaBEV, a novel framework that learns adaptive instance-aware BEV representations through a refine-and-contrast paradigm. Unlike existing methods that treat all BEV grids equally, AdaBEV introduces a Box-Guided Refinement Module (BG-RM) and an Instance-Background Contrastive Learning (IBCL) to enhance semantic awareness and feature discriminability. BG-RM refines only BEV grids associated with foreground instances using 2D supervision and spatial subdivision, while IBCL promotes stronger separation between foreground and background features via contrastive learning in BEV space. Extensive experiments on the Air-Co-Pred dataset demonstrate that AdaBEV achieves superior accuracy-computation trade-offs across model scales, outperforming other state-of-the-art methods at low resolutions and approaching upper bound performance while maintaining low-resolution BEV inputs and negligible overhead.

comment: 9 pages

☆ Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation

Yuheng Zha, Kun Zhou, Yujia Wu, Yushu Wang, Jie Feng, Zhi Xu, Shibo Hao, Zhengzhong Liu, Eric P. Xing, Zhiting Hu

Despite their success, current training pipelines for reasoning VLMs focus on a limited range of tasks, such as mathematical and logical reasoning. As a result, these models face difficulties in generalizing their reasoning capabilities to a wide range of domains, primarily due to the scarcity of readily available and verifiable reward data beyond these narrowly defined areas. Moreover, integrating data from multiple domains is challenging, as the compatibility between domain-specific datasets remains uncertain. To address these limitations, we build a comprehensive RL-ready visual reasoning dataset from 46 data sources across 8 dimensions, covering a wide range of tasks such as infographic, mathematical, spatial, cross-image, graphic user interface, medical, common sense and general science. We propose an influence function based data selection and difficulty based filtering strategy to identify high-quality training samples from this dataset. Subsequently, we train the VLM, referred to as Vision-G1, using multi-round RL with a data curriculum to iteratively improve its visual reasoning capabilities. Our model achieves state-of-the-art performance across various visual reasoning benchmarks, outperforming similar-sized VLMs and even proprietary models like GPT-4o and Gemini-1.5 Flash. The model, code and dataset are publicly available at https://github.com/yuh-zha/Vision-G1.

☆ WP-CLIP: Leveraging CLIP to Predict Wölfflin's Principles in Visual Art

Abhijay Ghildyal, Li-Yun Wang, Feng Liu

W\"olfflin's five principles offer a structured approach to analyzing stylistic variations for formal analysis. However, no existing metric effectively predicts all five principles in visual art. Computationally evaluating the visual aspects of a painting requires a metric that can interpret key elements such as color, composition, and thematic choices. Recent advancements in vision-language models (VLMs) have demonstrated their ability to evaluate abstract image attributes, making them promising candidates for this task. In this work, we investigate whether CLIP, pre-trained on large-scale data, can understand and predict W\"olfflin's principles. Our findings indicate that it does not inherently capture such nuanced stylistic elements. To address this, we fine-tune CLIP on annotated datasets of real art images to predict a score for each principle. We evaluate our model, WP-CLIP, on GAN-generated paintings and the Pandora-18K art dataset, demonstrating its ability to generalize across diverse artistic styles. Our results highlight the potential of VLMs for automated art analysis.

comment: ICCV 2025 AI4VA workshop (oral), Code: https://github.com/abhijay9/wpclip

☆ Stable Diffusion-Based Approach for Human De-Occlusion

Seung Young Noh, Ju Yong Chang

Humans can infer the missing parts of an occluded object by leveraging prior knowledge and visible cues. However, enabling deep learning models to accurately predict such occluded regions remains a challenging task. De-occlusion addresses this problem by reconstructing both the mask and RGB appearance. In this work, we focus on human de-occlusion, specifically targeting the recovery of occluded body structures and appearances. Our approach decomposes the task into two stages: mask completion and RGB completion. The first stage leverages a diffusion-based human body prior to provide a comprehensive representation of body structure, combined with occluded joint heatmaps that offer explicit spatial cues about missing regions. The reconstructed amodal mask then serves as a conditioning input for the second stage, guiding the model on which areas require RGB reconstruction. To further enhance RGB generation, we incorporate human-specific textual features derived using a visual question answering (VQA) model and encoded via a CLIP encoder. RGB completion is performed using Stable Diffusion, with decoder fine-tuning applied to mitigate pixel-level degradation in visible regions -- a known limitation of prior diffusion-based de-occlusion methods caused by latent space transformations. Our method effectively reconstructs human appearances even under severe occlusions and consistently outperforms existing methods in both mask and RGB completion. Moreover, the de-occluded images generated by our approach can improve the performance of downstream human-centric tasks, such as 2D pose estimation and 3D human reconstruction. The code will be made publicly available.

comment: MM 2025

☆ DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video

Hao Wen, Hongbo Kang, Jian Ma, Jing Huang, Yuanwang Yang, Haozhe Lin, Yu-Kun Lai, Kun Li

3D reconstruction of dynamic crowds in large scenes has become increasingly important for applications such as city surveillance and crowd analysis. However, current works attempt to reconstruct 3D crowds from a static image, causing a lack of temporal consistency and inability to alleviate the typical impact caused by occlusions. In this paper, we propose DyCrowd, the first framework for spatio-temporally consistent 3D reconstruction of hundreds of individuals' poses, positions and shapes from a large-scene video. We design a coarse-to-fine group-guided motion optimization strategy for occlusion-robust crowd reconstruction in large scenes. To address temporal instability and severe occlusions, we further incorporate a VAE (Variational Autoencoder)-based human motion prior along with a segment-level group-guided optimization. The core of our strategy leverages collective crowd behavior to address long-term dynamic occlusions. By jointly optimizing the motion sequences of individuals with similar motion segments and combining this with the proposed Asynchronous Motion Consistency (AMC) loss, we enable high-quality unoccluded motion segments to guide the motion recovery of occluded ones, ensuring robust and plausible motion recovery even in the presence of temporal desynchronization and rhythmic inconsistencies. Additionally, in order to fill the gap of no existing well-annotated large-scene video dataset, we contribute a virtual benchmark dataset, VirtualCrowd, for evaluating dynamic crowd reconstruction from large-scene videos. Experimental results demonstrate that the proposed method achieves state-of-the-art performance in the large-scene dynamic crowd reconstruction task. The code and dataset will be available for research purposes.

☆ Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation

Pinci Yang, Peisong Wen, Ke Ma, Qianqian Xu

Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference. As a fundamental principle, an ideal CTTA method should rapidly adapt to new domains (exploration) while retaining and exploiting knowledge from previously encountered domains to handle similar domains in the future. Despite significant advances, balancing exploration and exploitation in CTTA is still challenging: 1) Existing methods focus on adjusting predictions based on deep-layer outputs of neural networks. However, domain shifts typically affect shallow features, which are inefficient to be adjusted from deep predictions, leading to dilatory exploration; 2) A single model inevitably forgets knowledge of previous domains during the exploration, making it incapable of exploiting historical knowledge to handle similar future domains. To address these challenges, this paper proposes a mean teacher framework that strikes an appropriate Balance between Exploration and Exploitation (BEE) during the CTTA process. For the former challenge, we introduce a Multi-level Consistency Regularization (MCR) loss that aligns the intermediate features of the student and teacher models, accelerating adaptation to the current domain. For the latter challenge, we employ a Complementary Anchor Replay (CAR) mechanism to reuse historical checkpoints (anchors), recovering complementary knowledge for diverse domains. Experiments show that our method significantly outperforms state-of-the-art methods on several benchmarks, demonstrating its effectiveness for CTTA tasks.

☆ Synthesizing Accurate and Realistic T1-weighted Contrast-Enhanced MR Images using Posterior-Mean Rectified Flow

Bastian Brandstötter, Erich Kobler

Contrast-enhanced (CE) T1-weighted MRI is central to neuro-oncologic diagnosis but requires gadolinium-based agents, which add cost and scan time, raise environmental concerns, and may pose risks to patients. In this work, we propose a two-stage Posterior-Mean Rectified Flow (PMRF) pipeline for synthesizing volumetric CE brain MRI from non-contrast inputs. First, a patch-based 3D U-Net predicts the voxel-wise posterior mean (minimizing MSE). Then, this initial estimate is refined by a time-conditioned 3D rectified flow to incorporate realistic textures without compromising structural fidelity. We train this model on a multi-institutional collection of paired pre- and post-contrast T1w volumes (BraTS 2023-2025). On a held-out test set of 360 diverse volumes, our best refined outputs achieve an axial FID of $12.46$ and KID of $0.007$ ($\sim 68.7\%$ lower FID than the posterior mean) while maintaining low volumetric MSE of $0.057$ ($\sim 27\%$ higher than the posterior mean). Qualitative comparisons confirm that our method restores lesion margins and vascular details realistically, effectively navigating the perception-distortion trade-off for clinical deployment.

comment: 12 pages, 3 figures, MICCAI workshops (SASHIMI) 2025

☆ SpotVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer

Chen Qian, Xinran Yu, Zewen Huang, Danyang Li, Qiang Ma, Fan Dang, Xuan Ding, Guangyong Shang, Zheng Yang

Vision-Language Models (VLMs) are increasingly deployed in real-time applications such as autonomous driving and human-computer interaction, which demand fast and reliable responses based on accurate perception. To meet these requirements, existing systems commonly employ cloud-edge collaborative architectures, such as partitioned Large Vision-Language Models (LVLMs) or task offloading strategies between Large and Small Vision-Language Models (SVLMs). However, these methods fail to accommodate cloud latency fluctuations and overlook the full potential of delayed but accurate LVLM responses. In this work, we propose a novel cloud-edge collaborative paradigm for VLMs, termed Context Transfer, which treats the delayed outputs of LVLMs as historical context to provide real-time guidance for SVLMs inference. Based on this paradigm, we design SpotVLM, which incorporates both context replacement and visual focus modules to refine historical textual input and enhance visual grounding consistency. Extensive experiments on three real-time vision tasks across four datasets demonstrate the effectiveness of the proposed framework. The new paradigm lays the groundwork for more effective and latency-aware collaboration strategies in future VLM systems.

☆ HOMI: Ultra-Fast EdgeAI platform for Event Cameras

Shankaranarayanan H, Satyapreet Singh Yadav, Adithya Krishna, Ajay Vikram P, Mahesh Mehendale, Chetan Singh Thakur

Event cameras offer significant advantages for edge robotics applications due to their asynchronous operation and sparse, event-driven output, making them well-suited for tasks requiring fast and efficient closed-loop control, such as gesture-based human-robot interaction. Despite this potential, existing event processing solutions remain limited, often lacking complete end-to-end implementations, exhibiting high latency, and insufficiently exploiting event data sparsity. In this paper, we present HOMI, an ultra-low latency, end-to-end edge AI platform comprising a Prophesee IMX636 event sensor chip with an Xilinx Zynq UltraScale+MPSoC FPGA chip, deploying an in-house developed AI accelerator. We have developed hardware-optimized pre-processing pipelines supporting both constant-time and constant-event modes for histogram accumulation, linear and exponential time surfaces. Our general-purpose implementation caters to both accuracy-driven and low-latency applications. HOMI achieves 94% accuracy on the DVS Gesture dataset as a use case when configured for high accuracy operation and provides a throughput of 1000 fps for low-latency configuration. The hardware-optimised pipeline maintains a compact memory footprint and utilises only 33% of the available LUT resources on the FPGA, leaving ample headroom for further latency reduction, model parallelisation, multi-task deployments, or integration of more complex architectures.

☆ Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning

Yukang Lin, Xiang Zhang, Shichang Jia, Bowen Wan, Chenghan Fu, Xudong Ren, Yueran Liu, Wanxian Guan, Pengji Wang, Jian Xu, Bo Zheng, Baolin Liu

Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection. In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications.

☆ WIPES: Wavelet-based Visual Primitives

Wenhao Zhang, Hao Zhu, Delong Wu, Di Kang, Linchao Bao, Zhan Ma, Xun Cao

comment: IEEE/CVF International Conference on Computer Vision

☆ OpenMoCap: Rethinking Optical Motion Capture under Real-world Occlusion

Chen Qian, Danyang Li, Xinran Yu, Zheng Yang, Qiang Ma

Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in real-world applications. An in-depth analysis identifies two primary limitations of current models: (i) the lack of training datasets accurately reflecting realistic marker occlusion patterns, and (ii) the absence of training strategies designed to capture long-range dependencies among markers. To tackle these challenges, we introduce the CMU-Occlu dataset, which incorporates ray tracing techniques to realistically simulate practical marker occlusion patterns. Furthermore, we propose OpenMoCap, a novel motion-solving model designed specifically for robust motion capture in environments with significant occlusions. Leveraging a marker-joint chain inference mechanism, OpenMoCap enables simultaneous optimization and construction of deep constraints between markers and joints. Extensive comparative experiments demonstrate that OpenMoCap consistently outperforms competing methods across diverse scenarios, while the CMU-Occlu dataset opens the door for future studies in robust motion solving. The proposed OpenMoCap is integrated into the MoSen MoCap system for practical deployment. The code is released at: https://github.com/qianchen214/OpenMoCap.

☆ ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images

Wenjie Liao, Jieyu Yuan, Yifang Xu, Chunle Guo, Zilong Zhang, Jihong Li, Jiachen Fu, Haotian Fan, Tao Li, Junhui Cui, Chongyi Li

Recent advances in Multimodal Large Language Models (MLLMs) have introduced a paradigm shift for Image Quality Assessment (IQA) from unexplainable image quality scoring to explainable IQA, demonstrating practical applications like quality control and optimization guidance. However, current explainable IQA methods not only inadequately use the same distortion criteria to evaluate both User-Generated Content (UGC) and AI-Generated Content (AIGC) images, but also lack detailed quality analysis for monitoring image quality and guiding image restoration. In this study, we establish the first large-scale Visual Distortion Assessment Instruction Tuning Dataset for UGC images, termed ViDA-UGC, which comprises 11K images with fine-grained quality grounding, detailed quality perception, and reasoning quality description data. This dataset is constructed through a distortion-oriented pipeline, which involves human subject annotation and a Chain-of-Thought (CoT) assessment framework. This framework guides GPT-4o to generate quality descriptions by identifying and analyzing UGC distortions, which helps capturing rich low-level visual features that inherently correlate with distortion patterns. Moreover, we carefully select 476 images with corresponding 6,149 question answer pairs from ViDA-UGC and invite a professional team to ensure the accuracy and quality of GPT-generated information. The selected and revised data further contribute to the first UGC distortion assessment benchmark, termed ViDA-UGC-Bench. Experimental results demonstrate the effectiveness of the ViDA-UGC and CoT framework for consistently enhancing various image quality analysis abilities across multiple base MLLMs on ViDA-UGC-Bench and Q-Bench, even surpassing GPT-4o.

☆ ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous Driving

Can Cui, Yupeng Zhou, Juntong Peng, Sung-Yeon Park, Zichong Yang, Prashanth Sankaranarayanan, Jiaru Zhang, Ruqi Zhang, Ziran Wang

End-to-end autonomous driving systems built on Vision Language Models (VLMs) have shown significant promise, yet their reliance on autoregressive architectures introduces some limitations for real-world applications. The sequential, token-by-token generation process of these models results in high inference latency and cannot perform bidirectional reasoning, making them unsuitable for dynamic, safety-critical environments. To overcome these challenges, we introduce ViLaD, a novel Large Vision Language Diffusion (LVLD) framework for end-to-end autonomous driving that represents a paradigm shift. ViLaD leverages a masked diffusion model that enables parallel generation of entire driving decision sequences, significantly reducing computational latency. Moreover, its architecture supports bidirectional reasoning, allowing the model to consider both past and future simultaneously, and supports progressive easy-first generation to iteratively improve decision quality. We conduct comprehensive experiments on the nuScenes dataset, where ViLaD outperforms state-of-the-art autoregressive VLM baselines in both planning accuracy and inference speed, while achieving a near-zero failure rate. Furthermore, we demonstrate the framework's practical viability through a real-world deployment on an autonomous vehicle for an interactive parking task, confirming its effectiveness and soundness for practical applications.

☆ Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models

Tan-Hanh Pham, Chris Ngo

Many reasoning techniques for large multimodal models adapt language model approaches, such as Chain-of-Thought (CoT) prompting, which express reasoning as word sequences. While effective for text, these methods are suboptimal for multimodal contexts, struggling to align audio, visual, and textual information dynamically. To explore an alternative paradigm, we propose the Multimodal Chain of Continuous Thought (MCOUT), which enables reasoning directly in a joint latent space rather than in natural language. In MCOUT, the reasoning state is represented as a continuous hidden vector, iteratively refined and aligned with visual and textual embeddings, inspired by human reflective cognition. We develop two variants: MCOUT-Base, which reuses the language model`s last hidden state as the continuous thought for iterative reasoning, and MCOUT-Multi, which integrates multimodal latent attention to strengthen cross-modal alignment between visual and textual features. Experiments on benchmarks including MMMU, ScienceQA, and MMStar show that MCOUT consistently improves multimodal reasoning, yielding up to 8.23% accuracy gains over strong baselines and improving BLEU scores up to 8.27% across multiple-choice and open-ended tasks. These findings highlight latent continuous reasoning as a promising direction for advancing LMMs beyond language-bound CoT, offering a scalable framework for human-like reflective multimodal inference. Code is available at https://github.com/Hanhpt23/OmniMod.

☆ Foundation Model for Skeleton-Based Human Action Understanding

Hongsong Wang, Wanjiang Weng, Junbo Wang, Fang Zhao, Guo-Sen Xie, Xin Geng, Liang Wang

Human action understanding serves as a foundational pillar in the field of intelligent motion perception. Skeletons serve as a modality- and device-agnostic representation for human modeling, and skeleton-based action understanding has potential applications in humanoid robot control and interaction. \RED{However, existing works often lack the scalability and generalization required to handle diverse action understanding tasks. There is no skeleton foundation model that can be adapted to a wide range of action understanding tasks}. This paper presents a Unified Skeleton-based Dense Representation Learning (USDRL) framework, which serves as a foundational model for skeleton-based human action understanding. USDRL consists of a Transformer-based Dense Spatio-Temporal Encoder (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT). The DSTE module adopts two parallel streams to learn temporal dynamic and spatial structure features. The MG-FD module collaboratively performs feature decorrelation across temporal, spatial, and instance domains to reduce dimensional redundancy and enhance information extraction. The MPCT module employs both multi-view and multi-modal self-supervised consistency training. The former enhances the learning of high-level semantics and mitigates the impact of low-level discrepancies, while the latter effectively facilitates the learning of informative multimodal features. We perform extensive experiments on 25 benchmarks across across 9 skeleton-based action understanding tasks, covering coarse prediction, dense prediction, and transferred prediction. Our approach significantly outperforms the current state-of-the-art methods. We hope that this work would broaden the scope of research in skeleton-based action understanding and encourage more attention to dense prediction tasks.

comment: Accepted by TPAMI, Code is available at: https://github.com/wengwanjiang/FoundSkelModel

☆ Structure-preserving Feature Alignment for Old Photo Colorization

Yingxue Pang, Xin Jin, Jun Fu, Zhibo Chen

Deep learning techniques have made significant advancements in reference-based colorization by training on large-scale datasets. However, directly applying these methods to the task of colorizing old photos is challenging due to the lack of ground truth and the notorious domain gap between natural gray images and old photos. To address this issue, we propose a novel CNN-based algorithm called SFAC, i.e., Structure-preserving Feature Alignment Colorizer. SFAC is trained on only two images for old photo colorization, eliminating the reliance on big data and allowing direct processing of the old photo itself to overcome the domain gap problem. Our primary objective is to establish semantic correspondence between the two images, ensuring that semantically related objects have similar colors. We achieve this through a feature distribution alignment loss that remains robust to different metric choices. However, utilizing robust semantic correspondence to transfer color from the reference to the old photo can result in inevitable structure distortions. To mitigate this, we introduce a structure-preserving mechanism that incorporates a perceptual constraint at the feature level and a frozen-updated pyramid at the pixel level. Extensive experiments demonstrate the effectiveness of our method for old photo colorization, as confirmed by qualitative and quantitative metrics.

☆ Temporal and Rotational Calibration for Event-Centric Multi-Sensor Systems

Jiayao Mai, Xiuyuan Lu, Kuan Dai, Shaojie Shen, Yi Zhou

Event cameras generate asynchronous signals in response to pixel-level brightness changes, offering a sensing paradigm with theoretically microsecond-scale latency that can significantly enhance the performance of multi-sensor systems. Extrinsic calibration is a critical prerequisite for effective sensor fusion; however, the configuration that involves event cameras remains an understudied topic. In this paper, we propose a motion-based temporal and rotational calibration framework tailored for event-centric multi-sensor systems, eliminating the need for dedicated calibration targets. Our method uses as input the rotational motion estimates obtained from event cameras and other heterogeneous sensors, respectively. Different from conventional approaches that rely on event-to-frame conversion, our method efficiently estimates angular velocity from normal flow observations, which are derived from the spatio-temporal profile of event data. The overall calibration pipeline adopts a two-step approach: it first initializes the temporal offset and rotational extrinsics by exploiting kinematic correlations in the spirit of Canonical Correlation Analysis (CCA), and then refines both temporal and rotational parameters through a joint non-linear optimization using a continuous-time parametrization in SO(3). Extensive evaluations on both publicly available and self-collected datasets validate that the proposed method achieves calibration accuracy comparable to target-based methods, while exhibiting superior stability over purely CCA-based methods, and highlighting its precision, robustness and flexibility. To facilitate future research, our implementation will be made open-source. Code: https://github.com/NAIL-HNU/EvMultiCalib.

comment: 8 pages, 5 figures

☆ Anatomic Feature Fusion Model for Diagnosing Calcified Pulmonary Nodules on Chest X-Ray

Hyeonjin Choi, Yang-gon Kim, Dong-yeon Yoo, Ju-sung Sun, Jung-won Lee

Accurate and timely identification of pulmonary nodules on chest X-rays can differentiate between life-saving early treatment and avoidable invasive procedures. Calcification is a definitive indicator of benign nodules and is the primary foundation for diagnosis. In actual practice, diagnosing pulmonary nodule calcification on chest X-rays predominantly depends on the physician's visual assessment, resulting in significant diversity in interpretation. Furthermore, overlapping anatomical elements, such as ribs and spine, complicate the precise identification of calcification patterns. This study presents a calcification classification model that attains strong diagnostic performance by utilizing fused features derived from raw images and their structure-suppressed variants to reduce structural interference. We used 2,517 lesion-free images and 656 nodule images (151 calcified nodules and 550 non-calcified nodules), all obtained from Ajou University Hospital. The suggested model attained an accuracy of 86.52% and an AUC of 0.8889 in calcification diagnosis, surpassing the model trained on raw images by 3.54% and 0.0385, respectively.

comment: 8 pages, 4 figures

☆ PROD: Palpative Reconstruction of Deformable Objects through Elastostatic Signed Distance Functions

Hamza El-Kebir

We introduce PROD (Palpative Reconstruction of Deformables), a novel method for reconstructing the shape and mechanical properties of deformable objects using elastostatic signed distance functions (SDFs). Unlike traditional approaches that rely on purely geometric or visual data, PROD integrates palpative interaction -- measured through force-controlled surface probing -- to estimate both the static and dynamic response of soft materials. We model the deformation of an object as an elastostatic process and derive a governing Poisson equation for estimating its SDF from a sparse set of pose and force measurements. By incorporating steady-state elastodynamic assumptions, we show that the undeformed SDF can be recovered from deformed observations with provable convergence. Our approach also enables the estimation of material stiffness by analyzing displacement responses to varying force inputs. We demonstrate the robustness of PROD in handling pose errors, non-normal force application, and curvature errors in simulated soft body interactions. These capabilities make PROD a powerful tool for reconstructing deformable objects in applications ranging from robotic manipulation to medical imaging and haptic feedback systems.

comment: Accepted for presentation at the 2025 IEEE Conference on Decision and Control (CDC)

☆ REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language

Ipsita Praharaj, Yukta Butala, Yash Butala

The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While existing works approach this problem using supervised training for specific manipulation or anomaly detection in the embedding space, generalization across domains remains a challenge. We frame this problem of forgery detection as a prompt-driven visual reasoning task, leveraging the semantic alignment capabilities of large vision-language models. We propose a framework, `REVEAL` (Reasoning and Evaluation of Visual Evidence through Aligned Language), that incorporates generalized guidelines. We propose two tangential approaches - (1) Holistic Scene-level Evaluation that relies on the physics, semantics, perspective, and realism of the image as a whole and (2) Region-wise anomaly detection that splits the image into multiple regions and analyzes each of them. We conduct experiments over datasets from different domains (Photoshop, DeepFake and AIGC editing). We compare the Vision Language Models against competitive baselines and analyze the reasoning provided by them.

comment: 4 pages, 6 figures, International Conference on Computer Vision, ICCV 2025

♻ ☆ A polynomial formula for the perspective four points problem

David Lehavi, Brian Osserman

We present a fast and accurate solution to the perspective $n$-points problem, by way of a new approach to the n=4 case. Our solution hinges on a novel separation of variables: given four 3D points and four corresponding 2D points on the camera canvas, we start by finding another set of 3D points, sitting on the rays connecting the camera to the 2D canvas points, so that the six pair-wise distances between these 3D points are as close as possible to the six distances between the original 3D points. This step reduces the perspective problem to an absolute orientation problem, which has a solution via explicit formula. To solve the first problem we set coordinates which are as orientation-free as possible: on the 3D points side our coordinates are the squared distances between the points. On the 2D canvas-points side our coordinates are the dot products of the points after rotating one of them to sit on the optical axis. We then derive the solution with the help of a computer algebra system. Our solution is an order of magnitude faster than state of the art algorithms, while offering similar accuracy under realistic noise. Moreover, our reduction to the absolute orientation problem runs two orders of magnitude faster than other perspective problem solvers, allowing extremely efficient seed rejection when implementing RANSAC.

comment: 17 pages

♻ ☆ WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction

Richard Liu, Daniel Fu, Noah Tan, Itai Lang, Rana Hanocka

In this work we present WIR3D, a technique for abstracting 3D shapes through a sparse set of visually meaningful curves in 3D. We optimize the parameters of Bezier curves such that they faithfully represent both the geometry and salient visual features (e.g. texture) of the shape from arbitrary viewpoints. We leverage the intermediate activations of a pre-trained foundation model (CLIP) to guide our optimization process. We divide our optimization into two phases: one for capturing the coarse geometry of the shape, and the other for representing fine-grained features. Our second phase supervision is spatially guided by a novel localized keypoint loss. This spatial guidance enables user control over abstracted features. We ensure fidelity to the original surface through a neural SDF loss, which allows the curves to be used as intuitive deformation handles. We successfully apply our method for shape abstraction over a broad dataset of shapes with varying complexity, geometric structure, and texture, and demonstrate downstream applications for feature control and shape deformation.

comment: ICCV 2025 Oral Project page: https://threedle.github.io/wir3d/

♻ ☆ DAGait: Generalized Skeleton-Guided Data Alignment for Gait Recognition

Zhengxian Wu, Chuanrui Zhang, Hangrui Xu, Peng Jiao, Haoqian Wang

Gait recognition is emerging as a promising and innovative area within the field of computer vision, widely applied to remote person identification. Although existing gait recognition methods have achieved substantial success in controlled laboratory datasets, their performance often declines significantly when transitioning to wild datasets.We argue that the performance gap can be primarily attributed to the spatio-temporal distribution inconsistencies present in wild datasets, where subjects appear at varying angles, positions, and distances across the frames. To achieve accurate gait recognition in the wild, we propose a skeleton-guided silhouette alignment strategy, which uses prior knowledge of the skeletons to perform affine transformations on the corresponding silhouettes.To the best of our knowledge, this is the first study to explore the impact of data alignment on gait recognition. We conducted extensive experiments across multiple datasets and network architectures, and the results demonstrate the significant advantages of our proposed alignment strategy.Specifically, on the challenging Gait3D dataset, our method achieved an average performance improvement of 7.9% across all evaluated networks. Furthermore, our method achieves substantial improvements on cross-domain datasets, with accuracy improvements of up to 24.0%.

♻ ☆ Degradation-Agnostic Statistical Facial Feature Transformation for Blind Face Restoration in Adverse Weather Conditions

Chang-Hwan Son

With the increasing deployment of intelligent CCTV systems in outdoor environments, there is a growing demand for face recognition systems optimized for challenging weather conditions. Adverse weather significantly degrades image quality, which in turn reduces recognition accuracy. Although recent face image restoration (FIR) models based on generative adversarial networks (GANs) and diffusion models have shown progress, their performance remains limited due to the lack of dedicated modules that explicitly address weather-induced degradations. This leads to distorted facial textures and structures. To address these limitations, we propose a novel GAN-based blind FIR framework that integrates two key components: local Statistical Facial Feature Transformation (SFFT) and Degradation-Agnostic Feature Embedding (DAFE). The local SFFT module enhances facial structure and color fidelity by aligning the local statistical distributions of low-quality (LQ) facial regions with those of high-quality (HQ) counterparts. Complementarily, the DAFE module enables robust statistical facial feature extraction under adverse weather conditions by aligning LQ and HQ encoder representations, thereby making the restoration process adaptive to severe weather-induced degradations. Experimental results demonstrate that the proposed degradation-agnostic SFFT model outperforms existing state-of-the-art FIR methods based on GAN and diffusion models, particularly in suppressing texture distortions and accurately reconstructing facial structures. Furthermore, both the SFFT and DAFE modules are empirically validated in enhancing structural fidelity and perceptual quality in face restoration under challenging weather scenarios.

♻ ☆ NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

NextStep Team, Chunrui Han, Guopeng Li, Jingwei Wu, Quan Sun, Yan Cai, Yuang Peng, Zheng Ge, Deyu Zhou, Haomiao Tang, Hongyu Zhou, Kenkun Liu, Ailin Huang, Bin Wang, Changxin Miao, Deshan Sun, En Yu, Fukun Yin, Gang Yu, Hao Nie, Haoran Lv, Hanpeng Hu, Jia Wang, Jian Zhou, Jianjian Sun, Kaijun Tan, Kang An, Kangheng Lin, Liang Zhao, Mei Chen, Peng Xing, Rui Wang, Shiyu Liu, Shutao Xia, Tianhao You, Wei Ji, Xianfang Zeng, Xin Han, Xuelin Zhang, Yana Wei, Yanming Xu, Yimin Jiang, Yingming Wang, Yu Zhou, Yucheng Han, Ziyang Meng, Binxing Jiao, Daxin Jiang, Xiangyu Zhang, Yibo Zhu

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.

comment: Code: https://github.com/stepfun-ai/NextStep-1

♻ ☆ TopoMortar: A dataset to evaluate image segmentation methods focused on topology accuracy

Juan Miguel Valverde, Motoya Koga, Nijihiko Otsuka, Anders Bjorholm Dahl

We present TopoMortar, a brick wall dataset that is the first dataset specifically designed to evaluate topology-focused image segmentation methods, such as topology loss functions. Motivated by the known sensitivity of methods to dataset challenges, such as small training sets, noisy labels, and out-of-distribution test-set images, TopoMortar is created to enable in two ways investigating methods' effectiveness at improving topology accuracy. First, by eliminating dataset challenges that, as we show, impact the effectiveness of topology loss functions. Second, by allowing to represent different dataset challenges in the same dataset, isolating methods' performance from dataset challenges. TopoMortar includes three types of labels (accurate, pseudo-labels, and noisy labels), two fixed training sets (large and small), and in-distribution and out-of-distribution test-set images. We compared eight loss functions on TopoMortar, and we found that clDice achieved the most topologically accurate segmentations, and that the relative advantageousness of the other loss functions depends on the experimental setting. Additionally, we show that data augmentation and self-distillation can elevate Cross entropy Dice loss to surpass most topology loss functions, and that those simple methods can enhance topology loss functions as well. TopoMortar and our code can be found at https://jmlipman.github.io/TopoMortar

comment: Accepted to BMVC 2025 (Oral)

♻ ☆ CCDM: Continuous Conditional Diffusion Models for Image Generation

Xin Ding, Yongwei Wang, Kao Zhang, Z. Jane Wang

Continuous Conditional Generative Modeling (CCGM) estimates high-dimensional data distributions, such as images, conditioned on scalar continuous variables (aka regression labels). While Continuous Conditional Generative Adversarial Networks (CcGANs) were designed for this task, their instability during adversarial learning often leads to suboptimal results. Conditional Diffusion Models (CDMs) offer a promising alternative, generating more realistic images, but their diffusion processes, label conditioning, and model fitting procedures are either not optimized for or incompatible with CCGM, making it difficult to integrate CcGANs' vicinal approach. To address these issues, we introduce Continuous Conditional Diffusion Models (CCDMs), the first CDM specifically tailored for CCGM. CCDMs address existing limitations with specially designed conditional diffusion processes, a novel hard vicinal image denoising loss, a customized label embedding method, and efficient conditional sampling procedures. Through comprehensive experiments on four datasets with resolutions ranging from 64x64 to 192x192, we demonstrate that CCDMs outperform state-of-the-art CCGM models, establishing a new benchmark. Ablation studies further validate the model design and implementation, highlighting that some widely used CDM implementations are ineffective for the CCGM task. Our code is publicly available at https://github.com/UBCDingXin/CCDM.

♻ ☆ A locally statistical active contour model for SAR image segmentation can be solved by denoising algorithms

Guangming Liu

In this paper, we propose a novel locally statistical variational active contour model based on I-divergence-TV denoising model, which hybrides geodesic active contour (GAC) model with active contours without edges (ACWE) model, and can be used to segment images corrupted by multiplicative gamma noise. By adding a diffusion term into the level set evolution (LSE) equation of the proposed model, we construct a reaction-diffusion (RD) equation, which can gradually regularize the level set function (LSF) to be piecewise constant in each segment domain and gain the stable solution. We further transform the proposed model into classic ROF model by adding a proximity term. [27] is submitted on 29-Aug-2013, and our early edition ever submitted to TGRS on 12-Jun-2012, Venkatakrishnan et al. [31] proposed their 'pnp algorithm' on 29-May-2013, so Venkatakrishnan and we proposed the 'pnp algorithm' almost simultaneously. Inspired by a fast denoising algorithm proposed by Jia-Zhao recently, we propose two fast fixed point algorithms to solve SAR image segmentation question. Experimental results for real SAR images show that the proposed image segmentation model can efficiently stop the contours at weak or blurred edges, and can automatically detect the exterior and interior boundaries of images with multiplicative gamma noise. The proposed FPRD1/FPRD2 models are about 1/2 (or less than) of the time required for the SBRD model based on the Split Bregman technique.

comment: 19 pages, 15 figures

♻ ☆ When Deep Learning Fails: Limitations of Recurrent Models on Stroke-Based Handwriting for Alzheimer's Disease Detection

Emanuele Nardone, Tiziana D'Alessandro, Francesco Fontanella, Claudio De Stefano

Alzheimer's disease detection requires expensive neuroimaging or invasive procedures, limiting accessibility. This study explores whether deep learning can enable non-invasive Alzheimer's disease detection through handwriting analysis. Using a dataset of 34 distinct handwriting tasks collected from healthy controls and Alzheimer's disease patients, we evaluate and compare three recurrent neural architectures (LSTM, GRU, RNN) against traditional machine learning models. A crucial distinction of our approach is that the recurrent models process pre-extracted features from discrete strokes, not raw temporal signals. This violates the assumption of a continuous temporal flow that recurrent networks are designed to capture. Results reveal that they exhibit poor specificity and high variance. Traditional ensemble methods significantly outperform all deep architectures, achieving higher accuracy with balanced metrics. This demonstrates that recurrent architectures, designed for continuous temporal sequences, fail when applied to feature vectors extracted from ambiguously segmented strokes. Despite their complexity, deep learning models cannot overcome the fundamental disconnect between their architectural assumptions and the discrete, feature-based nature of stroke-level handwriting data. Although performance is limited, the study highlights several critical issues in data representation and model compatibility, pointing to valuable directions for future research.

♻ ☆ CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Retrieval

Xinpeng Zhao, Yanwei Zheng, Chuanlin Lan, Xiaowei Zhang, Bowen Huang, Jibin Yang, Dongxiao Yu

Weakly supervised text-based person retrieval seeks to retrieve images of a target person using textual descriptions, without relying on identity annotations and is more challenging and practical. The primary challenge is the intra-class differences, encompassing intra-modal feature variations and cross-modal semantic gaps. Prior works have focused on instance-level samples and ignored prototypical features of each person which are intrinsic and invariant. Toward this, we propose a Cross-Modal Prototypical Contrastive Learning (CPCL) method. In practice, the CPCL introduces the CLIP model to weakly supervised text-based person retrieval to map visual and textual instances into a shared latent space. Subsequently, the proposed Prototypical Multi-modal Memory (PMM) module captures associations between heterogeneous modalities of image-text pairs belonging to the same person through the Hybrid Cross-modal Matching (HCM) module in a many-to-many mapping fashion. Moreover, the Outlier Pseudo Label Mining (OPLM) module further distinguishes valuable outlier samples from each modality, enhancing the creation of more reliable clusters by mining implicit relationships between image-text pairs. We conduct extensive experiments on popular benchmarks of weakly supervised text-based person retrieval, which validate the effectiveness, generalizability of CPCL.

comment: 9 pages, 6 figures, under peer review

♻ ☆ Learn 3D VQA Better with Active Selection and Reannotation ACM MM 2025

Shengli Zhou, Yang Liu, Feng Zheng

3D Visual Question Answering (3D VQA) is crucial for enabling models to perceive the physical world and perform spatial reasoning. In 3D VQA, the free-form nature of answers often leads to improper annotations that can confuse or mislead models when training on the entire dataset. While other text generation tasks can mitigate this issue by learning on large-scale datasets, the scarcity of 3D scene data enlarges the negative effect of misleading annotations. Although active learning strategies can select valuable instances for training, they fail to identify and resolve misleading labels, which the oracle inevitably provides in practice. To address this issue, we propose a multi-turn interactive active learning strategy. This strategy selects data based on models' semantic uncertainty to form a solid knowledge foundation more effectively and actively requests reannotation from an oracle to resolve potentially misleading labels. For uncertainty assessment, we utilize a variance-based metric that takes semantic relationships between terms into consideration, thus avoiding the uniform inter-class similarity assumption of previous assessment metrics. Extensive experiments exhibit better model performance and a substantial reduction in training costs, with a halving of training costs for achieving relatively high accuracy. The code is available at https://github.com/fz-zsl/AQuA.

comment: 13 pages, 16 figures, accepted by ACM MM 2025

♻ ☆ Mapping the Unseen: Unified Promptable Panoptic Mapping with Dynamic Labeling using Foundation Models

Mohamad Al Mdfaa, Raghad Salameh, Geesara Kulathunga, Sergey Zagoruyko, Gonzalo Ferrer

In robotics and computer vision, semantic mapping remains a critical challenge for machines to comprehend complex environments. Traditional panoptic mapping approaches are constrained by fixed labels, limiting their ability to handle novel objects. We present Unified Promptable Panoptic Mapping (UPPM), which leverages foundation models for dynamic labeling without additional training. UPPM is evaluated across three comprehensive levels: Segmentation-to-Map, Map-to-Map, and Segmentation-to-Segmentation. Results demonstrate UPPM attains exceptional geometry reconstruction accuracy (0.61cm on the Flat dataset), the highest panoptic quality (0.414), and better performance compared to state-of-the-art segmentation methods. Furthermore, ablation studies validate the contributions of unified semantics, custom NMS, and blurry frame filtering, with the custom NMS improving the completion ratio by 8.27% on the Flat dataset. UPPM demonstrates effective scene reconstruction with rich semantic labeling across diverse datasets.

comment: This work has been submitted to the IEEE for possible publication

♻ ☆ Inverse Bridge Matching Distillation

Nikita Gushchin, David Li, Daniil Selikhanovych, Evgeny Burnaev, Dmitry Baranchuk, Alexander Korotin

Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern diffusion and flow models, DBMs suffer from the problem of slow inference. To address it, we propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice. Unlike previously developed DBM distillation techniques, the proposed method can distill both conditional and unconditional types of DBMs, distill models in a one-step generator, and use only the corrupted images for training. We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks, and show that our distillation technique allows us to accelerate the inference of DBMs from 4x to 100x and even provide better generation quality than used teacher model depending on particular setup. We provide the code at https://github.com/ngushchin/IBMD

♻ ☆ Hyperspectral Image Generation with Unmixing Guided Diffusion Model

Shiyu Shen, Bin Pan, Ziye Zhang, Zhenwei Shi

Recently, hyperspectral image generation has received increasing attention, but existing generative models rely on conditional generation schemes, which limits the diversity of generated images. Diffusion models are popular for their ability to generate high-quality samples, but adapting these models from RGB to hyperspectral data presents the challenge of high dimensionality and physical constraints. To address these challenges, we propose a novel diffusion model guided by hyperspectral unmixing. Our model comprises two key modules: an unmixing autoencoder module and an abundance diffusion module. The unmixing autoencoder module leverages unmixing guidance to shift the generative task from the image space to the low-dimensional abundance space, significantly reducing computational complexity while preserving high fidelity. The abundance diffusion module generates samples that satisfy the constraints of non-negativity and unity, ensuring the physical consistency of the reconstructed HSIs. Additionally, we introduce two evaluation metrics tailored to hyperspectral data. Empirical results, evaluated using both traditional metrics and our proposed metrics, indicate that our model is capable of generating high-quality and diverse hyperspectral images, offering an advancement in hyperspectral data generation.

♻ ☆ TRIDE: A Text-assisted Radar-Image weather-aware fusion network for Depth Estimation

Huawei Sun, Zixu Wang, Hao Feng, Julius Ott, Lorenzo Servadei, Robert Wille

Depth estimation, essential for autonomous driving, seeks to interpret the 3D environment surrounding vehicles. The development of radar sensors, known for their cost-efficiency and robustness, has spurred interest in radar-camera fusion-based solutions. However, existing algorithms fuse features from these modalities without accounting for weather conditions, despite radars being known to be more robust than cameras under adverse weather. Additionally, while Vision-Language models have seen rapid advancement, utilizing language descriptions alongside other modalities for depth estimation remains an open challenge. This paper first introduces a text-generation strategy along with feature extraction and fusion techniques that can assist monocular depth estimation pipelines, leading to improved accuracy across different algorithms on the KITTI dataset. Building on this, we propose TRIDE, a radar-camera fusion algorithm that enhances text feature extraction by incorporating radar point information. To address the impact of weather on sensor performance, we introduce a weather-aware fusion block that adaptively adjusts radar weighting based on current weather conditions. Our method, benchmarked on the nuScenes dataset, demonstrates performance gains over the state-of-the-art, achieving a 12.87% improvement in MAE and a 9.08% improvement in RMSE. Code: https://github.com/harborsarah/TRIDE

comment: Accepted by TMLR (2025.08)

♻ ☆ PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

Yanjie Pan, Qingdong He, Zhengkai Jiang, Pengcheng Xu, Chaoyi Wang, Jinlong Peng, Haoxuan Wang, Yun Cao, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously preserving semantic fidelity across multiple heterogeneous control signals while maintaining high visual quality, where they employ separate control branches that often introduce conflicting guidance during the denoising process, leading to structural distortions and artifacts in generated images. To address this issue, we present PixelPonder, a novel unified control framework, which allows for effective control of multiple visual conditions under a single control structure. Specifically, we design a patch-level adaptive condition selection mechanism that dynamically prioritizes spatially relevant control signals at the sub-region level, enabling precise local guidance without global interference. Additionally, a time-aware control injection scheme is deployed to modulate condition influence according to denoising timesteps, progressively transitioning from structural preservation to texture refinement and fully utilizing the control information from different categories to promote more harmonious image generation. Extensive experiments demonstrate that PixelPonder surpasses previous methods across different benchmark datasets, showing superior improvement in spatial alignment accuracy while maintaining high textual semantic consistency.

♻ ☆ TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes

Nikai Du, Zhennan Chen, Shan Gao, Zhizhou Chen, Xi Chen, Zhengkai Jiang, Jian Yang, Ying Tai

This paper explores the task of Complex Visual Text Generation (CVTG), which centers on generating intricate textual content distributed across diverse regions within visual images. In CVTG, image generation models often rendering distorted and blurred visual text or missing some visual text. To tackle these challenges, we propose TextCrafter, a novel multi-visual text rendering method. TextCrafter employs a progressive strategy to decompose complex visual text into distinct components while ensuring robust alignment between textual content and its visual carrier. Additionally, it incorporates a token focus enhancement mechanism to amplify the prominence of visual text during the generation process. TextCrafter effectively addresses key challenges in CVTG tasks, such as text confusion, omissions, and blurriness. Moreover, we present a new benchmark dataset, CVTG-2K, tailored to rigorously evaluate the performance of generative models on CVTG tasks. Extensive experiments demonstrate that our method surpasses state-of-the-art approaches.

♻ ☆ Best Foot Forward: Robust Foot Reconstruction in-the-wild

Kyle Fogarty, Jing Yang, Chayan Kumar Patodi, Jack Foster, Aadi Bhanti, Steven Chacko, Cengiz Oztireli, Ujwal Bonde

Accurate 3D foot reconstruction is crucial for personalized orthotics, digital healthcare, and virtual fittings. However, existing methods struggle with incomplete scans and anatomical variations, particularly in self-scanning scenarios where user mobility is limited, making it difficult to capture areas like the arch and heel. We present a novel end-to-end pipeline that refines Structure-from-Motion (SfM) reconstruction. It first resolves scan alignment ambiguities using SE(3) canonicalization with a viewpoint prediction module, then completes missing geometry through an attention-based network trained on synthetically augmented point clouds. Our approach achieves state-of-the-art performance on reconstruction metrics while preserving clinically validated anatomical fidelity. By combining synthetic training data with learned geometric priors, we enable robust foot reconstruction under real-world capture conditions, unlocking new opportunities for mobile-based 3D scanning in healthcare and retail.

comment: ICCV 2025 Workshop on Advanced Perception for Autonomous Healthcare

♻ ☆ Diving into the Fusion of Monocular Priors for Generalized Stereo Matching

Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, Yunde Jia

The matching formulation makes it naturally hard for the stereo matching to handle ill-posed regions like occlusions and non-Lambertian surfaces. Fusing monocular priors has been proven helpful for ill-posed matching, but the biased monocular prior learned from small stereo datasets constrains the generalization. Recently, stereo matching has progressed by leveraging the unbiased monocular prior from the vision foundation model (VFM) to improve the generalization in ill-posed regions. We dive into the fusion process and observe three main problems limiting the fusion of the VFM monocular prior. The first problem is the misalignment between affine-invariant relative monocular depth and absolute depth of disparity. Besides, when we use the monocular feature in an iterative update structure, the over-confidence in the disparity update leads to local optima results. A direct fusion of a monocular depth map could alleviate the local optima problem, but noisy disparity results computed at the first several iterations will misguide the fusion. In this paper, we propose a binary local ordering map to guide the fusion, which converts the depth map into a binary relative format, unifying the relative and absolute depth representation. The computed local ordering map is also used to re-weight the initial disparity update, resolving the local optima and noisy problem. In addition, we formulate the final direct fusion of monocular depth to the disparity as a registration problem, where a pixel-wise linear regression module can globally and adaptively align them. Our method fully exploits the monocular prior to support stereo matching results effectively and efficiently. We significantly improve the performance from the experiments when generalizing from SceneFlow to Middlebury and Booster datasets while barely reducing the efficiency.

comment: Code: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching

♻ ☆ Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models

Enming Zhang, Bingke Zhu, Yingying Chen, Qinghai Miao, Ming Tang, Jinqiao Wang

Vision-Language Models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage VLMs' potential in adapting to downstream tasks, context optimization methods like Prompt Tuning are essential. However, one key limitation is the lack of diversity in prompt templates, whether they are hand-crafted or learned through additional modules. This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks. To address this challenge, we propose Context Optimization with Multi-Knowledge Representation (CoKnow), a framework that enhances Prompt Learning for VLMs with rich contextual knowledge. To facilitate CoKnow during inference, we trained lightweight semantic knowledge mappers, which are capable of generating Multi-Knowledge Representation for an input image without requiring additional priors. Experimentally, We conducted extensive experiments on 11 publicly available datasets, demonstrating that CoKnow outperforms a series of previous methods.

♻ ☆ V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?

Natchapon Jongwiriyanurak, Zichao Zeng, June Moh Goo, Xinglei Wang, Ilya Ilyankou, Kerkritt Sriroongvikrai, Nicola Christie, Meihui Wang, Huanfa Chen, James Haworth

Road safety assessments are critical yet costly, especially in Low- and Middle-Income Countries (LMICs), where most roads remain unrated. Traditional methods require expert annotation and training data, while supervised learning-based approaches struggle to generalise across regions. In this paper, we introduce \textit{V-RoAst}, a zero-shot Visual Question Answering (VQA) framework using Vision-Language Models (VLMs) to classify road safety attributes defined by the iRAP standard. We introduce the first open-source dataset from ThaiRAP, consisting of over 2,000 curated street-level images from Thailand annotated for this task. We evaluate Gemini-1.5-flash and GPT-4o-mini on this dataset and benchmark their performance against VGGNet and ResNet baselines. While VLMs underperform on spatial awareness, they generalise well to unseen classes and offer flexible prompt-based reasoning without retraining. Our results show that VLMs can serve as automatic road assessment tools when integrated with complementary data. This work is the first to explore VLMs for zero-shot infrastructure risk assessment and opens new directions for automatic, low-cost road safety mapping. Code and dataset: https://github.com/PongNJ/V-RoAst.

♻ ☆ PSScreen: Partially Supervised Multiple Retinal Disease Screening

Boyi Zheng, Qing Liu

Leveraging multiple partially labeled datasets to train a model for multiple retinal disease screening reduces the reliance on fully annotated datasets, but remains challenging due to significant domain shifts across training datasets from various medical sites, and the label absent issue for partial classes. To solve these challenges, we propose PSScreen, a novel Partially Supervised multiple retinal disease Screening model. Our PSScreen consists of two streams and one learns deterministic features and the other learns probabilistic features via uncertainty injection. Then, we leverage the textual guidance to decouple two types of features into disease-wise features and align them via feature distillation to boost the domain generalization ability. Meanwhile, we employ pseudo label consistency between two streams to address the label absent issue and introduce a self-distillation to transfer task-relevant semantics about known classes from the deterministic to the probabilistic stream to further enhance the detection performances. Experiments show that our PSScreen significantly enhances the detection performances on six retinal diseases and the normal state averagely and achieves state-of-the-art results on both in-domain and out-of-domain datasets. Codes are available at https://github.com/boyiZheng99/PSScreen.

comment: Accepted at BMVC 2025 (Oral)

♻ ☆ From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

Ke Niu, Haiyang Yu, Zhuofan Chen, Mengyang Zhao, Teng Fu, Bin Li, Xiangyang Xue

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.

♻ ☆ Deep Positive-Negative Prototypes for Adversarially Robust Discriminative Prototypical Learning

Ramin Zarei Sabzevar, Hamed Mohammadzadeh, Tahmineh Tavakoli, Ahad Harati

Despite the advantages of discriminative prototype-based methods, their role in adversarial robustness remains underexplored. Meanwhile, current adversarial training methods predominantly focus on robustness against adversarial attacks without explicitly leveraging geometric structures in the latent space, usually resulting in reduced accuracy on the original clean data. We propose a novel framework named Adversarially trained Deep Positive-Negative Prototypes (Adv-DPNP), which integrates discriminative prototype-based learning with adversarial training. Adv-DPNP uses unified class prototypes that serve as both classifier weights and robust anchors in the latent space. Moreover, a novel dual-branch training mechanism maintains stable prototypes by updating them exclusively with clean data, while the feature extractor is trained on both clean and adversarial inputs to increase invariance to adversarial perturbations. In addition, we use a composite loss that combines positive-prototype alignment, negative-prototype repulsion, and consistency regularization to further enhance discrimination, adversarial robustness, and clean accuracy. Extensive experiments on standard benchmarks (CIFAR-10/100 and SVHN) confirm that Adv-DPNP improves clean accuracy over state-of-the-art defenses and baseline methods, while maintaining competitive or superior robustness under a suite of widely used attacks, including FGSM, PGD, C\&W, and AutoAttack. We also evaluate robustness to common corruptions on CIFAR-10-C, where Adv-DPNP achieves the highest average accuracy across severities and corruption types. Additionally, we provide an in-depth analysis of the discriminative quality of the learned feature representations, highlighting the effectiveness of Adv-DPNP in maintaining compactness and clear separation in the latent space.

comment: This version substantially revises the manuscript, including a new title and updated experimental results

♻ ☆ Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos

Shucheng Gong, Lingzhe Zhao, Wenpu Li, Hong Xie, Yin Zhang, Shiyu Zhao, Peidong Liu

Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low dynamic range (LDR) images, limiting their ability to capture detailed scenes in high-contrast environments. While some prior works address high dynamic range (HDR) scene reconstruction, they typically require multi-view sharp images with varying exposure times captured at fixed camera positions, which is time-consuming and impractical. To make data acquisition more flexible, we propose \textbf{Casual3DHDR}, a robust one-stage method that reconstructs 3D HDR scenes from casually-captured auto-exposure (AE) videos, even under severe motion blur and unknown, varying exposure times. Our approach integrates a continuous-time camera trajectory into a unified physical imaging model, jointly optimizing exposure times, camera trajectory, and the camera response function (CRF). Extensive experiments on synthetic and real-world datasets demonstrate that \textbf{Casual3DHDR} outperforms existing methods in robustness and rendering quality. Our source code and dataset will be available at https://lingzhezhao.github.io/CasualHDRSplat/

comment: Accepted to ACM Multimedia 2025. Project page: https://lingzhezhao.github.io/CasualHDRSplat/

♻ ☆ Co-Paced Learning Strategy Based on Confidence for Flying Bird Object Detection Model Training

Zi-Wei Sun, Ze-Xi Hua, Heng-Chao Li, Yan Li

The flying bird objects captured by surveillance cameras exhibit varying levels of recognition difficulty due to factors such as their varying sizes or degrees of similarity to the background. To alleviate the negative impact of hard samples on training the Flying Bird Object Detection (FBOD) model for surveillance videos, we propose the Co-Paced Learning strategy Based on Confidence (CPL-BC) and apply it to the training process of the FBOD model. This strategy involves maintaining two models with identical structures but different initial parameter configurations that collaborate with each other to select easy samples for training, where the prediction confidence exceeds a set threshold. As training progresses, the strategy gradually lowers the threshold, thereby gradually enhancing the model's ability to recognize objects, from easier to more hard ones. Prior to applying CPL-BC, we pre-trained the two FBOD models to equip them with the capability to assess the difficulty of flying bird object samples. Experimental results on two different datasets of flying bird objects in surveillance videos demonstrate that, compared to other model learning strategies, CPL-BC significantly improves detection accuracy, thereby verifying the method's effectiveness and advancement.

♻ ☆ Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation

Feiran Li, Qianqian Xu, Shilong Bao, Boyu Han, Zhiyong Yang, Qingming Huang

In this paper, we present our approach to the DataCV ICCV Challenge, which centers on building a high-quality face dataset to train a face recognition model. The constructed dataset must not contain identities overlapping with any existing public face datasets. To handle this challenge, we begin with a thorough cleaning of the baseline HSFace dataset, identifying and removing mislabeled or inconsistent identities through a Mixture-of-Experts (MoE) strategy combining face embedding clustering and GPT-4o-assisted verification. We retain the largest consistent identity cluster and apply data augmentation up to a fixed number of images per identity. To further diversify the dataset, we generate synthetic identities using Stable Diffusion with prompt engineering. As diffusion models are computationally intensive, we generate only one reference image per identity and efficiently expand it using Vec2Face, which rapidly produces 49 identity-consistent variants. This hybrid approach fuses GAN-based and diffusion-based samples, enabling efficient construction of a diverse and high-quality dataset. To address the high visual similarity among synthetic identities, we adopt a curriculum learning strategy by placing them early in the training schedule, allowing the model to progress from easier to harder samples. Our final dataset contains 50 images per identity, and all newly generated identities are checked with mainstream face datasets to ensure no identity leakage. Our method achieves \textbf{1st place} in the competition, and experimental results show that our dataset improves model performance across 10K, 20K, and 100K identity scales. Code is available at https://github.com/Ferry-Li/datacv_fr.

comment: This paper has been accpeted to ICCV 2025 DataCV Workshop

♻ ☆ Diffusion Based Ambiguous Image Segmentation

Jakob Lønborg Christensen, Morten Rieger Hannemose, Anders Bjorholm Dahl, Vedrana Andersen Dahl

Medical image segmentation often involves inherent uncertainty due to variations in expert annotations. Capturing this uncertainty is an important goal and previous works have used various generative image models for the purpose of representing the full distribution of plausible expert ground truths. In this work, we explore the design space of diffusion models for generative segmentation, investigating the impact of noise schedules, prediction types, and loss weightings. Notably, we find that making the noise schedule harder with input scaling significantly improves performance. We conclude that x- and v-prediction outperform epsilon-prediction, likely because the diffusion process is in the discrete segmentation domain. Many loss weightings achieve similar performance as long as they give enough weight to the end of the diffusion process. We base our experiments on the LIDC-IDRI lung lesion dataset and obtain state-of-the-art (SOTA) performance. Additionally, we introduce a randomly cropped variant of the LIDC-IDRI dataset that is better suited for uncertainty in image segmentation. Our model also achieves SOTA in this harder setting.

comment: Accepted at SCIA25

♻ ☆ LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering

Xinxin Dong, Baoyun Peng, Haokai Ma, Yufei Wang, Zixuan Dong, Fei Hu, Xiaodong Wang

Video Question Answering (VideoQA) requires identifying sparse critical moments in long videos and reasoning about their causal relationships to answer semantically complex questions. While recent advances in multimodal learning have improved alignment and fusion, current approaches remain limited by two prevalent but fundamentally flawed strategies: (1) task-agnostic sampling indiscriminately processes all frames, overwhelming key events with irrelevant content; and (2) heuristic retrieval captures superficial patterns but misses causal-temporal structures needed for complex reasoning. To address these challenges, we introduce LeAdQA, an innovative approach that bridges these gaps through synergizing causal-aware query refinement with fine-grained visual grounding. Our method first leverages LLMs to reformulate question-option pairs, resolving causal ambiguities and sharpening temporal focus. These refined queries subsequently direct a temporal grounding model to precisely retrieve the most salient segments, complemented by an adaptive fusion mechanism dynamically integrating the evidence to maximize relevance. The integrated visual-textual cues are then processed by an MLLM to generate accurate, contextually-grounded answers. Experiments on NExT-QA, IntentQA, and NExT-GQA demonstrate that our method's precise visual grounding substantially enhances the understanding of video-question relationships, achieving state-of-the-art (SOTA) performance on complex reasoning tasks while maintaining computational efficiency.

♻ ☆ Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language

Guangfu Hao, Haojie Wen, Liangxuan Guo, Yang Chen, Yanchao Bi, Shan Yu

Flexible tool selection reflects a complex cognitive ability that distinguishes humans from other species, yet computational models that capture this ability remain underdeveloped. We developed a framework using low-dimensional attribute representations to bridge visual tool perception and linguistic task understanding. We constructed a comprehensive dataset (ToolNet) containing 115 common tools labeled with 13 carefully designed attributes spanning physical, functional, and psychological properties, paired with natural language scenarios describing tool usage. Visual encoders (ResNet or ViT) extract attributes from tool images while fine-tuned language models (GPT-2, LLaMA, DeepSeek) derive required attributes from task descriptions. Our approach achieves 74% accuracy in tool selection tasks-significantly outperforming direct tool matching (20%) and smaller multimodal models (21%-58%), while approaching performance of much larger models like GPT-4o (73%) with substantially fewer parameters. Human evaluation studies validate our framework's alignment with human decision-making patterns, and generalization experiments demonstrate effective performance on novel tool categories. Ablation studies revealed that manipulation-related attributes (graspability, elongation, hand-relatedness) consistently prove most critical across modalities. This work provides a parameter-efficient, interpretable solution that mimics human-like tool cognition, advancing both cognitive science understanding and practical applications in tool selection tasks.

♻ ☆ Novel Object 6D Pose Estimation with a Single Reference View

Jian Liu, Wei Sun, Kai Zeng, Jin Zheng, Hui Yang, Hossein Rahmani, Ajmal Mian, Lin Wang

Existing novel object 6D pose estimation methods typically rely on CAD models or dense reference views, which are both difficult to acquire. Using only a single reference view is more scalable, but challenging due to large pose discrepancies and limited geometric and spatial information. To address these issues, we propose a Single-Reference-based novel object 6D (SinRef-6D) pose estimation method. Our key idea is to iteratively establish point-wise alignment in a common coordinate system based on state space models (SSMs). Specifically, iterative object-space point-wise alignment can effectively handle large pose discrepancies, while our proposed RGB and Points SSMs can capture long-range dependencies and spatial information from a single view, offering linear complexity and superior spatial modeling capability. Once pre-trained on synthetic data, SinRef-6D can estimate the 6D pose of a novel object using only a single reference view, without requiring retraining or a CAD model. Extensive experiments on six popular datasets and real-world robotic scenes demonstrate that we achieve on-par performance with CAD-based and dense reference view-based methods, despite operating in the more challenging single reference setting. Code will be released at https://github.com/CNJianLiu/SinRef-6D.

comment: 17 pages, 12 figures (including supplementary material)

♻ ☆ DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation

Vikram Singh, Kabir Malhotra, Rohan Desai, Ananya Shankaracharya, Priyadarshini Chatterjee, Krishnan Menon Iyer

Lesion segmentation, in contrast to natural scene segmentation, requires handling subtle variations in texture and color, frequent imaging artifacts (such as hairs, rulers, and bubbles), and a critical need for precise boundary localization to aid in accurate diagnosis. The accurate delineation of melanocytic tumors in dermoscopic images is a crucial component of automated skin cancer screening systems and clinical decision support. In this paper, we present a novel dual-resolution architecture inspired by ResNet, specifically tailored for the segmentation of melanocytic tumors. Our approach incorporates a high-resolution stream that preserves fine boundary details, alongside a complementary pooled stream that captures multi-scale contextual information for robust lesion recognition. These two streams are closely integrated through boundary-aware residual connections, which inject edge information into deep feature maps, and a channel attention mechanism that adapts the model's sensitivity to color and texture variations in dermoscopic images. To tackle common imaging artifacts and the challenges posed by small clinical datasets, we introduce a lightweight artifact suppression block and a multi-task training strategy. This strategy combines the Dice-Tversky loss with an explicit boundary loss and a contrastive regularizer to enhance feature stability. This unified design enables the model to generate pixel-accurate segmentation masks without the need for extensive post-processing or complex pre-training. Extensive evaluation on public dermoscopic benchmarks reveals that our method significantly enhances boundary precision and clinically relevant segmentation metrics, outperforming traditional encoder-decoder baselines. This makes our approach a valuable component for building automated melanoma assessment systems.

comment: MICCAIA

♻ ☆ VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation

Ayaan Nooruddin Siddiqui, Mahnoor Zaidi, Ayesha Nazneen Shahbaz, Priyadarshini Chatterjee, Krishnan Menon Iyer

The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as well as the challenge of low contrast and noisy vessel appearances across different patients and imaging modalities. In this work, we propose a novel weakly supervised training framework specifically designed for subcutaneous vessel segmentation. This method utilizes low-cost, sparse annotations such as centerline traces, dot markers, or short scribbles to guide the learning process. These sparse annotations are expanded into dense probabilistic supervision through a differentiable random walk label propagation model, which integrates vesselness cues and tubular continuity priors driven by image data. The label propagation process results in per-pixel hitting probabilities and uncertainty estimates, which are incorporated into an uncertainty-weighted loss function to prevent overfitting in ambiguous areas. Notably, the label propagation model is trained jointly with a CNN-based segmentation network, allowing the system to learn vessel boundaries and continuity constraints without the need for explicit edge supervision. Additionally, we introduce a topology-aware regularizer that encourages centerline connectivity and penalizes irrelevant branches, further enhancing clinical applicability. Our experiments on clinical subcutaneous imaging datasets demonstrate that our approach consistently outperforms both naive sparse-label training and traditional dense pseudo-labeling methods, yielding more accurate vascular maps and better-calibrated uncertainty, which is crucial for clinical decision-making. This method significantly reduces the annotation workload while maintaining clinically relevant vessel topology.

♻ ☆ Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

Lexiang Tang, Xianwei Zhuang, Bang Yang, Zhiyuan Hu, Hongxiang Li, Lu Ma, Jinghan Ru, Yuexian Zou

Large vision-language models (LVLMs) have demonstrated impressive capabilities across diverse multimodal tasks, yet they remain highly susceptible to visual hallucinations (VH), often producing confident but inaccurate descriptions of visual content. Building on the insight that not all tokens and attention heads contribute equally to VH mitigation, we introduce VisFlow, a lightweight and training-free framework that alleviates hallucinations by directly modulating attention patterns during inference. To address two primary challenges of VH, namely insufficient visual attention and the dominance of language priors, we identify three problematic attention behaviors in LVLMs: (1) disproportionate allocation of attention to uninformative or trailing visual tokens, (2) over-dependence on the previously generated token, and (3) excessive fixation on system prompts that hinders multimodal integration. To overcome these issues, VisFlow introduces a dual-level Attention Intervention, consisting of Token-level Attention Intervention (TAI), which reinforces attention to salient visual regions, and Head-level Attention Intervention (HAI), which suppresses undue focus on system prompts and adjacent text tokens. Together, these interventions strengthen visual alignment while reducing linguistic bias. Extensive experiments across diverse models and benchmarks demonstrate that VisFlow effectively mitigates hallucinations with minimal computational overhead.

♻ ☆ SLGaussian: Fast Language Gaussian Splatting in Sparse Views ACM MM 2025

Kangjie Chen, BingQuan Dai, Minghan Qin, Dongbin Zhang, Peihao Li, Yingshuang Zou, Haoqian Wang

3D semantic field learning is crucial for applications like autonomous navigation, AR/VR, and robotics, where accurate comprehension of 3D scenes from limited viewpoints is essential. Existing methods struggle under sparse view conditions, relying on inefficient per-scene multi-view optimizations, which are impractical for many real-world tasks. To address this, we propose SLGaussian, a feed-forward method for constructing 3D semantic fields from sparse viewpoints, allowing direct inference of 3DGS-based scenes. By ensuring consistent SAM segmentations through video tracking and using low-dimensional indexing for high-dimensional CLIP features, SLGaussian efficiently embeds language information in 3D space, offering a robust solution for accurate 3D scene understanding under sparse view conditions. In experiments on two-view sparse 3D object querying and segmentation in the LERF and 3D-OVS datasets, SLGaussian outperforms existing methods in chosen IoU, Localization Accuracy, and mIoU. Moreover, our model achieves scene inference in under 30 seconds and open-vocabulary querying in just 0.011 seconds per query.

comment: Accepted by ACM MM 2025. Project page: https://chenkangjie1123.github.io/SLGaussian.github.io/

♻ ☆ InterRVOS: Interaction-aware Referring Video Object Segmentation

Woojeong Jin, Seongchan Kim, Jaeho Lee, Seungryong Kim

Referring video object segmentation (RVOS) aims to segment objects in a video described by a natural language expression. However, most existing approaches focus on segmenting only the referred object (typically the actor), even when the expression clearly describes an interaction involving multiple objects with distinct roles. For instance, "A throwing B" implies a directional interaction, but standard RVOS segments only the actor (A), neglecting other involved target objects (B). In this paper, we introduce Interaction-aware Referring Video Object Segmentation (InterRVOS), a novel task that focuses on the modeling of interactions. It requires the model to segment the actor and target objects separately, reflecting their asymmetric roles in an interaction. This task formulation enables fine-grained understanding of object relationships, as many video events are defined by such relationships rather than individual objects. To support this task, we propose a new evaluation protocol that separately evaluates actor and target segmentation, enabling more accurate assessment of the model's ability to distinguish and segment actor and target roles. We also present InterRVOS-127K, a large-scale dataset with over 127K automatically annotated expressions, including interaction expressions annotated with distinct masks for actor and target objects. Furthermore, we develop ReVIOSa, an MLLM-based architecture that introduces interaction-aware special tokens and leverages an attention mask loss to enhance role-specific segmentation. Extensive experiments show that ReVIOSa not only outperforms existing baselines on our proposed InterRVOS-127K evaluation set, but also achieves strong performance on standard RVOS benchmarks. Our project page is available at: https://cvlab-kaist.github.io/InterRVOS.

♻ ☆ InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis

Jiale Liu, Huan Wang, Yue Zhang, Xiaoyu Luo, Jiaxiang Hu, Zhiliang Liu, Min Xie

Non-destructive testing (NDT), particularly X-ray inspection, is vital for industrial quality assurance, yet existing deep-learning-based approaches often lack interactivity, interpretability, and the capacity for critical self-assessment, limiting their reliability and operator trust. To address these shortcomings, this paper proposes InsightX Agent, a novel LMM-based agentic framework designed to deliver reliable, interpretable, and interactive X-ray NDT analysis. Unlike typical sequential pipelines, InsightX Agent positions a Large Multimodal Model (LMM) as a central orchestrator, coordinating between the Sparse Deformable Multi-Scale Detector (SDMSD) and the Evidence-Grounded Reflection (EGR) tool. The SDMSD generates dense defect region proposals for multi-scale feature maps and sparsifies them through Non-Maximum Suppression (NMS), optimizing detection of small, dense targets in X-ray images while maintaining computational efficiency. The EGR tool guides the LMM agent through a chain-of-thought-inspired review process, incorporating context assessment, individual defect analysis, false positive elimination, confidence recalibration and quality assurance to validate and refine the SDMSD's initial proposals. By strategically employing and intelligently using tools, InsightX Agent moves beyond passive data processing to active reasoning, enhancing diagnostic reliability and providing interpretations that integrate diverse information sources. Experimental evaluations on the GDXray+ dataset demonstrate that InsightX Agent not only achieves a high object detection F1-score of 96.35% but also offers significantly improved interpretability and trustworthiness in its analyses, highlighting the transformative potential of agentic LLM frameworks for industrial inspection tasks.

♻ ☆ Embodied Image Quality Assessment for Robotic Intelligence

Jianbo Zhang, Chunyi Li, Jie Hao, Jun Jia, Huiyu Duan, Guoquan Zheng, Liang Yuan, Guangtao Zhai

Image Quality Assessment (IQA) of User-Generated Content (UGC) is a critical technique for human Quality of Experience (QoE). However, does the the image quality of Robot-Generated Content (RGC) demonstrate traits consistent with the Moravec paradox, potentially conflicting with human perceptual norms? Human subjective scoring is more based on the attractiveness of the image. Embodied agent are required to interact and perceive in the environment, and finally perform specific tasks. Visual images as inputs directly influence downstream tasks. In this paper, we explore the perception mechanism of embodied robots for image quality. We propose the first Embodied Preference Database (EPD), which contains 12,500 distorted image annotations. We establish assessment metrics based on the downstream tasks of robot. In addition, there is a gap between UGC and RGC. To address this, we propose a novel Multi-scale Attention Embodied Image Quality Assessment called MA-EIQA. For the proposed EPD dataset, this is the first no-reference IQA model designed for embodied robot. Finally, the performance of mainstream IQA algorithms on EPD dataset is verified. The experiments demonstrate that quality assessment of embodied images is different from that of humans. We sincerely hope that the EPD can contribute to the development of embodied AI by focusing on image quality assessment. The benchmark is available at https://github.com/Jianbo-maker/EPD_benchmark.

♻ ☆ Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake

Hongrui Zheng, Yuezun Li, Liejun Wang, Yunfeng Diao, Zhiqing Guo

Active defense strategies have been developed to counter the threat of deepfake technology. However, a primary challenge is their lack of persistence, as their effectiveness is often short-lived. Attackers can bypass these defenses by simply collecting protected samples and retraining their models. This means that static defenses inevitably fail when attackers retrain their models, which severely limits practical use. We argue that an effective defense not only distorts forged content but also blocks the model's ability to adapt, which occurs when attackers retrain their models on protected images. To achieve this, we propose an innovative Two-Stage Defense Framework (TSDF). Benefiting from the intensity separation mechanism designed in this paper, the framework uses dual-function adversarial perturbations to perform two roles. First, it can directly distort the forged results. Second, it acts as a poisoning vehicle that disrupts the data preparation process essential for an attacker's retraining pipeline. By poisoning the data source, TSDF aims to prevent the attacker's model from adapting to the defensive perturbations, thus ensuring the defense remains effective long-term. Comprehensive experiments show that the performance of traditional interruption methods degrades sharply when it is subjected to adversarial retraining. However, our framework shows a strong dual defense capability, which can improve the persistence of active defense. Our code will be available at https://github.com/vpsg-research/TSDF.

♻ ☆ Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-order Geometric Primitives

Ziyu Zhang, Binbin Huang, Hanqing Jiang, Liyang Zhou, Xiaojun Xiang, Shunhan Shen

We propose Quadratic Gaussian Splatting (QGS), a novel representation that replaces static primitives with deformable quadric surfaces (e.g., ellipse, paraboloids) to capture intricate geometry. Unlike prior works that rely on Euclidean distance for primitive density modeling--a metric misaligned with surface geometry under deformation--QGS introduces geodesic distance-based density distributions. This innovation ensures that density weights adapt intrinsically to the primitive curvature, preserving consistency during shape changes (e.g., from planar disks to curved paraboloids). By solving geodesic distances in closed form on quadric surfaces, QGS enables surface-aware splatting, where a single primitive can represent complex curvature that previously required dozens of planar surfels, potentially reducing memory usage while maintaining efficient rendering via fast ray-quadric intersection. Experiments on DTU, Tanks and Temples, and MipNeRF360 datasets demonstrate state-of-the-art surface reconstruction, with QGS reducing geometric error (chamfer distance) by 33% over 2DGS and 27% over GOF on the DTU dataset. Crucially, QGS retains competitive appearance quality, bridging the gap between geometric precision and visual fidelity for applications like robotics and immersive reality.

comment: 16pages,18figures

♻ ☆ Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation

Xin Wang, Yin Guo, Jiamin Xia, Kaiyu Zhang, Niranjan Balu, Mahmud Mossa-Basha, Linda Shapiro, Chun Yuan

Most prior unsupervised domain adaptation approaches for medical image segmentation are narrowly tailored to either the source-accessible setting, where adaptation is guided by source-target alignment, or the source-free setting, which typically resorts to implicit supervision mechanisms such as pseudo-labeling and model distillation. This substantial divergence in methodological designs between the two settings reveals an inherent flaw: the lack of an explicit, structured construction of anatomical knowledge that naturally generalizes across domains and settings. To bridge this longstanding divide, we introduce a unified, semantically grounded framework that supports both source-accessible and source-free adaptation. Fundamentally distinct from all prior works, our framework's adaptability emerges naturally as a direct consequence of the model architecture, without the need for any handcrafted adaptation strategies. Specifically, our model learns a domain-agnostic probabilistic manifold as a global space of anatomical regularities, mirroring how humans establish visual understanding. Thus, the structural content in each image can be interpreted as a canonical anatomy retrieved from the manifold and a spatial transformation capturing individual-specific geometry. This disentangled, interpretable formulation enables semantically meaningful prediction with intrinsic adaptability. Extensive experiments on challenging cardiac and abdominal datasets show that our framework achieves state-of-the-art results in both settings, with source-free performance closely approaching its source-accessible counterpart, a level of consistency rarely observed in prior works. Beyond quantitative improvement, we demonstrate strong interpretability of the proposed framework via manifold traversal for smooth shape manipulation.

♻ ☆ Latent Expression Generation for Referring Image Segmentation and Grounding

Seonghoon Yu, Junbeom Hong, Joonseok Lee, Jeany Son

Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual description. The target object in an image can be described in multiple ways, reflecting diverse attributes such as color, position, and more. However, most existing methods rely on a single textual input, which captures only a fraction of the rich information available in the visual domain. This mismatch between rich visual details and sparse textual cues can lead to the misidentification of similar objects. To address this, we propose a novel visual grounding framework that leverages multiple latent expressions generated from a single textual input by incorporating complementary visual details absent from the original description. Specifically, we introduce subject distributor and visual concept injector modules to embed both shared-subject and distinct-attributes concepts into the latent representations, thereby capturing unique and target-specific visual cues. We also propose a positive-margin contrastive learning strategy to align all latent expressions with the original text while preserving subtle variations. Experimental results show that our method not only outperforms state-of-the-art RIS and REC approaches on multiple benchmarks but also achieves outstanding performance on the generalized referring expression segmentation (GRES) benchmark.

comment: Accepted to ICCV 2025

♻ ☆ Vibration-Based Energy Metric for Restoring Needle Alignment in Autonomous Robotic Ultrasound

Zhongyu Chen, Chenyang Li, Xuesong Li, Dianye Huang, Zhongliang Jiang, Stefanie Speidel, Xiangyu Chu, K. W. Samuel Au

Precise needle alignment is essential for percutaneous needle insertion in robotic ultrasound-guided procedures. However, inherent challenges such as speckle noise, needle-like artifacts, and low image resolution make robust needle detection difficult, particularly when visibility is reduced or lost. In this paper, we propose a method to restore needle alignment when the ultrasound imaging plane and the needle insertion plane are misaligned. Unlike many existing approaches that rely heavily on needle visibility in ultrasound images, our method uses a more robust feature by periodically vibrating the needle using a mechanical system. Specifically, we propose a vibration-based energy metric that remains effective even when the needle is fully out of plane. Using this metric, we develop a control strategy to reposition the ultrasound probe in response to misalignments between the imaging plane and the needle insertion plane in both translation and rotation. Experiments conducted on ex-vivo porcine tissue samples using a dual-arm robotic ultrasound-guided needle insertion system demonstrate the effectiveness of the proposed approach. The experimental results show the translational error of 0.41$\pm$0.27 mm and the rotational error of 0.51$\pm$0.19 degrees.

comment: Accepted by IROS2025

♻ ☆ Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models

Eunseo Koh, Seunghoo Hong, Tae-Young Kim, Simon S. Woo, Jae-Pil Heo

Text-to-Image (T2I) diffusion models have made significant progress in generating diverse high-quality images from textual prompts. However, these models still face challenges in suppressing content that is strongly entangled with specific words. For example, when generating an image of "Charlie Chaplin", a "mustache" consistently appears even if explicitly instructed not to include it, as the concept of "mustache" is strongly entangled with "Charlie Chaplin". To address this issue, we propose a novel approach to directly suppress such entangled content within the text embedding space of diffusion models. Our method introduces a delta vector that modifies the text embedding to weaken the influence of undesired content in the generated image, and we further demonstrate that this delta vector can be easily obtained through a zero-shot approach. Furthermore, we propose a Selective Suppression with Delta Vector (SSDV) method to adapt delta vector into the cross-attention mechanism, enabling more effective suppression of unwanted content in regions where it would otherwise be generated. Additionally, we enabled more precise suppression in personalized T2I models by optimizing delta vector, which previous baselines were unable to achieve. Extensive experimental results demonstrate that our approach significantly outperforms existing methods, both in terms of quantitative and qualitative metrics.

♻ ☆ Visual Perception Engine: Fast and Flexible Multi-Head Inference for Robotic Vision Tasks

Jakub Łucki, Jonathan Becktor, Georgios Georgakis, Rob Royce, Shehryar Khattak

Deploying multiple machine learning models on resource-constrained robotic platforms for different perception tasks often results in redundant computations, large memory footprints, and complex integration challenges. In response, this work presents Visual Perception Engine (VPEngine), a modular framework designed to enable efficient GPU usage for visual multitasking while maintaining extensibility and developer accessibility. Our framework architecture leverages a shared foundation model backbone that extracts image representations, which are efficiently shared, without any unnecessary GPU-CPU memory transfers, across multiple specialized task-specific model heads running in parallel. This design eliminates the computational redundancy inherent in feature extraction component when deploying traditional sequential models while enabling dynamic task prioritization based on application demands. We demonstrate our framework's capabilities through an example implementation using DINOv2 as the foundation model with multiple task (depth, object detection and semantic segmentation) heads, achieving up to 3x speedup compared to sequential execution. Building on CUDA Multi-Process Service (MPS), VPEngine offers efficient GPU utilization and maintains a constant memory footprint while allowing per-task inference frequencies to be adjusted dynamically during runtime. The framework is written in Python and is open source with ROS2 C++ (Humble) bindings for ease of use by the robotics community across diverse robotic platforms. Our example implementation demonstrates end-to-end real-time performance at $\geq$50 Hz on NVIDIA Jetson Orin AGX for TensorRT optimized models.

comment: 8 pages, 6 figures, 2 tables

♻ ☆ Re:Verse -- Can Your VLM Read a Manga?

Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, Shruti Vyas

Current Vision Language Models (VLMs) demonstrate a critical gap between surface-level recognition and deep narrative reasoning when processing sequential visual storytelling. Through a comprehensive investigation of manga narrative understanding, we reveal that while recent large multimodal models excel at individual panel interpretation, they systematically fail at temporal causality and cross-panel cohesion, core requirements for coherent story comprehension. We introduce a novel evaluation framework that combines fine-grained multimodal annotation, cross-modal embedding analysis, and retrieval-augmented assessment to systematically characterize these limitations. Our methodology includes (i) a rigorous annotation protocol linking visual elements to narrative structure through aligned light novel text, (ii) comprehensive evaluation across multiple reasoning paradigms, including direct inference and retrieval-augmented generation, and (iii) cross-modal similarity analysis revealing fundamental misalignments in current VLMs' joint representations. Applying this framework to Re:Zero manga across 11 chapters with 308 annotated panels, we conduct the first systematic study of long-form narrative understanding in VLMs through three core evaluation axes: generative storytelling, contextual dialogue grounding, and temporal reasoning. Our findings demonstrate that current models lack genuine story-level intelligence, struggling particularly with non-linear narratives, character consistency, and causal inference across extended sequences. This work establishes both the foundation and practical methodology for evaluating narrative intelligence, while providing actionable insights into the capability of deep sequential understanding of Discrete Visual Narratives beyond basic recognition in Multimodal Models. Project Page: https://re-verse.vercel.app

comment: Accepted (oral) at ICCV (AISTORY Workshop) 2025

♻ ☆ RMMSS: Towards Advanced Robust Multi-Modal Semantic Segmentation with Hybrid Prototype Distillation and Feature Selection

Jiaqi Tan, Xu Zheng, Yang Liu

Multi-modal semantic segmentation (MMSS) faces significant challenges in real-world applications due to incomplete, degraded, or missing sensor data. While current MMSS methods typically use self-distillation with modality dropout to improve robustness, they largely overlook inter-modal correlations and thus suffer significant performance degradation when no modalities are missing. To this end, we present RMMSS, a two-stage framework designed to progressively enhance model robustness under missing-modality conditions, while maintaining strong performance in full-modality scenarios. It comprises two key components: the Hybrid Prototype Distillation Module (HPDM) and the Feature Selection Module (FSM). In the first stage, we pre-train the teacher model with full-modality data and then introduce HPDM to do cross-modal knowledge distillation for obtaining a highly robust model. In the second stage, we freeze both the pre-trained full-modality teacher model and the robust model and propose a trainable FSM that extracts optimal representations from both the feature and logits layers of the models via feature score calculation. This process learns a final student model that maintains strong robustness while achieving high performance under full-modality conditions. Our experiments on three datasets demonstrate that our method improves missing-modality performance by 2.80%, 3.89%, and 0.89%, respectively, compared to the state-of-the-art, while causing almost no drop in full-modality performance (only -0.1% mIoU). Meanwhile, different backbones (AnySeg and CMNeXt) are utilized to validate the generalizability of our framework.

♻ ☆ MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow Estimation

Juntian Du, Zhihu Zhou, Runzhe Zhang, Yuan Sun, Pinyi Chen, Keji Mao

Recently, the Mamba architecture has demonstrated significant successes in various computer vision tasks, such as classification and segmentation. However, its application to optical flow estimation remains unexplored. In this paper, we introduce MambaFlow, a novel framework designed to leverage the high accuracy and efficiency of the Mamba architecture for capturing locally correlated features while preserving global information in end-to-end optical flow estimation. To our knowledge, MambaFlow is the first architecture centered around the Mamba design tailored specifically for optical flow estimation. It comprises two key components: (1) PolyMamba, which enhances feature representation through a dual-Mamba architecture, incorporating a Self-Mamba module for intra-token modeling and a Cross-Mamba module for inter-modality interaction, enabling both deep contextualization and effective feature fusion; and (2) PulseMamba, which leverages an Attention Guidance Aggregator (AGA) to adaptively integrate features with dynamically learned weights in contrast to naive concatenation, and then employs the intrinsic recurrent mechanism of Mamba to perform autoregressive flow decoding, facilitating efficient flow information dissemination. Extensive experiments demonstrate that MambaFlow achieves remarkable results comparable to mainstream methods on benchmark datasets. Compared to SEA-RAFT, MambaFlow attains higher accuracy on the Sintel benchmark, demonstrating stronger potential for real-world deployment on resource-constrained devices. The source code will be made publicly available upon acceptance of the paper.

♻ ☆ MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Images

JongWoo Kim, Bryan Wong, Huazhu Fu, Willmer Rafell Quiñones, Young Sin Ko, MunYong Yi

Cancer diagnosis has greatly benefited from the integration of whole-slide images (WSIs) with multiple instance learning (MIL), enabling high-resolution analysis of tissue morphology. Graph-based MIL (GNN-MIL) approaches have emerged as powerful solutions for capturing contextual information in WSIs, thereby improving diagnostic accuracy. However, WSIs require significant computational and infrastructural resources, limiting accessibility in resource-constrained settings. Conventional light microscopes offer a cost-effective alternative, but applying GNN-MIL to such data is challenging due to extensive redundant images and missing spatial coordinates, which hinder contextual learning. To address these issues, we introduce MicroMIL, the first weakly-supervised MIL framework specifically designed for images acquired from conventional light microscopes. MicroMIL leverages a representative image extractor (RIE) that employs deep cluster embedding (DCE) and hard Gumbel-Softmax to dynamically reduce redundancy and select representative images. These images serve as graph nodes, with edges computed via cosine similarity, eliminating the need for spatial coordinates while preserving contextual information. Extensive experiments on a real-world colon cancer dataset and the BreakHis dataset demonstrate that MicroMIL achieves state-of-the-art performance, improving both diagnostic accuracy and robustness to redundancy. The code is available at https://github.com/kimjongwoo-cell/MicroMIL

comment: Accepted at MICCAI 2025

♻ ☆ TimeMachine: Fine-Grained Facial Age Editing with Identity Preservation

Yilin Mi, Qixin Yan, Zheng-Peng Duan, Chunle Guo, Hubery Yin, Hao Liu, Chen Li, Chongyi Li

With the advancement of generative models, facial image editing has made significant progress. However, achieving fine-grained age editing while preserving personal identity remains a challenging task. In this paper, we propose TimeMachine, a novel diffusion-based framework that achieves accurate age editing while keeping identity features unchanged. To enable fine-grained age editing, we inject high-precision age information into the multi-cross attention module, which explicitly separates age-related and identity-related features. This design facilitates more accurate disentanglement of age attributes, thereby allowing precise and controllable manipulation of facial aging. Furthermore, we propose an Age Classifier Guidance (ACG) module that predicts age directly in the latent space, instead of performing denoising image reconstruction during training. By employing a lightweight module to incorporate age constraints, this design enhances age editing accuracy by modest increasing training cost. Additionally, to address the lack of large-scale, high-quality facial age datasets, we construct a HFFA dataset (High-quality Fine-grained Facial-Age dataset) which contains one million high-resolution images labeled with identity and facial attributes. Experimental results demonstrate that TimeMachine achieves state-of-the-art performance in fine-grained age editing while preserving identity consistency.

♻ ☆ HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model

Qi Liu, Yabei Li, Hongsong Wang, Lei He

Traditional closed-set 3D detection frameworks fail to meet the demands of open-world applications like autonomous driving. Existing open-vocabulary 3D detection methods typically adopt a two-stage pipeline consisting of pseudo-label generation followed by semantic alignment. While vision-language models (VLMs) recently have dramatically improved the semantic accuracy of pseudo-labels, their geometric quality, particularly bounding box precision, remains commonly neglected. To address this issue, we propose a High Box Quality Open-Vocabulary 3D Detection (HQ-OV3D) framework, dedicated to generate and refine high-quality pseudo-labels for open-vocabulary classes. The framework comprises two key components: an Intra-Modality Cross-Validated (IMCV) Proposal Generator that utilizes cross-modality geometric consistency to generate high-quality initial 3D proposals, and an Annotated-Class Assisted (ACA) Denoiser that progressively refines 3D proposals by leveraging geometric priors from annotated categories through a DDIM-based denoising mechanism. Compared to the state-of-the-art method, training with pseudo-labels generated by our approach achieves a 7.37% improvement in mAP on novel classes, demonstrating the superior quality of the pseudo-labels produced by our framework. HQ-OV3D can serve not only as a strong standalone open-vocabulary 3D detector but also as a plug-in high-quality pseudo-label generator for existing open-vocabulary detection or annotation pipelines.

♻ ☆ Privacy-Preserving Driver Drowsiness Detection with Spatial Self-Attention and Federated Learning

Tran Viet Khoa, Do Hai Son, Mohammad Abu Alsheikh, Yibeltal F Alem, Dinh Thai Hoang

Driver drowsiness is one of the main causes of road accidents and is recognized as a leading contributor to traffic-related fatalities. However, detecting drowsiness accurately remains a challenging task, especially in real-world settings where facial data from different individuals is decentralized and highly diverse. In this paper, we propose a novel framework for drowsiness detection that is designed to work effectively with heterogeneous and decentralized data. Our approach develops a new Spatial Self-Attention (SSA) mechanism integrated with a Long Short-Term Memory (LSTM) network to better extract key facial features and improve detection performance. To support federated learning, we employ a Gradient Similarity Comparison (GSC) that selects the most relevant trained models from different operators before aggregation. This improves the accuracy and robustness of the global model while preserving user privacy. We also develop a customized tool that automatically processes video data by extracting frames, detecting and cropping faces, and applying data augmentation techniques such as rotation, flipping, brightness adjustment, and zooming. Experimental results show that our framework achieves a detection accuracy of 89.9% in the federated learning settings, outperforming existing methods under various deployment scenarios. The results demonstrate the effectiveness of our approach in handling real-world data variability and highlight its potential for deployment in intelligent transportation systems to enhance road safety through early and reliable drowsiness detection.

♻ ☆ Attention to the Burstiness in Visual Prompt Tuning!

Yuzhu Wang, Manni Duan, Shu Kong

Visual Prompt Tuning (VPT) is a parameter-efficient fune-tuning technique that adapts a pre-trained vision Transformer (ViT) by learning a small set of parameters in the input space, known as prompts. In VPT, we uncover ``burstiness'' in the values arising from the interaction of image patch embeddings, and the key and query projectors within Transformer's self-attention module. Furthermore, the values of patch embeddings and the key and query projectors exhibit Laplacian and hyper-Laplacian distribution, respectively. Intuitively, these non-Gaussian distributions pose challenges for learning prompts. To address this, we propose whitening these data, de-correlating them and equalizing their variance towards more Gaussian before learning prompts. We derive the whitening matrix over random image patch embeddings and ViT's key and query projectors, and multiply it with the prompt to be learned in a bilinear manner. Surprisingly, this method significantly accelerates prompt tuning and boosts accuracy, e.g., $>$25 accuracy points on the CUB dataset; interestingly, it learns ``bursty prompts''. Extending the bilinear model which is known to introduce burstiness, we present a compact, low-rank version by learning two smaller matrices whose multiplication yields the final prompts. We call the proposed methods Bilinear Prompt Tuning (BPT). Extensive experiments across multiple benchmark datasets demonstrate that BPT methods not only outperform various VPT methods but also reduce parameter count and computation overhead.

comment: ICCV 2025; v2: camera ready

♻ ☆ AFR-CLIP: Enhancing Zero-Shot Industrial Anomaly Detection with Stateless-to-Stateful Anomaly Feature Rectification

Jingyi Yuan, Chenqiang Gao, Pengyu Jie, Xuan Xia, Shangri Huang, Wanquan Liu

Recently, zero-shot anomaly detection (ZSAD) has emerged as a pivotal paradigm for industrial inspection and medical diagnostics, detecting defects in novel objects without requiring any target-dataset samples during training. Existing CLIP-based ZSAD methods generate anomaly maps by measuring the cosine similarity between visual and textual features. However, CLIP's alignment with object categories instead of their anomalous states limits its effectiveness for anomaly detection. To address this limitation, we propose AFR-CLIP, a CLIP-based anomaly feature rectification framework. AFR-CLIP first performs image-guided textual rectification, embedding the implicit defect information from the image into a stateless prompt that describes the object category without indicating any anomalous state. The enriched textual embeddings are then compared with two pre-defined stateful (normal or abnormal) embeddings, and their text-on-text similarity yields the anomaly map that highlights defective regions. To further enhance perception to multi-scale features and complex anomalies, we introduce self prompting (SP) and multi-patch feature aggregation (MPFA) modules. Extensive experiments are conducted on eleven anomaly detection benchmarks across industrial and medical domains, demonstrating AFR-CLIP's superiority in ZSAD.

comment: There was some citation error in the last version. So please read the 3rd version

♻ ☆ Towards Consumer-Grade Cybersickness Prediction: Multi-Model Alignment for Real-Time Vision-Only Inference

Yitong Zhu, Zhuowen Liang, Yiming Wu, Tangyao Li, Yuyang Wang

Cybersickness remains a major obstacle to the widespread adoption of immersive virtual reality (VR), particularly in consumer-grade environments. While prior methods rely on invasive signals such as electroencephalography (EEG) for high predictive accuracy, these approaches require specialized hardware and are impractical for real-world applications. In this work, we propose a scalable, deployable framework for personalized cybersickness prediction leveraging only non-invasive signals readily available from commercial VR headsets, including head motion, eye tracking, and physiological responses. Our model employs a modality-specific graph neural network enhanced with a Difference Attention Module to extract temporal-spatial embeddings capturing dynamic changes across modalities. A cross-modal alignment module jointly trains the video encoder to learn personalized traits by aligning video features with sensor-derived representations. Consequently, the model accurately predicts individual cybersickness using only video input during inference. Experimental results show our model achieves 88.4\% accuracy, closely matching EEG-based approaches (89.16\%), while reducing deployment complexity. With an average inference latency of 90ms, our framework supports real-time applications, ideal for integration into consumer-grade VR platforms without compromising personalization or performance. The code will be relesed at https://github.com/U235-Aurora/PTGNN.

♻ ☆ VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip

Wenqi Guo, Shan Du

We introduce Value Sign Flip (VSF), a simple and efficient method for incorporating negative prompt guidance in few-step diffusion and flow-matching image generation models. Unlike existing approaches such as classifier-free guidance (CFG), NASA, and NAG, VSF dynamically suppresses undesired content by flipping the sign of attention values from negative prompts. Our method requires only small computational overhead and integrates effectively with MMDiT-style architectures such as Stable Diffusion 3.5 Turbo, as well as cross-attention-based models like Wan. We validate VSF on challenging datasets with complex prompt pairs and demonstrate superior performance in both static image and video generation tasks. Experimental results show that VSF significantly improves negative prompt adherence compared to prior methods in few-step models, and even CFG in non-few-step models, while maintaining competitive image quality. Code and ComfyUI node are available in https://github.com/weathon/VSF/tree/main.

2025-08-17

Sound 10

☆ CEM-Net: Cross-Emotion Memory Network for Emotional Talking Face Generation

Kangyi Wu, Pengna Li, Jingwen Fu, Yang Wu, Yuhan Liu, Sanping Zhou, Jinjun Wang

Emotional talking face generation aims to animate a human face in given reference images and generate a talking video that matches the content and emotion of driving audio. However, existing methods neglect that reference images may have a strong emotion that conflicts with the audio emotion, leading to severe emotion inaccuracy and distorted generated results. To tackle the issue, we introduce a cross-emotion memory network(CEM-Net), designed to generate emotional talking faces aligned with the driving audio when reference images exhibit strong emotion. Specifically, an Audio Emotion Enhancement module(AEE) is first devised with the cross-reconstruction training strategy to enhance audio emotion, overcoming the disruption from reference image emotion. Secondly, since reference images cannot provide sufficient facial motion information of the speaker under audio emotion, an Emotion Bridging Memory module(EBM) is utilized to compensate for the lacked information. It brings in expression displacement from the reference image emotion to the audio emotion and stores it in the memory.Given a cross-emotion feature as a query, the matching displacement can be retrieved at inference time. Extensive experiments have demonstrated that our CEM-Net can synthesize expressive, natural and lip-synced talking face videos with better emotion accuracy.

☆ Cross-Modal Knowledge Distillation with Multi-Level Data Augmentation for Low-Resource Audio-Visual Sound Event Localization and Detection

Qing Wang, Ya Jiang, Hang Chen, Sabato Marco Siniscalchi, Jun Du, Jianqing Gao

This work presents a cross-modal knowledge distillation (CMKD) framework combined with multi-level data augmentation for low-resource audio-visual (AV) sound event localization and detection (SELD). An audio-only SELD model acts as the teacher, transferring knowledge to an AV student model through both output responses and intermediate feature representations. To enhance learning, data augmentation is applied by mixing features randomly selected from multiple network layers and associated loss functions tailored to the SELD task. Extensive experiments on the DCASE 2023 and 2024 SELD datasets show that the proposed method significantly improves AV SELD performance, yielding relative gains of 22%~36% in the overall metric over the baseline. Notably, our approach achieves results comparable to or better than teacher models trained on much larger datasets, surpassing state-of-the-art methods on both DCASE 2023 and 2024 SELD tasks.

comment: 34 pages, 7 figures

☆ CarelessWhisper: Turning Whisper into a Causal Streaming Model

Tomer Krichli, Bhiksha Raj, Joseph Keshet

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming (online or real-time) transcription, due to limitations in their architecture and training methodology. We propose a method to turn the transformer encoder-decoder model into a low-latency streaming model that is careless about future context. We present an analysis explaining why it is not straightforward to convert an encoder-decoder transformer to a low-latency streaming model. Our proposed method modifies the existing (non-causal) encoder to a causal encoder by fine-tuning both the encoder and decoder using Low-Rank Adaptation (LoRA) and a weakly aligned dataset. We then propose an updated inference mechanism that utilizes the fine-tune causal encoder and decoder to yield greedy and beam-search decoding, and is shown to be locally optimal. Experiments on low-latency chunk sizes (less than 300 msec) show that our fine-tuned model outperforms existing non-fine-tuned streaming approaches in most cases, while using a lower complexity. Additionally, we observe that our training process yields better alignment, enabling a simple method for extracting word-level timestamps. We release our training and inference code, along with the fine-tuned models, to support further research and development in streaming ASR.

comment: 17 pages, 7 Figures, This work has been submitted to the IEEE for possible publication

☆ HuBERT-VIC: Improving Noise-Robust Automatic Speech Recognition of Speech Foundation Model via Variance-Invariance-Covariance Regularization

Hyebin Ahn, Kangwook Jang, Hoirin Kim

Noise robustness in speech foundation models (SFMs) has been a critical challenge, as most models are primarily trained on clean data and experience performance degradation when the models are exposed to noisy speech. To address this issue, we propose HuBERT-VIC, a noise-robust SFM with variance, in-variance, and covariance regularization (VICReg) objectives. These objectives adjust the statistics of noisy speech representations, enabling the model to capture diverse acoustic characteristics and improving the generalization ability across different types of noise. When applied to HuBERT, our model shows relative performance improvements of 23.3% on LibriSpeech test-clean and 13.2% on test-other, compared to the baseline model pre-trained on noisy speech.

comment: Accepted at Interspeech 2025

☆ Exploring Self-Supervised Audio Models for Generalized Anomalous Sound Detection

Bing Han, Anbai Jiang, Xinhu Zheng, Wei-Qiang Zhang, Jia Liu, Pingyi Fan, Yanmin Qian

Machine anomalous sound detection (ASD) is a valuable technique across various applications. However, its generalization performance is often limited due to challenges in data collection and the complexity of acoustic environments. Inspired by the success of large pre-trained models in numerous fields, this paper introduces a robust ASD model that leverages self-supervised pre-trained models trained on large-scale speech and audio datasets. Although there are inconsistencies between the pre-training datasets and the ASD task, our findings indicate that pre-training still provides substantial benefits for ASD. To mitigate overfitting and retain learned knowledge when fine-tuning with limited data, we explore Fully-Connected Low-Rank Adaptation (LoRA) as an alternative to full fine-tuning. Additionally, we propose a Machine-aware Group Adapter module, which enables the model to capture differences between various machines within a unified framework, thereby enhancing the generalization performance of ASD systems. To address the challenge of missing attribute labels, we design a novel objective function that dynamically clusters unattributed data using vector quantization and optimizes through a dual-level contrastive learning loss. The proposed methods are evaluated on all benchmark datasets, including the DCASE 2020-2024 five ASD challenges, and the experimental results show significant improvements of our new approach and demonstrate the effectiveness of our proposed strategies.

comment: Accepted by TASLP. 15 pages, 7 figures;

♻ ☆ Fast Algorithm for Moving Sound Source

Dong Yang

Modern neural network-based speech processing systems usually need to have reverberation resistance, so the training of such systems requires a large amount of reverberation data. In the process of system training, it is now more inclined to use sampling static systems to simulate dynamic systems, or to supplement data through actually recorded data. However, this cannot fundamentally solve the problem of simulating motion data that conforms to physical laws. Aiming at the core issue of insufficient training data for speech enhancement models in moving scenarios, this paper proposes Yang's motion spatio-temporal sampling reconstruction theory to realize efficient simulation of motion continuous time-varying reverberation. This theory breaks through the limitations of the traditional static Image-Source Method (ISM) in time-varying systems. By decomposing the impulse response of the moving image source into two parts: linear time-invariant modulation and discrete time-varying fractional delay, a moving sound field model conforming to physical laws is established. Based on the band-limited characteristics of motion displacement, a hierarchical sampling strategy is proposed: high sampling rate is used for low-order images to retain details, and low sampling rate is used for high-order images to reduce computational complexity. A fast synthesis architecture is designed to realize real-time simulation. Experiments show that compared with the open-source models, the proposed theory can more accurately restore the amplitude and phase changes in moving scenarios, solving the industry problem of motion sound source data simulation, and providing high-quality dynamic training data for speech enhancement models.

♻ ☆ Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis

Anna Seo Gyeong Choi, Alexander Richardson, Ryan Partlan, Sunny Tang, Sunghye Cho

This study compares three acoustic feature extraction toolkits (OpenSMILE, Praat, and Librosa) applied to clinical speech data from individuals with schizophrenia spectrum disorders (SSD) and healthy controls (HC). By standardizing extraction parameters across the toolkits, we analyzed speech samples from 77 SSD and 87 HC participants and found significant toolkit-dependent variations. While F0 percentiles showed high cross-toolkit correlation (r=0.962 to 0.999), measures like F0 standard deviation and formant values often had poor, even negative, agreement. Additionally, correlation patterns differed between SSD and HC groups. Classification analysis identified F0 mean, HNR, and MFCC1 (AUC greater than 0.70) as promising discriminators. These findings underscore reproducibility concerns and advocate for standardized protocols, multi-toolkit cross-validation, and transparent reporting.

comment: Accepted to Interspeech 2025

♻ ☆ DiffVox: A Differentiable Model for Capturing and Analysing Vocal Effects Distributions

Chin-Yun Yu, Marco A. Martínez-Ramírez, Junghyun Koo, Ben Hayes, Wei-Hsiang Liao, György Fazekas, Yuki Mitsufuji

This study introduces a novel and interpretable model, DiffVox, for matching vocal effects in music production. DiffVox, short for ``Differentiable Vocal Fx", integrates parametric equalisation, dynamic range control, delay, and reverb with efficient differentiable implementations to enable gradient-based optimisation for parameter estimation. Vocal presets are retrieved from two datasets, comprising 70 tracks from MedleyDB and 365 tracks from a private collection. Analysis of parameter correlations reveals strong relationships between effects and parameters, such as the high-pass and low-shelf filters often working together to shape the low end, and the delay time correlating with the intensity of the delayed signals. Principal component analysis reveals connections to McAdams' timbre dimensions, where the most crucial component modulates the perceived spaciousness while the secondary components influence spectral brightness. Statistical testing confirms the non-Gaussian nature of the parameter distribution, highlighting the complexity of the vocal effects space. These initial findings on the parameter distributions set the foundation for future research in vocal effects modelling and automatic mixing. Our source code and datasets are accessible at https://github.com/SonyResearch/diffvox.

comment: Accepted at DAFx 2025

♻ ☆ Radif Corpus: A Symbolic Dataset for Non-Metric Iranian Classical Music

Maziar Kanani, Sean O Leary, James McDermott

Non-metric music forms the core of the repertoire in Iranian classical music. Dastgahi music serves as the underlying theoretical system for both Iranian art music and certain folk traditions. At the heart of Iranian classical music lies the radif, a foundational repertoire that organizes melodic material central to performance and pedagogy. In this study, we introduce a digital corpus representing the complete non-metrical radif repertoire, covering all 13 existing components of this repertoire. We provide MIDI files (about 281 minutes in total) and data spreadsheets describing notes, note durations, intervals, and hierarchical structures for 228 pieces of music. We faithfully represent the tonality including quarter-tones, and the non-metric aspect. Furthermore, we provide supporting basic statistics, and measures of complexity and similarity over the corpus. Our corpus provides a platform for computational studies of Iranian classical music. Researchers might employ it in studying melodic patterns, investigating improvisational styles, or for other tasks in music information retrieval, music theory, and computational (ethno)musicology.

♻ ☆ Adaptive Noise Resilient Keyword Spotting Using One-Shot Learning

Luciano Sebastian Martinez-Rau, Quynh Nguyen Phuong Vu, Yuxuan Zhang, Bengt Oelmann, Sebastian Bader

Keyword spotting (KWS) is a key component of smart devices, enabling efficient and intuitive audio interaction. However, standard KWS systems deployed on embedded devices often suffer performance degradation under real-world operating conditions. Resilient KWS systems address this issue by enabling dynamic adaptation, with applications such as adding or replacing keywords, adjusting to specific users, and improving noise robustness. However, deploying resilient, standalone KWS systems with low latency on resource-constrained devices remains challenging due to limited memory and computational resources. This study proposes a low computational approach for continuous noise adaptation of pretrained neural networks used for KWS classification, requiring only 1-shot learning and one epoch. The proposed method was assessed using two pretrained models and three real-world noise sources at signal-to-noise ratios (SNRs) ranging from 24 to -3 dB. The adapted models consistently outperformed the pretrained models across all scenarios, especially at SNR $\leq$ 18 dB, achieving accuracy improvements of 4.9% to 46.0%. These results highlight the efficacy of the proposed methodology while being lightweight enough for deployment on resource-constrained devices.

comment: Preprint submitted to the IEEE 11th World Forum on Internet of Things

Audio and Speech Processing 12

☆ On the Extension of Differential Beamforming Theory to Arbitrary Planar Arrays of First-Order Elements

Federico Miotello, Davide Albertini, Alberto Bernardini

Small-size acoustic arrays exploit spatial diversity to achieve capabilities beyond those of single-element devices, with applications ranging from teleconferencing to immersive multimedia. A key requirement for broadband array processing is a frequency-invariant spatial response, which ensures consistent directivity across wide bandwidths and prevents spectral coloration. Differential beamforming offers an inherently frequency-invariant solution by leveraging pressure differences between closely spaced elements of small-size arrays. Traditional approaches, however, assume the array elements to be omnidirectional, whereas real transducers exhibit frequency-dependent directivity that can degrade performance if not properly modeled. To address this limitation, we propose a generalized modal matching framework for frequency-invariant differential beamforming, applicable to unconstrained planar arrays of first-order directional elements. By representing the desired beampattern as a truncated circular harmonic expansion and fitting it to the actual element responses, our method accommodates arbitrary planar geometries and element orientations. This approach enables the synthesis of beampatterns of any order and steering direction without imposing rigid layout requirements. Simulations confirm that accounting for sensor directivity at the design stage yields accurate and robust performance across varying frequencies, geometries, and noise conditions.

☆ CarelessWhisper: Turning Whisper into a Causal Streaming Model

Tomer Krichli, Bhiksha Raj, Joseph Keshet

comment: 17 pages, 7 Figures, This work has been submitted to the IEEE for possible publication

☆ HuBERT-VIC: Improving Noise-Robust Automatic Speech Recognition of Speech Foundation Model via Variance-Invariance-Covariance Regularization

Hyebin Ahn, Kangwook Jang, Hoirin Kim

comment: Accepted at Interspeech 2025

☆ What do Speech Foundation Models Learn? Analysis and Applications

Ankita Pasad

Speech foundation models (SFMs) are designed to serve as general-purpose representations for a wide range of speech-processing tasks. The last five years have seen an influx of increasingly successful self-supervised and supervised pre-trained models with impressive performance on various downstream tasks. Although the zoo of SFMs continues to grow, our understanding of the knowledge they acquire lags behind. This thesis presents a lightweight analysis framework using statistical tools and training-free tasks to investigate the acoustic and linguistic knowledge encoded in SFM layers. We conduct a comparative study across multiple SFMs and statistical tools. Our study also shows that the analytical insights have concrete implications for downstream task performance. The effectiveness of an SFM is ultimately determined by its performance on speech applications. Yet it remains unclear whether the benefits extend to spoken language understanding (SLU) tasks that require a deeper understanding than widely studied ones, such as speech recognition. The limited exploration of SLU is primarily due to a lack of relevant datasets. To alleviate that, this thesis contributes tasks, specifically spoken named entity recognition (NER) and named entity localization (NEL), to the Spoken Language Understanding Evaluation benchmark. We develop SFM-based approaches for NER and NEL, and find that end-to-end (E2E) models leveraging SFMs can surpass traditional cascaded (speech recognition followed by a text model) approaches. Further, we evaluate E2E SLU models across SFMs and adaptation strategies to assess the impact on task performance. Collectively, this thesis tackles previously unanswered questions about SFMs, providing tools and datasets to further our understanding and to enable the community to make informed design choices for future model development and adoption.

comment: Ph.D. Thesis

☆ Exploring Self-Supervised Audio Models for Generalized Anomalous Sound Detection

Bing Han, Anbai Jiang, Xinhu Zheng, Wei-Qiang Zhang, Jia Liu, Pingyi Fan, Yanmin Qian

comment: Accepted by TASLP. 15 pages, 7 figures;

♻ ☆ Multi-agent Auditory Scene Analysis

Caleb Rascon, Luis Gato-Diaz, Eduardo García-Alarcón

Auditory scene analysis (ASA) aims to retrieve information from the acoustic environment, by carrying out three main tasks: sound source location, separation, and classification. These tasks are traditionally executed with a linear data flow, where the sound sources are first located; then, using their location, each source is separated into its own audio stream; from each of which, information is extracted that is relevant to the application scenario (audio event detection, speaker identification, emotion classification, etc.). However, running these tasks linearly increases the overall response time, while making the last tasks (separation and classification) highly sensitive to errors of the first task (location). A considerable amount of effort and computational complexity has been employed in the state-of-the-art to develop techniques that are the least error-prone possible. However, doing so gives rise to an ASA system that is non-viable in many applications that require a small computational footprint and a low response time, such as bioacoustics, hearing-aid design, search and rescue, human-robot interaction, etc. To this effect, in this work, a multi-agent approach is proposed to carry out ASA where the tasks are run in parallel, with feedback loops between them to compensate for local errors, such as: using the quality of the separation output to correct the location error; and using the classification result to reduce the localization's sensitivity towards interferences. The result is a multi-agent auditory scene analysis (MASA) system that is robust against local errors, without a considerable increase in complexity, and with a low response time. The complete proposed MASA system is provided as a framework that uses open-source tools for sound acquisition and reproduction (JACK) and inter-agent communication (ROS2), allowing users to add their own agents.

comment: Submitted to Applied Soft Computing

♻ ☆ Fast Algorithm for Moving Sound Source

Dong Yang

♻ ☆ Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis

Anna Seo Gyeong Choi, Alexander Richardson, Ryan Partlan, Sunny Tang, Sunghye Cho

comment: Accepted to Interspeech 2025

♻ ☆ DiffVox: A Differentiable Model for Capturing and Analysing Vocal Effects Distributions

Chin-Yun Yu, Marco A. Martínez-Ramírez, Junghyun Koo, Ben Hayes, Wei-Hsiang Liao, György Fazekas, Yuki Mitsufuji

comment: Accepted at DAFx 2025

♻ ☆ Radif Corpus: A Symbolic Dataset for Non-Metric Iranian Classical Music

Maziar Kanani, Sean O Leary, James McDermott

♻ ☆ Adaptive Noise Resilient Keyword Spotting Using One-Shot Learning

Luciano Sebastian Martinez-Rau, Quynh Nguyen Phuong Vu, Yuxuan Zhang, Bengt Oelmann, Sebastian Bader

comment: Preprint submitted to the IEEE 11th World Forum on Internet of Things

♻ ☆ Predicting speech intelligibility in older adults for speech enhancement using the Gammachirp Envelope Similarity Index, GESI

Ayako Yamamoto, Fuki Miyazaki, Toshio Irino

We propose an objective intelligibility measure (OIM), called the Gammachirp Envelope Similarity Index (GESI), that can predict speech intelligibility (SI) in older adults. GESI is a bottom-up model based on psychoacoustic knowledge from the peripheral to the central auditory system. It computes the single SI metric using the gammachirp filterbank (GCFB), the modulation filterbank, and the extended cosine similarity measure. It takes into account not only the hearing level represented in the audiogram, but also the temporal processing characteristics captured by the temporal modulation transfer function (TMTF). To evaluate performance, SI experiments were conducted with older adults of various hearing levels using speech-in-noise with ideal speech enhancement on familiarity-controlled Japanese words. The prediction performance was compared with HASPIw2, which was developed for keyword SI prediction. The results showed that GESI predicted the subjective SI scores more accurately than HASPIw2. GESI was also found to be at least as effective as, if not more effective than, HASPIv2 in predicting English sentence-level SI. The effect of introducing TMTF into the GESI algorithm was insignificant, suggesting that TMTF measurements and models are not yet mature. Therefore, it may be necessary to perform TMTF measurements with bandpass noise and to improve the incorporation of temporal characteristics into the model.

comment: This is a revised manuscript that was submitted to Speech Communication on August 15, 2025

Computer Vision and Pattern Recognition 7

☆ Toward Architecture-Agnostic Local Control of Posterior Collapse in VAEs

Hyunsoo Song, Seungwhan Kim, Seungkyu Lee

Variational autoencoders (VAEs), one of the most widely used generative models, are known to suffer from posterior collapse, a phenomenon that reduces the diversity of generated samples. To avoid posterior collapse, many prior works have tried to control the influence of regularization loss. However, the trade-off between reconstruction and regularization is not satisfactory. For this reason, several methods have been proposed to guarantee latent identifiability, which is the key to avoiding posterior collapse. However, they require structural constraints on the network architecture. For further clarification, we define local posterior collapse to reflect the importance of individual sample points in the data space and to relax the network constraint. Then, we propose Latent Reconstruction(LR) loss, which is inspired by mathematical properties of injective and composite functions, to control posterior collapse without restriction to a specific architecture. We experimentally evaluate our approach, which controls posterior collapse on varied datasets such as MNIST, fashionMNIST, Omniglot, CelebA, and FFHQ.

comment: 8 pages, 6 figures

☆ MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training

Muhammad Osama Zeeshan, Natacha Gillet, Alessandro Lameiras Koerich, Marco Pedersoli, Francois Bremond, Eric Granger

Personalized expression recognition (ER) involves adapting a machine learning model to subject-specific data for improved recognition of expressions with considerable interpersonal variability. Subject-specific ER can benefit significantly from multi-source domain adaptation (MSDA) methods, where each domain corresponds to a specific subject, to improve model accuracy and robustness. Despite promising results, state-of-the-art MSDA approaches often overlook multimodal information or blend sources into a single domain, limiting subject diversity and failing to explicitly capture unique subject-specific characteristics. To address these limitations, we introduce MuSACo, a multi-modal subject-specific selection and adaptation method for ER based on co-training. It leverages complementary information across multiple modalities and multiple source domains for subject-specific adaptation. This makes MuSACo particularly relevant for affective computing applications in digital health, such as patient-specific assessment for stress or pain, where subject-level nuances are crucial. MuSACo selects source subjects relevant to the target and generates pseudo-labels using the dominant modality for class-aware learning, in conjunction with a class-agnostic loss to learn from less confident target samples. Finally, source features from each modality are aligned, while only confident target features are combined. Our experimental results on challenging multimodal ER datasets: BioVid and StressID, show that MuSACo can outperform UDA (blending) and state-of-the-art MSDA methods.

☆ An Initial Study of Bird's-Eye View Generation for Autonomous Vehicles using Cross-View Transformers

Felipe Carlos dos Santos, Eric Aislan Antonelo, Gustavo Claudio Karl Couto

Bird's-Eye View (BEV) maps provide a structured, top-down abstraction that is crucial for autonomous-driving perception. In this work, we employ Cross-View Transformers (CVT) for learning to map camera images to three BEV's channels - road, lane markings, and planned trajectory - using a realistic simulator for urban driving. Our study examines generalization to unseen towns, the effect of different camera layouts, and two loss formulations (focal and L1). Using training data from only a town, a four-camera CVT trained with the L1 loss delivers the most robust test performance, evaluated in a new town. Overall, our results underscore CVT's promise for mapping camera inputs to reasonably accurate BEV maps.

comment: 12 pages,submitted in ENIAC 2025

☆ LangVision-LoRA-NAS: Neural Architecture Search for Variable LoRA Rank in Vision Language Models

Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath

Vision Language Models (VLMs) integrate visual and text modalities to enable multimodal understanding and generation. These models typically combine a Vision Transformer (ViT) as an image encoder and a Large Language Model (LLM) for text generation. LoRA (Low-Rank Adaptation) is an efficient fine-tuning method to adapt pre-trained models to new tasks by introducing low-rank updates to their weights. While LoRA has emerged as a powerful technique for fine-tuning large models by introducing low-rank updates, current implementations assume a fixed rank, potentially limiting flexibility and efficiency across diverse tasks. This paper introduces \textit{LangVision-LoRA-NAS}, a novel framework that integrates Neural Architecture Search (NAS) with LoRA to optimize VLMs for variable-rank adaptation. Our approach leverages NAS to dynamically search for the optimal LoRA rank configuration tailored to specific multimodal tasks, balancing performance and computational efficiency. Through extensive experiments using the LLaMA-3.2-11B model on several datasets, LangVision-LoRA-NAS demonstrates notable improvement in model performance while reducing fine-tuning costs. Our Base and searched fine-tuned models on LLaMA-3.2-11B-Vision-Instruct can be found \href{https://huggingface.co/collections/krishnateja95/llama-32-11b-vision-instruct-langvision-lora-nas-6786cac480357a6a6fcc59ee}{\textcolor{blue}{here}} and the code for LangVision-LoRA-NAS can be found \href{https://github.com/krishnateja95/LangVision-NAS}{\textcolor{blue}{here}}.

comment: Accepted by ICIP 2025 Conference

☆ Segmenting Thalamic Nuclei: T1 Maps Provide a Reliable and Efficient Solution

Anqi Feng, Zhangxing Bian, Samuel W. Remedios, Savannah P. Hays, Blake E. Dewey, Jiachen Zhuo, Dan Benjamini, Jerry L. Prince

Accurate thalamic nuclei segmentation is crucial for understanding neurological diseases, brain functions, and guiding clinical interventions. However, the optimal inputs for segmentation remain unclear. This study systematically evaluates multiple MRI contrasts, including MPRAGE and FGATIR sequences, quantitative PD and T1 maps, and multiple T1-weighted images at different inversion times (multi-TI), to determine the most effective inputs. For multi-TI images, we employ a gradient-based saliency analysis with Monte Carlo dropout and propose an Overall Importance Score to select the images contributing most to segmentation. A 3D U-Net is trained on each of these configurations. Results show that T1 maps alone achieve strong quantitative performance and superior qualitative outcomes, while PD maps offer no added value. These findings underscore the value of T1 maps as a reliable and efficient input among the evaluated options, providing valuable guidance for optimizing imaging protocols when thalamic structures are of clinical or research interest.

☆ Design and Validation of a Responsible Artificial Intelligence-based System for the Referral of Diabetic Retinopathy Patients

E. Ulises Moya-Sánchez, Abraham Sánchez-Perez, Raúl Nanclares Da Veiga, Alejandro Zarate-Macías, Edgar Villareal, Alejandro Sánchez-Montes, Edtna Jauregui-Ulloa, Héctor Moreno, Ulises Cortés

Diabetic Retinopathy (DR) is a leading cause of vision loss in working-age individuals. Early detection of DR can reduce the risk of vision loss by up to 95%, but a shortage of retinologists and challenges in timely examination complicate detection. Artificial Intelligence (AI) models using retinal fundus photographs (RFPs) offer a promising solution. However, adoption in clinical settings is hindered by low-quality data and biases that may lead AI systems to learn unintended features. To address these challenges, we developed RAIS-DR, a Responsible AI System for DR screening that incorporates ethical principles across the AI lifecycle. RAIS-DR integrates efficient convolutional models for preprocessing, quality assessment, and three specialized DR classification models. We evaluated RAIS-DR against the FDA-approved EyeArt system on a local dataset of 1,046 patients, unseen by both systems. RAIS-DR demonstrated significant improvements, with F1 scores increasing by 5-12%, accuracy by 6-19%, and specificity by 10-20%. Additionally, fairness metrics such as Disparate Impact and Equal Opportunity Difference indicated equitable performance across demographic subgroups, underscoring RAIS-DR's potential to reduce healthcare disparities. These results highlight RAIS-DR as a robust and ethically aligned solution for DR screening in clinical settings. The code, weights of RAIS-DR are available at https://gitlab.com/inteligencia-gubernamental-jalisco/jalisco-retinopathy with RAIL.

comment: 14 pages,3 figures, under review

♻ ☆ Advanced Gesture Recognition for Autism Spectrum Disorder Detection: Integrating YOLOv7, Video Augmentation, and VideoMAE for Naturalistic Video Analysis

Amit Kumar Singh, Vrijendra Singh

Deep learning and contactless sensing technologies have significantly advanced the automated assessment of human behaviors in healthcare. In the context of autism spectrum disorder (ASD), repetitive motor behaviors such as spinning, head banging, and arm flapping are key indicators for diagnosis. This study focuses on distinguishing between children with ASD and typically developed (TD) peers by analyzing videos captured in natural, uncontrolled environments. Using the publicly available Self-Stimulatory Behavior Dataset (SSBD), we address the classification task as a binary problem, ASD vs. TD, based on stereotypical repetitive gestures. We adopt a pipeline integrating YOLOv7-based detection, extensive video augmentations, and the VideoMAE framework, which efficiently captures both spatial and temporal features through a high-ratio masking and reconstruction strategy. Our proposed approach achieves 95% accuracy, 0.93 precision, 0.94 recall, and 0.94 F1 score, surpassing the previous state-of-the-art by a significant margin. These results demonstrate the effectiveness of combining advanced object detection, robust data augmentation, and masked autoencoder-based video modeling for reliable ASD vs. TD classification in naturalistic settings.

comment: Change Note for Version 3 - Extended Study (ASD vs TD Classification) This version extends v2 from 3-class gesture recognition to binary ASD vs TD detection, using expanded SSBD variants, a new TD class, improved preprocessing, and updated metrics (95% acc, 0.93 prec, 0.94 rec, 0.94 F1). Methodology remains YOLOv7 + VideoMAE + augmentation

2025-08-16

Sound 5

☆ Optimizing Neural Architectures for Hindi Speech Separation and Enhancement in Noisy Environments

Arnav Ramamoorthy

This paper addresses the challenges of Hindi speech separation and enhancement using advanced neural network architectures, with a focus on edge devices. We propose a refined approach leveraging the DEMUCS model to overcome limitations of traditional methods, achieving substantial improvements in speech clarity and intelligibility. The model is fine-tuned with U-Net and LSTM layers, trained on a dataset of 400,000 Hindi speech clips augmented with ESC-50 and MS-SNSD for diverse acoustic environments. Evaluation using PESQ and STOI metrics shows superior performance, particularly under extreme noise conditions. To ensure deployment on resource-constrained devices like TWS earbuds, we explore quantization techniques to reduce computational requirements. This research highlights the effectiveness of customized AI algorithms for speech processing in Indian contexts and suggests future directions for optimizing edge-based architectures.

comment: ICAD 2025

☆ Towards Automatic Evaluation and High-Quality Pseudo-Parallel Dataset Construction for Audio Editing: A Human-in-the-Loop Method

Yuhang Jia, Hui Wang, Xin Nie, Yujie Guo, Lianru Gao, Yong Qin

Audio editing aims to manipulate audio content based on textual descriptions, supporting tasks such as adding, removing, or replacing audio events. Despite recent progress, the lack of high-quality benchmark datasets and comprehensive evaluation metrics remains a major challenge for both assessing audio editing quality and improving the task itself. In this work, we propose a novel approach for audio editing task by incorporating expert knowledge into both the evaluation and dataset construction processes: 1) First, we establish AuditScore, the first comprehensive dataset for subjective evaluation of audio editing, consisting of over 6,300 edited samples generated from 7 representative audio editing frameworks and 23 system configurations. Each sample is annotated by professional raters on three key aspects of audio editing quality: overall Quality, Relevance to editing intent, and Faithfulness to original features. 2) Based on this dataset, we train AuditEval, the first model designed for automatic MOS-style scoring tailored to audio editing tasks. AuditEval addresses the critical lack of objective evaluation metrics and the prohibitive cost of subjective assessment in this field. 3) We further leverage AuditEval to evaluate and filter a large amount of synthetically mixed editing pairs, constructing a high-quality pseudo-parallel dataset by selecting the most plausible samples. Objective experiments validate the effectiveness of our expert-informed filtering strategy in yielding higher-quality data, while also revealing the limitations of relying solely on objective metrics. The dataset, codes and tools can be found at: https://github.com/NKU-HLT/AuditEval.

♻ ☆ Towards Generalized Source Tracing for Codec-Based Deepfake Speech

Xuanjun Chen, I-Ming Lin, Lin Zhang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang

Recent attempts at source tracing for codec-based deepfake speech (CodecFake), generated by neural audio codec-based speech generation (CoSG) models, have exhibited suboptimal performance. However, how to train source tracing models using simulated CoSG data while maintaining strong performance on real CoSG-generated audio remains an open challenge. In this paper, we show that models trained solely on codec-resynthesized data tend to overfit to non-speech regions and struggle to generalize to unseen content. To mitigate these challenges, we introduce the Semantic-Acoustic Source Tracing Network (SASTNet), which jointly leverages Whisper for semantic feature encoding and Wav2vec2 with AudioMAE for acoustic feature encoding. Our proposed SASTNet achieves state-of-the-art performance on the CoSG test set of the CodecFake+ dataset, demonstrating its effectiveness for reliable source tracing.

comment: IEEE ASRU 2025

♻ ☆ Differentiable Room Acoustic Rendering with Multi-View Vision Priors

Derong Jin, Ruohan Gao

An immersive acoustic experience enabled by spatial audio is just as crucial as the visual aspect in creating realistic virtual environments. However, existing methods for room impulse response estimation rely either on data-demanding learning-based models or computationally expensive physics-based modeling. In this work, we introduce Audio-Visual Differentiable Room Acoustic Rendering (AV-DAR), a framework that leverages visual cues extracted from multi-view images and acoustic beam tracing for physics-based room acoustic rendering. Experiments across six real-world environments from two datasets demonstrate that our multimodal, physics-based approach is efficient, interpretable, and accurate, significantly outperforming a series of prior methods. Notably, on the Real Acoustic Field dataset, AV-DAR achieves comparable performance to models trained on 10 times more data while delivering relative gains ranging from 16.6% to 50.9% when trained at the same scale.

comment: ICCV 2025 (Oral); Project Page: https://humathe.github.io/avdar/

♻ ☆ Controllable joint noise reduction and hearing loss compensation using a differentiable auditory model

Philippe Gonzalez, Torsten Dau, Tobias May

Deep learning-based hearing loss compensation (HLC) seeks to enhance speech intelligibility and quality for hearing impaired listeners using neural networks. One major challenge of HLC is the lack of a ground-truth target. Recent works have used neural networks to emulate non-differentiable auditory peripheral models in closed-loop frameworks, but this approach lacks flexibility. Alternatively, differentiable auditory models allow direct optimization, yet previous studies focused on individual listener profiles, or joint noise reduction (NR) and HLC without balancing each task. This work formulates NR and HLC as a multi-task learning problem, training a system to simultaneously predict denoised and compensated signals from noisy speech and audiograms using a differentiable auditory model. Results show the system achieves similar objective metric performance to systems trained for each task separately, while being able to adjust the balance between NR and HLC during inference.

comment: Accepted to Clarity 2025 Workshop

Audio and Speech Processing 5

☆ MASSLOC: A Massive Sound Source Localization System based on Direction-of-Arrival Estimation

Georg K. J. Fischer, Thomas Schaechtle, Moritz Schabinger, Alexander Richter, Ivo Häring, Fabian Höflinger, Stefan J. Rupitsch

Acoustic indoor localization offers the potential for highly accurate position estimation while generally exhibiting low hardware requirements compared to Radio Frequency (RF)-based solutions. Furthermore, angular-based localization significantly reduces installation effort by minimizing the number of required fixed anchor nodes. In this contribution, we propose the so-called MASSLOC system, which leverages sparse two-dimensional array geometries to localize and identify a large number of concurrently active sources. Additionally, the use of complementary Zadoff-Chu sequences is introduced to enable efficient, beamforming-based source identification. These sequences provide a trade-off between favorable correlation properties and accurate, unsynchronized direction-of-arrival estimation by exhibiting a spectrally balanced waveform. The system is evaluated in both a controlled anechoic chamber and a highly reverberant lobby environment with a reverberation time of 1.6 s. In a laboratory setting, successful direction-of-arrival estimation and identification of up to 14 simultaneously emitting sources are demonstrated. Adopting a Perspective-n-Point (PnP) calibration approach, the system achieves a median three-dimensional localization error of 55.7 mm and a median angular error of 0.84 deg with dynamic source movement of up to 1.9 mps in the challenging reverberant environment. The multi-source capability is also demonstrated and evaluated in that environment with a total of three tags. These results indicate the scalability and robustness of the MASSLOC system, even under challenging acoustic conditions.

comment: IEEE Transactions on Instrumentation and Measurement

☆ FNH-TTS: A Fast, Natural, and Human-Like Speech Synthesis System with advanced prosodic modeling based on Mixture of Experts

Qingliang Meng, Luogeng Xiong, Wei Liang, Limei Yu, Huizhi Liang, Tian Li

Achieving natural and human-like speech synthesis with low inference costs remains a major challenge in speech synthesis research. This study focuses on human prosodic patterns and synthesized spectrum harmony, addressing the challenges of prosody modeling and artifact issues in non-autoregressive models. To enhance prosody modeling and synthesis quality, we introduce a new Duration Predictor based on the Mixture of Experts alongside a new Vocoder with two advanced multi-scale discriminators. We integrated the these new modules into the VITS system, forming our FNH-TTS system. Our experiments on LJSpeech, VCTK, and LibriTTS demonstrate the system's superiority in synthesis quality, phoneme duration prediction, Vocoder results, and synthesis speed. Our prosody visualization results show that FNH-TTS produces duration predictions that more closely align with natural human beings than other systems.

♻ ☆ Towards Generalized Source Tracing for Codec-Based Deepfake Speech

Xuanjun Chen, I-Ming Lin, Lin Zhang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang

comment: IEEE ASRU 2025

♻ ☆ Controllable joint noise reduction and hearing loss compensation using a differentiable auditory model

Philippe Gonzalez, Torsten Dau, Tobias May

comment: Accepted to Clarity 2025 Workshop

♻ ☆ Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities

Guan-Ting Lin, Jiachen Lian, Tingle Li, Qirui Wang, Gopala Anumanchipalli, Alexander H. Liu, Hung-yi Lee

Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (SDMs) operate in half-duplex mode-processing one turn at a time - emerging full-duplex SDMs can listen and speak simultaneously, enabling more natural conversations. However, current evaluations remain limited, focusing mainly on turn-based metrics or coarse corpus-level analyses. To address this, we introduce Full-Duplex-Bench, a benchmark that systematically evaluates key interactive behaviors: pause handling, backchanneling, turn-taking, and interruption management. Our framework uses automatic metrics for consistent, reproducible assessment and provides a fair, fast evaluation setup. By releasing our benchmark and code, we aim to advance spoken dialogue modeling and foster the development of more natural and engaging SDMs.

comment: Accepted by ASRU 2025

2025-08-15

Sound 14

☆ Pretrained Conformers for Audio Fingerprinting and Retrieval

Kemal Altwlkany, Elmedin Selmanovic, Sead Delalic

Conformers have shown great results in speech processing due to their ability to capture both local and global interactions. In this work, we utilize a self-supervised contrastive learning framework to train conformer-based encoders that are capable of generating unique embeddings for small segments of audio, generalizing well to previously unseen data. We achieve state-of-the-art results for audio retrieval tasks while using only 3 seconds of audio to generate embeddings. Our models are almost completely immune to temporal misalignments and achieve state-of-the-art results in cases of other audio distortions such as noise, reverb or extreme temporal stretching. Code and models are made publicly available and the results are easy to reproduce as we train and test using popular and freely available datasets of different sizes.

☆ Representing Speech Through Autoregressive Prediction of Cochlear Tokens

Greta Tuckute, Klemen Kotar, Evelina Fedorenko, Daniel L. K. Yamins

We introduce AuriStream, a biologically inspired model for encoding speech via a two-stage framework inspired by the human auditory processing hierarchy. The first stage transforms raw audio into a time-frequency representation based on the human cochlea, from which we extract discrete \textbf{cochlear tokens}. The second stage applies an autoregressive sequence model over the cochlear tokens. AuriStream learns meaningful phoneme and word representations, and state-of-the-art lexical semantics. AuriStream shows competitive performance on diverse downstream SUPERB speech tasks. Complementing AuriStream's strong representational capabilities, it generates continuations of audio which can be visualized in a spectrogram space and decoded back into audio, providing insights into the model's predictions. In summary, we present a two-stage framework for speech representation learning to advance the development of more human-like models that efficiently handle a range of speech-based tasks.

☆ Speech Emotion Recognition Using Fine-Tuned DWFormer:A Study on Track 1 of the IERPChallenge 2024

Honghong Wang, Xupeng Jia, Jing Deng, Rong Zheng

The field of artificial intelligence has a strong interest in the topic of emotion recognition. The majority of extant emotion recognition models are oriented towards enhancing the precision of discrete emotion label prediction. Given the direct relationship between human personality and emotion, as well as the significant inter-individual differences in subjective emotional expression, the IERP Challenge 2024 incorporates personality traits into emotion recognition research. This paper presents the Fosafer submissions to the Track 1 of the IERP Challenge 2024. This task primarily concerns the recognition of emotions in audio, while also providing text and audio features. In Track 1, we utilized exclusively audio-based features and fine-tuned a pre-trained speech emotion recognition model, DWFormer, through the integration of data augmentation and score fusion strategies, thereby achieving the first place among the participating teams.

comment: 5 pages,1 figures

☆ Mitigating Category Imbalance: Fosafer System for the Multimodal Emotion and Intent Joint Understanding Challenge ICASSP2025

Honghong Wang, Yankai Wang, Dejun Zhang, Jing Deng, Rong Zheng

This paper presents Fosafer approach to the Track 2 Mandarin in the Multimodal Emotion and Intent Joint Understandingchallenge, which focuses on achieving joint recognition of emotion and intent in Mandarin, despite the issue of category imbalance. To alleviate this issue, we use a variety of data augmentation techniques across text, video, and audio modalities. Additionally, we introduce the SampleWeighted Focal Contrastive loss, designed to address the challenges of recognizing minority class samples and those that are semantically similar but difficult to distinguish. Moreover, we fine-tune the Hubert model to adapt the emotion and intent joint recognition. To mitigate modal competition, we introduce a modal dropout strategy. For the final predictions, a plurality voting approach is used to determine the results. The experimental results demonstrate the effectiveness of our method, which achieves the second-best performance in the Track 2 Mandarin challenge.

comment: 2 pages. pubilshed by ICASSP2025

☆ MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts

Heyang Xue, Xuchen Song, Yu Tang, Jianyu Chen, Yanru Chen, Yang Li, Yahui Zhou

Description-based text-to-speech (TTS) models exhibit strong performance on in-domain text descriptions, i.e., those encountered during training. However, in real-world applications, the diverse range of user-generated descriptions inevitably introduces numerous out-of-domain inputs that challenge the text understanding capabilities of these systems. To address this issue, we propose MoE-TTS, a description-based TTS model designed to enhance the understanding of out-of-domain text descriptions. MoE-TTS employs a modality-based mixture-of-experts (MoE) approach to augment a pre-trained textual large language model (LLM) with a set of specialized weights adapted to the speech modality while maintaining the original LLM frozen during training. This approach allows MoE-TTS to effectively leverage the pre-trained knowledge and text understanding abilities of textual LLMs. Our experimental results indicate that: first, even the most advanced closed-source commercial products can be challenged by carefully designed out-of-domain description test sets; second, MoE-TTS achieves superior performance in generating speech that more accurately reflects the descriptions. We encourage readers to listen to the demos at https://welkinyang.github.io/MoE-TTS/.

☆ Benchmarking Prosody Encoding in Discrete Speech Tokens

Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu

Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks. However, these discrete tokens are typically learned in advance, separately from the training of language models or downstream tasks. As a result, choices related to discretization, such as the SSL model used or the number of clusters, must be made heuristically. In particular, speech language models are expected to understand and generate responses that reflect not only the semantic content but also prosodic features. Yet, there has been limited research on the ability of discrete tokens to capture prosodic information. To address this gap, this study conducts a comprehensive analysis focusing on prosodic encoding based on their sensitivity to the artificially modified prosody, aiming to provide practical guidelines for designing discrete tokens.

comment: Accepted by ASRU2025

☆ Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation

Chenyang Le, Yinfeng Xia, Huiyan Li, Manhong Wang, Yutao Sun, Xingyang Ma, Yanmin Qian

Recent advancements in speech-to-text translation have led to the development of multilingual models capable of handling multiple language pairs simultaneously. However, these unified models often suffer from large parameter sizes, making it challenging to balance inference efficiency and performance, particularly in local deployment scenarios. We propose an innovative Parasitic Dual-Scale Approach, which combines an enhanced speculative sampling method with model compression and knowledge distillation techniques. Building on the Whisper Medium model, we enhance it for multilingual speech translation into whisperM2M, and integrate our novel KVSPN module, achieving state-of-the-art (SOTA) performance across six popular languages with improved inference efficiency. KVSPN enables a 40\% speedup with no BLEU score degradation. Combined with distillation methods, it represents a 2.6$\times$ speedup over the original Whisper Medium with superior performance.

comment: Interspeech 2025

☆ Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style

Wonjune Kang, Deb Roy

We introduce the task of expressive speech retrieval, where the goal is to retrieve speech utterances spoken in a given style based on a natural language description of that style. While prior work has primarily focused on performing speech retrieval based on what was said in an utterance, we aim to do so based on how something was said. We train speech and text encoders to embed speech and text descriptions of speaking styles into a joint latent space, which enables using free-form text prompts describing emotions or styles as queries to retrieve matching expressive speech segments. We perform detailed analyses of various aspects of our proposed framework, including encoder architectures, training criteria for effective cross-modal alignment, and prompt augmentation for improved generalization to arbitrary text queries. Experiments on multiple datasets encompassing 22 speaking styles demonstrate that our approach achieves strong retrieval performance as measured by Recall@k.

comment: Accepted to ASRU 2025

☆ What Matters for Bioacoustic Encoding

Marius Miron, David Robinson, Milad Alizadeh, Ellen Gilsenan-McMahon, Gagan Narula, Olivier Pietquin, Matthieu Geist, Emmanuel Chemla, Maddie Cusimano, Felix Effenberger, Masato Hagiwara, Benjamin Hoffman, Sara Keen, Diane Kim, Jane Lawton, Jen-Yu Liu, Aza Raskin

☆ Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding

Zhifeng Kong, Arushi Goel, Joao Felipe Santos, Sreyan Ghosh, Rafael Valle, Wei Ping, Bryan Catanzaro

Chain-of-thought reasoning has demonstrated significant improvements in large language models and vision language models, yet its potential for audio language models remains largely unexplored. In this technical report, we take a preliminary step towards closing this gap. For better assessment of sound reasoning, we propose AF-Reasoning-Eval, a benchmark targeting common-sense reasoning and the ability to discriminate among closely related choices. To prepare training corpus for sound reasoning abilities, we propose automatic pipelines that transform existing audio question answering and classification data into explicit reasoning chains, yielding AF-CoT-Train with 1.24M samples. We study the effect of finetuning Audio Flamingo series on AF-CoT-Train and observe considerable improvements on several reasoning benchmarks, validating the effectiveness of chain-of-thought finetuning on advanced sound understanding.

♻ ☆ Neurodyne: Neural Pitch Manipulation with Representation Learning and Cycle-Consistency GAN

Yicheng Gu, Chaoren Wang, Zhizheng Wu, Lauri Juvela

Pitch manipulation is the process of producers adjusting the pitch of an audio segment to a specific key and intonation, which is essential in music production. Neural-network-based pitch-manipulation systems have been popular in recent years due to their superior synthesis quality compared to classical DSP methods. However, their performance is still limited due to their inaccurate feature disentanglement using source-filter models and the lack of paired in- and out-of-tune training data. This work proposes Neurodyne to address these issues. Specifically, Neurodyne uses adversarial representation learning to learn a pitch-independent latent representation to avoid inaccurate disentanglement and cycle-consistency training to create paired training data implicitly. Experimental results on global-key and template-based pitch manipulation demonstrate the effectiveness of the proposed system, marking improved synthesis quality while maintaining the original singer identity.

♻ ☆ L3AC: Towards a Lightweight and Lossless Audio Codec

Linwei Zhai, Han Ding, Cui Zhao, fei wang, Ge Wang, Wang Zhi, Wei Xi

Neural audio codecs have recently gained traction for their ability to compress high-fidelity audio and provide discrete tokens for generative modeling. However, leading approaches often rely on resource-intensive models and complex multi-quantizer architectures, limiting their practicality in real-world applications. In this work, we introduce L3AC, a lightweight neural audio codec that addresses these challenges by leveraging a single quantizer and a highly efficient architecture. To enhance reconstruction fidelity while minimizing model complexity, L3AC explores streamlined convolutional networks and local Transformer modules, alongside TConv--a novel structure designed to capture acoustic variations across multiple temporal scales. Despite its compact design, extensive experiments across diverse datasets demonstrate that L3AC matches or exceeds the reconstruction quality of leading codecs while reducing computational overhead by an order of magnitude. The single-quantizer design further enhances its adaptability for downstream tasks. The source code is publicly available at https://github.com/zhai-lw/L3AC.

♻ ☆ Generalizable speech deepfake detection via meta-learned LoRA

Janne Laakkonen, Ivan Kukanov, Ville Hautamäki

Reliable detection of speech deepfakes (spoofs) must remain effective when the distribution of spoofing attacks shifts. We frame the task as domain generalization and show that inserting Low-Rank Adaptation (LoRA) adapters into every attention head of a self-supervised (SSL) backbone, then training only those adapters with Meta-Learning Domain Generalization (MLDG), yields strong zero-shot performance. The resulting model updates about 3.6 million parameters, roughly 1.1% of the 318 million updated in full fine-tuning, yet surpasses a fully fine-tuned counterpart on five of six evaluation corpora. A first-order MLDG loop encourages the adapters to focus on cues that persist across attack types, lowering the average EER from 8.84% for the fully fine-tuned model to 5.30% with our best MLDG-LoRA configuration. Our findings show that combining meta-learning with parameter-efficient adaptation offers an effective method for zero-shot, distribution-shift-aware speech deepfake detection.

comment: 10 pages, 5 figures, 7 tables

♻ ☆ SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization

Beilong Tang, Xiaoxiao Miao, Xin Wang, Ming Li

Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a novel speaker-embedding-free framework called SEF-MK. Instead of using a single k-means model trained on the entire dataset, SEF-MK anonymizes SSL representations for each utterance by randomly selecting one of multiple k-means models, each trained on a different subset of speakers. We explore this approach from both attacker and user perspectives. Extensive experiments show that, compared to a single k-means model, SEF-MK with multiple k-means models better preserves linguistic and emotional content from the user's viewpoint. However, from the attacker's perspective, utilizing multiple k-means models boosts the effectiveness of privacy attacks. These insights can aid users in designing voice anonymization systems to mitigate attacker threats.

comment: 8 pages, 3 figures, accepted by 2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

Audio and Speech Processing 17

☆ Pretrained Conformers for Audio Fingerprinting and Retrieval

Kemal Altwlkany, Elmedin Selmanovic, Sead Delalic

☆ Representing Speech Through Autoregressive Prediction of Cochlear Tokens

Greta Tuckute, Klemen Kotar, Evelina Fedorenko, Daniel L. K. Yamins

☆ Emphasis Sensitivity in Speech Representations

Shaun Cassini, Thomas Hain, Anton Ragni

This work investigates whether modern speech models are sensitive to prosodic emphasis - whether they encode emphasized and neutral words in systematically different ways. Prior work typically relies on isolated acoustic correlates (e.g., pitch, duration) or label prediction, both of which miss the relational structure of emphasis. This paper proposes a residual-based framework, defining emphasis as the difference between paired neutral and emphasized word representations. Analysis on self-supervised speech models shows that these residuals correlate strongly with duration changes and perform poorly at word identity prediction, indicating a structured, relational encoding of prosodic emphasis. In ASR fine-tuned models, residuals occupy a subspace up to 50% more compact than in pre-trained models, further suggesting that emphasis is encoded as a consistent, low-dimensional transformation that becomes more structured with task-specific learning.

comment: Accepted to IEEE ASRU 2025

☆ Enhancing In-the-Wild Speech Emotion Conversion with Resynthesis-based Duration Modeling

Navin Raj Prabhu, Danilo de Oliveira, Nale Lehmann-Willenbrock, Timo Gerkmann

Speech Emotion Conversion aims to modify the emotion expressed in input speech while preserving lexical content and speaker identity. Recently, generative modeling approaches have shown promising results in changing local acoustic properties such as fundamental frequency, spectral envelope and energy, but often lack the ability to control the duration of sounds. To address this, we propose a duration modeling framework using resynthesis-based discrete content representations, enabling modification of speech duration to reflect target emotions and achieve controllable speech rates without using parallel data. Experimental results reveal that the inclusion of the proposed duration modeling framework significantly enhances emotional expressiveness, in the in-the-wild MSP-Podcast dataset. Analyses show that low-arousal emotions correlate with longer durations and slower speech rates, while high-arousal emotions produce shorter, faster speech.

comment: Copyright 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

☆ Speech Emotion Recognition Using Fine-Tuned DWFormer:A Study on Track 1 of the IERPChallenge 2024

Honghong Wang, Xupeng Jia, Jing Deng, Rong Zheng

comment: 5 pages,1 figures

☆ Mitigating Category Imbalance: Fosafer System for the Multimodal Emotion and Intent Joint Understanding Challenge ICASSP2025

Honghong Wang, Yankai Wang, Dejun Zhang, Jing Deng, Rong Zheng

comment: 2 pages. pubilshed by ICASSP2025

☆ MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts

Heyang Xue, Xuchen Song, Yu Tang, Jianyu Chen, Yanru Chen, Yang Li, Yahui Zhou

☆ EmoSSLSphere: Multilingual Emotional Speech Synthesis with Spherical Vectors and Discrete Speech Tokens

Joonyong Park, Kenichi Nakamura

This paper introduces EmoSSLSphere, a novel framework for multilingual emotional text-to-speech (TTS) synthesis that combines spherical emotion vectors with discrete token features derived from self-supervised learning (SSL). By encoding emotions in a continuous spherical coordinate space and leveraging SSL-based representations for semantic and acoustic modeling, EmoSSLSphere enables fine-grained emotional control, effective cross-lingual emotion transfer, and robust preservation of speaker identity. We evaluate EmoSSLSphere on English and Japanese corpora, demonstrating significant improvements in speech intelligibility, spectral fidelity, prosodic consistency, and overall synthesis quality. Subjective evaluations further confirm that our method outperforms baseline models in terms of naturalness and emotional expressiveness, underscoring its potential as a scalable solution for multilingual emotional TTS.

comment: In Proceedings of the 13th ISCA Speech Synthesis Workshop

☆ Benchmarking Prosody Encoding in Discrete Speech Tokens

Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu

comment: Accepted by ASRU2025

☆ Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation

Chenyang Le, Yinfeng Xia, Huiyan Li, Manhong Wang, Yutao Sun, Xingyang Ma, Yanmin Qian

comment: Interspeech 2025

☆ Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style

Wonjune Kang, Deb Roy

comment: Accepted to ASRU 2025

♻ ☆ Neurodyne: Neural Pitch Manipulation with Representation Learning and Cycle-Consistency GAN

Yicheng Gu, Chaoren Wang, Zhizheng Wu, Lauri Juvela

♻ ☆ MultiAiTutor: Child-Friendly Educational Multilingual Speech Generation Tutor with LLMs

Xiaoxue Gao, Huayun Zhang, Nancy F. Chen

Generative speech models have demonstrated significant potential in personalizing teacher-student interactions, offering valuable real-world applications for language learning in children's education. However, achieving high-quality, child-friendly speech generation remains challenging, particularly for low-resource languages across diverse languages and cultural contexts. In this paper, we propose MultiAiTutor, an educational multilingual generative AI tutor with child-friendly designs, leveraging LLM architecture for speech generation tailored for educational purposes. We propose to integrate age-appropriate multilingual speech generation using LLM architectures, facilitating young children's language learning through culturally relevant image-description tasks in three low-resource languages: Singaporean-accent Mandarin, Malay, and Tamil. Experimental results from both objective metrics and subjective evaluations demonstrate the superior performance of the proposed MultiAiTutor compared to baseline methods.

comment: We are withdrawing the manuscript to revise the title and contents of figures for better alignment with the paper's contributions

♻ ☆ Generalizable speech deepfake detection via meta-learned LoRA

Janne Laakkonen, Ivan Kukanov, Ville Hautamäki

comment: 10 pages, 5 figures, 7 tables

♻ ☆ Fairness in Dysarthric Speech Synthesis: Understanding Intrinsic Bias in Dysarthric Speech Cloning using F5-TTS

M Anuprabha, Krishna Gurugubelli, Anil Kumar Vuppala

Dysarthric speech poses significant challenges in developing assistive technologies, primarily due to the limited availability of data. Recent advances in neural speech synthesis, especially zero-shot voice cloning, facilitate synthetic speech generation for data augmentation; however, they may introduce biases towards dysarthric speech. In this paper, we investigate the effectiveness of state-of-the-art F5-TTS in cloning dysarthric speech using TORGO dataset, focusing on intelligibility, speaker similarity, and prosody preservation. We also analyze potential biases using fairness metrics like Disparate Impact and Parity Difference to assess disparities across dysarthric severity levels. Results show that F5-TTS exhibits a strong bias toward speech intelligibility over speaker and prosody preservation in dysarthric speech synthesis. Insights from this study can help integrate fairness-aware dysarthric speech synthesis, fostering the advancement of more inclusive speech technologies.

comment: Accepted at Interspeech 2025

♻ ☆ SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization

Beilong Tang, Xiaoxiao Miao, Xin Wang, Ming Li

comment: 8 pages, 3 figures, accepted by 2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

♻ ☆ Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems

Bo Ren, Yu Shi, Jinyu Li

End-to-End Automatic Speech Recognition (ASR) has advanced significantly yet still struggles with rare and domain-specific entities. This paper introduces a simple yet efficient prompt-based biasing technique for contextualized ASR, enhancing recognition accuracy by leverage a unified multitask learning framework. The approach comprises two key components: a prompt biasing model which is trained to determine when to focus on entities in prompt, and a entity filtering mechanism which efficiently filters out irrelevant entities. Our method significantly enhances ASR accuracy on entities, achieving a relative 30.7% and 18.0% reduction in Entity Word Error Rate compared to the baseline model with shallow fusion on in-house domain dataset with small and large entity lists, respectively. The primary advantage of this method lies in its efficiency and simplicity without any structure change, making it lightweight and highly efficient.

Computer Vision and Pattern Recognition 140

☆ Thyme: Think Beyond Images

Yi-Fan Zhang, Xingyu Lu, Shukang Yin, Chaoyou Fu, Wei Chen, Xiao Hu, Bin Wen, Kaiyu Jiang, Changyi Liu, Tianke Zhang, Haonan Fan, Kaibing Chen, Jiankang Chen, Haojie Ding, Kaiyu Tang, Zhang Zhang, Liang Wang, Fan Yang, Tingting Gao, Guorui Zhou

Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing Thyme (Think Beyond Images), a novel paradigm for enabling MLLMs to transcend existing ``think with images'' approaches by autonomously generating and executing diverse image processing and computational operations via executable code. This approach not only facilitates a rich, on-the-fly set of image manipulations (e.g., cropping, rotation, contrast enhancement) but also allows for mathematical computations, all while maintaining high autonomy in deciding when and how to apply these operations. We activate this capability through a two-stage training strategy: an initial SFT on a curated dataset of 500K samples to teach code generation, followed by a RL phase to refine decision-making. For the RL stage, we manually collect and design high-resolution question-answer pairs to increase the learning difficulty, and we propose GRPO-ATS (Group Relative Policy Optimization with Adaptive Temperature Sampling), an algorithm that applies distinct temperatures to text and code generation to balance reasoning exploration with code execution precision. We conduct extensive experimental analysis and ablation studies. Comprehensive evaluations on nearly 20 benchmarks show that Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.

comment: Project page: https://thyme-vl.github.io/

☆ Is ChatGPT-5 Ready for Mammogram VQA?

Qiang Li, Shansong Wang, Mingzhe Hu, Mojtaba Safari, Zachary Eidex, Xiaofeng Yang

Mammogram visual question answering (VQA) integrates image interpretation with clinical reasoning and has potential to support breast cancer screening. We systematically evaluated the GPT-5 family and GPT-4o model on four public mammography datasets (EMBED, InBreast, CMMD, CBIS-DDSM) for BI-RADS assessment, abnormality detection, and malignancy classification tasks. GPT-5 consistently was the best performing model but lagged behind both human experts and domain-specific fine-tuned models. On EMBED, GPT-5 achieved the highest scores among GPT variants in density (56.8%), distortion (52.5%), mass (64.5%), calcification (63.5%), and malignancy (52.8%) classification. On InBreast, it attained 36.9% BI-RADS accuracy, 45.9% abnormality detection, and 35.0% malignancy classification. On CMMD, GPT-5 reached 32.3% abnormality detection and 55.0% malignancy accuracy. On CBIS-DDSM, it achieved 69.3% BI-RADS accuracy, 66.0% abnormality detection, and 58.2% malignancy accuracy. Compared with human expert estimations, GPT-5 exhibited lower sensitivity (63.5%) and specificity (52.3%). While GPT-5 exhibits promising capabilities for screening tasks, its performance remains insufficient for high-stakes clinical imaging applications without targeted domain adaptation and optimization. However, the tremendous improvements in performance from GPT-4o to GPT-5 show a promising trend in the potential for general large language models (LLMs) to assist with mammography VQA tasks.

☆ LoRAtorio: An intrinsic approach to LoRA Skill Composition

Niki Foteinopoulou, Ignas Budvytis, Stephan Liwicki

Low-Rank Adaptation (LoRA) has become a widely adopted technique in text-to-image diffusion models, enabling the personalisation of visual concepts such as characters, styles, and objects. However, existing approaches struggle to effectively compose multiple LoRA adapters, particularly in open-ended settings where the number and nature of required skills are not known in advance. In this work, we present LoRAtorio, a novel train-free framework for multi-LoRA composition that leverages intrinsic model behaviour. Our method is motivated by two key observations: (1) LoRA adapters trained on narrow domains produce denoised outputs that diverge from the base model, and (2) when operating out-of-distribution, LoRA outputs show behaviour closer to the base model than when conditioned in distribution. The balance between these two observations allows for exceptional performance in the single LoRA scenario, which nevertheless deteriorates when multiple LoRAs are loaded. Our method operates in the latent space by dividing it into spatial patches and computing cosine similarity between each patch's predicted noise and that of the base model. These similarities are used to construct a spatially-aware weight matrix, which guides a weighted aggregation of LoRA outputs. To address domain drift, we further propose a modification to classifier-free guidance that incorporates the base model's unconditional score into the composition. We extend this formulation to a dynamic module selection setting, enabling inference-time selection of relevant LoRA adapters from a large pool. LoRAtorio achieves state-of-the-art performance, showing up to a 1.3% improvement in ClipScore and a 72.43% win rate in GPT-4V pairwise evaluations, and generalises effectively to multiple latent diffusion models.

comment: 32 pages, 17 figures

☆ Controlling Multimodal LLMs via Reward-guided Decoding

Oscar Mañas, Pierluca D'Oro, Koustuv Sinha, Adriana Romero-Soriano, Michal Drozdzal, Aishwarya Agrawal

As Multimodal Large Language Models (MLLMs) gain widespread applicability, it is becoming increasingly desirable to adapt them for diverse user needs. In this paper, we study the adaptation of MLLMs through controlled decoding. To achieve this, we introduce the first method for reward-guided decoding of MLLMs and demonstrate its application in improving their visual grounding. Our method involves building reward models for visual grounding and using them to guide the MLLM's decoding process. Concretely, we build two separate reward models to independently control the degree of object precision and recall in the model's output. Our approach enables on-the-fly controllability of an MLLM's inference process in two ways: first, by giving control over the relative importance of each reward function during decoding, allowing a user to dynamically trade off object precision for recall in image captioning tasks; second, by giving control over the breadth of the search during decoding, allowing the user to control the trade-off between the amount of test-time compute and the degree of visual grounding. We evaluate our method on standard object hallucination benchmarks, showing that it provides significant controllability over MLLM inference, while consistently outperforming existing hallucination mitigation methods.

comment: Published at ICCV 2025

☆ CoreEditor: Consistent 3D Editing via Correspondence-constrained Diffusion

Zhe Zhu, Honghua Chen, Peng Li, Mingqiang Wei

Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view inputs. However, without explicit control over multi-view information exchange, they often fail to maintain cross-view consistency, leading to insufficient edits and blurry details. We introduce CoreEditor, a novel framework for consistent text-to-3D editing. The key innovation is a correspondence-constrained attention mechanism that enforces precise interactions between pixels expected to remain consistent throughout the diffusion denoising process. Beyond relying solely on geometric alignment, we further incorporate semantic similarity estimated during denoising, enabling more reliable correspondence modeling and robust multi-view editing. In addition, we design a selective editing pipeline that allows users to choose preferred results from multiple candidates, offering greater flexibility and user control. Extensive experiments show that CoreEditor produces high-quality, 3D-consistent edits with sharper details, significantly outperforming prior methods.

☆ DashCam Video: A complementary low-cost data stream for on-demand forest-infrastructure system monitoring

Durga Joshi, Chandi Witharana, Robert Fahey, Thomas Worthley, Zhe Zhu, Diego Cerrai

Our study introduces a novel, low-cost, and reproducible framework for real-time, object-level structural assessment and geolocation of roadside vegetation and infrastructure with commonly available but underutilized dashboard camera (dashcam) video data. We developed an end-to-end pipeline that combines monocular depth estimation, depth error correction, and geometric triangulation to generate accurate spatial and structural data from street-level video streams from vehicle-mounted dashcams. Depth maps were first estimated using a state-of-the-art monocular depth model, then refined via a gradient-boosted regression framework to correct underestimations, particularly for distant objects. The depth correction model achieved strong predictive performance (R2 = 0.92, MAE = 0.31 on transformed scale), significantly reducing bias beyond 15 m. Further, object locations were estimated using GPS-based triangulation, while object heights were calculated using pin hole camera geometry. Our method was evaluated under varying conditions of camera placement and vehicle speed. Low-speed vehicle with inside camera gave the highest accuracy, with mean geolocation error of 2.83 m, and mean absolute error (MAE) in height estimation of 2.09 m for trees and 0.88 m for poles. To the best of our knowledge, it is the first framework to combine monocular depth modeling, triangulated GPS-based geolocation, and real-time structural assessment for urban vegetation and infrastructure using consumer-grade video data. Our approach complements conventional RS methods, such as LiDAR and image by offering a fast, real-time, and cost-effective solution for object-level monitoring of vegetation risks and infrastructure exposure, making it especially valuable for utility companies, and urban planners aiming for scalable and frequent assessments in dynamic urban environments.

comment: 35 Pages, 15 figures

☆ Visual Perception Engine: Fast and Flexible Multi-Head Inference for Robotic Vision Tasks

Jakub Łucki, Jonathan Becktor, Georgios Georgakis, Robert Royce, Shehryar Khattak

comment: 6 pages, 6 figures, 2 tables

☆ Causality Matters: How Temporal Information Emerges in Video Language Models

Yumeng Shi, Quanyu Long, Yin Wu, Wenya Wang

Video language models (VideoLMs) have made significant progress in multimodal understanding. However, temporal understanding, which involves identifying event order, duration, and relationships across time, still remains a core challenge. Prior works emphasize positional encodings (PEs) as a key mechanism for encoding temporal structure. Surprisingly, we find that removing or modifying PEs in video inputs yields minimal degradation in the performance of temporal understanding. In contrast, reversing the frame sequence while preserving the original PEs causes a substantial drop. To explain this behavior, we conduct substantial analysis experiments to trace how temporal information is integrated within the model. We uncover a causal information pathway: temporal cues are progressively synthesized through inter-frame attention, aggregated in the final frame, and subsequently integrated into the query tokens. This emergent mechanism shows that temporal reasoning emerges from inter-visual token interactions under the constraints of causal attention, which implicitly encodes temporal structure. Based on these insights, we propose two efficiency-oriented strategies: staged cross-modal attention and a temporal exit mechanism for early token truncation. Experiments on two benchmarks validate the effectiveness of both approaches. To the best of our knowledge, this is the first work to systematically investigate video temporal understanding in VideoLMs, offering insights for future model improvement.

☆ TrajSV: A Trajectory-based Model for Sports Video Representations and Applications

Zheng Wang, Shihao Xu, Wei Shi

Sports analytics has received significant attention from both academia and industry in recent years. Despite the growing interest and efforts in this field, several issues remain unresolved, including (1) data unavailability, (2) lack of an effective trajectory-based framework, and (3) requirement for sufficient supervision labels. In this paper, we present TrajSV, a trajectory-based framework that addresses various issues in existing studies. TrajSV comprises three components: data preprocessing, Clip Representation Network (CRNet), and Video Representation Network (VRNet). The data preprocessing module extracts player and ball trajectories from sports broadcast videos. CRNet utilizes a trajectory-enhanced Transformer module to learn clip representations based on these trajectories. Additionally, VRNet learns video representations by aggregating clip representations and visual features with an encoder-decoder architecture. Finally, a triple contrastive loss is introduced to optimize both video and clip representations in an unsupervised manner. The experiments are conducted on three broadcast video datasets to verify the effectiveness of TrajSV for three types of sports (i.e., soccer, basketball, and volleyball) with three downstream applications (i.e., sports video retrieval, action spotting, and video captioning). The results demonstrate that TrajSV achieves state-of-the-art performance in sports video retrieval, showcasing a nearly 70% improvement. It outperforms baselines in action spotting, achieving state-of-the-art results in 9 out of 17 action categories, and demonstrates a nearly 20% improvement in video captioning. Additionally, we introduce a deployed system along with the three applications based on TrajSV.

comment: This paper has been accepted by TCSVT

☆ Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model

Zuo Zuo, Jiahao Dong, Yanyun Qu, Zongze Wu

Industrial anomaly detection (AD) plays a significant role in manufacturing where a long-standing challenge is data scarcity. A growing body of works have emerged to address insufficient anomaly data via anomaly generation. However, these anomaly generation methods suffer from lack of fidelity or need to be trained with extra data. To this end, we propose a training-free anomaly generation framework dubbed AAG, which is based on Stable Diffusion (SD)'s strong generation ability for effective anomaly image generation. Given a normal image, mask and a simple text prompt, AAG can generate realistic and natural anomalies in the specific regions and simultaneously keep contents in other regions unchanged. In particular, we propose Cross-Attention Enhancement (CAE) to re-engineer the cross-attention mechanism within Stable Diffusion based on the given mask. CAE increases the similarity between visual tokens in specific regions and text embeddings, which guides these generated visual tokens in accordance with the text description. Besides, generated anomalies need to be more natural and plausible with object in given image. We propose Self-Attention Enhancement (SAE) which improves similarity between each normal visual token and anomaly visual tokens. SAE ensures that generated anomalies are coherent with original pattern. Extensive experiments on MVTec AD and VisA datasets demonstrate effectiveness of AAG in anomaly generation and its utility. Furthermore, anomaly images generated by AAG can bolster performance of various downstream anomaly inspection tasks.

☆ Reinforcing Video Reasoning Segmentation to Think Before It Segments

Sitong Gong, Lu Zhang, Yunzhi Zhuge, Xu Jia, Pingping Zhang, Huchuan Lu

Video reasoning segmentation (VRS) endeavors to delineate referred objects in videos guided by implicit instructions that encapsulate human intent and temporal logic. Previous approaches leverage large vision language models (LVLMs) to encode object semantics into tokens for mask prediction. However, this paradigm suffers from limited interpretability during inference and suboptimal performance due to inadequate spatiotemporal reasoning. Drawing inspiration from seminal breakthroughs in reinforcement learning, we introduce Veason-R1, a specialized LVLM for VRS that emphasizes structured reasoning in segmentation. Veason-R1 is trained through Group Relative Policy Optimization (GRPO) augmented with Chain-of-Thought (CoT) initialization. To begin with, we curate high-quality CoT training data to instill structured reasoning trajectories, bridging video-level semantics and frame-level spatial grounding, yielding the supervised fine-tuned model Veason-SFT. Subsequently, GRPO fine-tuning encourages efficient exploration of the reasoning space by optimizing reasoning chains. To this end, we incorporate a holistic reward mechanism that synergistically enhances spatial alignment and temporal consistency, bolstering keyframe localization and fine-grained grounding. Comprehensive empirical evaluations demonstrate that Veason-R1 achieves state-of-the-art performance on multiple benchmarks, surpassing prior art by significant margins (e.g., +1.3 J &F in ReVOS and +10.0 J &F in ReasonVOS), while exhibiting robustness to hallucinations (+8.8 R). Our code and model weights will be available at Veason-R1.

comment: 12 pages

☆ An Efficient Medical Image Classification Method Based on a Lightweight Improved ConvNeXt-Tiny Architecture

Jingsong Xia, Yue Yin, Xiuhan Li

Intelligent analysis of medical imaging plays a crucial role in assisting clinical diagnosis. However, achieving efficient and high-accuracy image classification in resource-constrained computational environments remains challenging. This study proposes a medical image classification method based on an improved ConvNeXt-Tiny architecture. Through structural optimization and loss function design, the proposed method enhances feature extraction capability and classification performance while reducing computational complexity. Specifically, the method introduces a dual global pooling (Global Average Pooling and Global Max Pooling) feature fusion strategy into the ConvNeXt-Tiny backbone to simultaneously preserve global statistical features and salient response information. A lightweight channel attention module, termed Squeeze-and-Excitation Vector (SEVector), is designed to improve the adaptive allocation of channel weights while minimizing parameter overhead. Additionally, a Feature Smoothing Loss is incorporated into the loss function to enhance intra-class feature consistency and suppress intra-class variance. Under CPU-only conditions (8 threads), the method achieves a maximum classification accuracy of 89.10% on the test set within 10 training epochs, exhibiting a stable convergence trend in loss values. Experimental results demonstrate that the proposed method effectively improves medical image classification performance in resource-limited settings, providing a feasible and efficient solution for the deployment and promotion of medical imaging analysis models.

☆ Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction

Shilei Wang, Gong Cheng, Pujian Lai, Dong Gao, Junwei Han

Efficient trackers achieve faster runtime by reducing computational complexity and model parameters. However, this efficiency often compromises the expense of weakened feature representation capacity, thus limiting their ability to accurately capture target states using single-layer features. To overcome this limitation, we propose Multi-State Tracker (MST), which utilizes highly lightweight state-specific enhancement (SSE) to perform specialized enhancement on multi-state features produced by multi-state generation (MSG) and aggregates them in an interactive and adaptive manner using cross-state interaction (CSI). This design greatly enhances feature representation while incurring minimal computational overhead, leading to improved tracking robustness in complex environments. Specifically, the MSG generates multiple state representations at multiple stages during feature extraction, while SSE refines them to highlight target-specific features. The CSI module facilitates information exchange between these states and ensures the integration of complementary features. Notably, the introduced SSE and CSI modules adopt a highly lightweight hidden state adaptation-based state space duality (HSA-SSD) design, incurring only 0.1 GFLOPs in computation and 0.66 M in parameters. Experimental results demonstrate that MST outperforms all previous efficient trackers across multiple datasets, significantly improving tracking accuracy and robustness. In particular, it shows excellent runtime performance, with an AO score improvement of 4.5\% over the previous SOTA efficient tracker HCAT on the GOT-10K dataset. The code is available at https://github.com/wsumel/MST.

☆ A Real-time Concrete Crack Detection and Segmentation Model Based on YOLOv11

Shaoze Huang, Qi Liu, Chao Chen, Yuhang Chen

Accelerated aging of transportation infrastructure in the rapidly developing Yangtze River Delta region necessitates efficient concrete crack detection, as crack deterioration critically compromises structural integrity and regional economic growth. To overcome the limitations of inefficient manual inspection and the suboptimal performance of existing deep learning models, particularly for small-target crack detection within complex backgrounds, this paper proposes YOLOv11-KW-TA-FP, a multi-task concrete crack detection and segmentation model based on the YOLOv11n architecture. The proposed model integrates a three-stage optimization framework: (1) Embedding dynamic KernelWarehouse convolution (KWConv) within the backbone network to enhance feature representation through a dynamic kernel sharing mechanism; (2) Incorporating a triple attention mechanism (TA) into the feature pyramid to strengthen channel-spatial interaction modeling; and (3) Designing an FP-IoU loss function to facilitate adaptive bounding box regression penalization. Experimental validation demonstrates that the enhanced model achieves significant performance improvements over the baseline, attaining 91.3% precision, 76.6% recall, and 86.4% mAP@50. Ablation studies confirm the synergistic efficacy of the proposed modules. Furthermore, robustness tests indicate stable performance under conditions of data scarcity and noise interference. This research delivers an efficient computer vision solution for automated infrastructure inspection, exhibiting substantial practical engineering value.

☆ Semi-Supervised Learning with Online Knowledge Distillation for Skin Lesion Classification

Siyamalan Manivannan

Deep Learning has emerged as a promising approach for skin lesion analysis. However, existing methods mostly rely on fully supervised learning, requiring extensive labeled data, which is challenging and costly to obtain. To alleviate this annotation burden, this study introduces a novel semi-supervised deep learning approach that integrates ensemble learning with online knowledge distillation for enhanced skin lesion classification. Our methodology involves training an ensemble of convolutional neural network models, using online knowledge distillation to transfer insights from the ensemble to its members. This process aims to enhance the performance of each model within the ensemble, thereby elevating the overall performance of the ensemble itself. Post-training, any individual model within the ensemble can be deployed at test time, as each member is trained to deliver comparable performance to the ensemble. This is particularly beneficial in resource-constrained environments. Experimental results demonstrate that the knowledge-distilled individual model performs better than independently trained models. Our approach demonstrates superior performance on both the \emph{International Skin Imaging Collaboration} 2018 and 2019 public benchmark datasets, surpassing current state-of-the-art results. By leveraging ensemble learning and online knowledge distillation, our method reduces the need for extensive labeled data while providing a more resource-efficient solution for skin lesion classification in real-world scenarios.

☆ AIM: Amending Inherent Interpretability via Self-Supervised Masking

Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper

It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features. In this work, we propose "Amending Inherent Interpretability via Self-Supervised Masking" (AIM), a simple yet interestingly effective method that promotes the network's utilization of genuine features over spurious alternatives without requiring additional annotations. In particular, AIM uses features at multiple encoding stages to guide a self-supervised, sample-specific feature-masking process. As a result, AIM enables the training of well-performing and inherently interpretable models that faithfully summarize the decision process. We validate AIM across a diverse range of challenging datasets that test both out-of-distribution generalization and fine-grained visual understanding. These include general-purpose classification benchmarks such as ImageNet100, HardImageNet, and ImageWoof, as well as fine-grained classification datasets such as Waterbirds, TravelingBirds, and CUB-200. AIM demonstrates significant dual benefits: interpretability improvements, as measured by the Energy Pointing Game (EPG) score, and accuracy gains over strong baselines. These consistent gains across domains and architectures provide compelling evidence that AIM promotes the use of genuine and meaningful features that directly contribute to improved generalization and human-aligned interpretability.

comment: Accepted at International Conference on Computer Vision (ICCV) 2025

☆ Handwritten Text Recognition of Historical Manuscripts Using Transformer-Based Models

Erez Meoded

Historical handwritten text recognition (HTR) is essential for unlocking the cultural and scholarly value of archival documents, yet digitization is often hindered by scarce transcriptions, linguistic variation, and highly diverse handwriting styles. In this study, we apply TrOCR, a state-of-the-art transformer-based HTR model, to 16th-century Latin manuscripts authored by Rudolf Gwalther. We investigate targeted image preprocessing and a broad suite of data augmentation techniques, introducing four novel augmentation methods designed specifically for historical handwriting characteristics. We also evaluate ensemble learning approaches to leverage the complementary strengths of augmentation-trained models. On the Gwalther dataset, our best single-model augmentation (Elastic) achieves a Character Error Rate (CER) of 1.86, while a top-5 voting ensemble achieves a CER of 1.60 - representing a 50% relative improvement over the best reported TrOCR_BASE result and a 42% improvement over the previous state of the art. These results highlight the impact of domain-specific augmentations and ensemble strategies in advancing HTR performance for historical manuscripts.

☆ Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition

Feiyue Zhao, Zhichao Zhang

Convolutional neural networks (CNNs) have demonstrated strong performance in visual recognition tasks, but their inherent reliance on regular grid structures limits their capacity to model complex topological relationships and non-local semantics within images. To address this limita tion, we propose the hierarchical graph feature enhancement (HGFE), a novel framework that integrates graph-based rea soning into CNNs to enhance both structural awareness and feature representation. HGFE builds two complementary levels of graph structures: intra-window graph convolution to cap ture local spatial dependencies and inter-window supernode interactions to model global semantic relationships. Moreover, we introduce an adaptive frequency modulation module that dynamically balances low-frequency and high-frequency signal propagation, preserving critical edge and texture information while mitigating over-smoothing. The proposed HGFE module is lightweight, end-to-end trainable, and can be seamlessly integrated into standard CNN backbone networks. Extensive experiments on CIFAR-100 (classification), PASCAL VOC, and VisDrone (detection), as well as CrackSeg and CarParts (segmentation), validated the effectiveness of the HGFE in improving structural representation and enhancing overall recognition performance.

☆ Relative Position Matters: Trajectory Prediction and Planning with Polar Representation

Bozhou Zhang, Nan Song, Bingzhao Gao, Li Zhang

Trajectory prediction and planning in autonomous driving are highly challenging due to the complexity of predicting surrounding agents' movements and planning the ego agent's actions in dynamic environments. Existing methods encode map and agent positions and decode future trajectories in Cartesian coordinates. However, modeling the relationships between the ego vehicle and surrounding traffic elements in Cartesian space can be suboptimal, as it does not naturally capture the varying influence of different elements based on their relative distances and directions. To address this limitation, we adopt the Polar coordinate system, where positions are represented by radius and angle. This representation provides a more intuitive and effective way to model spatial changes and relative relationships, especially in terms of distance and directional influence. Based on this insight, we propose Polaris, a novel method that operates entirely in Polar coordinates, distinguishing itself from conventional Cartesian-based approaches. By leveraging the Polar representation, this method explicitly models distance and direction variations and captures relative relationships through dedicated encoding and refinement modules, enabling more structured and spatially aware trajectory prediction and planning. Extensive experiments on the challenging prediction (Argoverse 2) and planning benchmarks (nuPlan) demonstrate that Polaris achieves state-of-the-art performance.

☆ Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving

Bozhou Zhang, Jingyu Li, Nan Song, Li Zhang

End-to-end autonomous driving has achieved remarkable advancements in recent years. Existing methods primarily follow a perception-planning paradigm, where perception and planning are executed sequentially within a fully differentiable framework for planning-oriented optimization. We further advance this paradigm through a perception-in-plan framework design, which integrates perception into the planning process. This design facilitates targeted perception guided by evolving planning objectives over time, ultimately enhancing planning performance. Building on this insight, we introduce VeteranAD, a coupled perception and planning framework for end-to-end autonomous driving. By incorporating multi-mode anchored trajectories as planning priors, the perception module is specifically designed to gather traffic elements along these trajectories, enabling comprehensive and targeted perception. Planning trajectories are then generated based on both the perception results and the planning priors. To make perception fully serve planning, we adopt an autoregressive strategy that progressively predicts future trajectories while focusing on relevant regions for targeted perception at each step. With this simple yet effective design, VeteranAD fully unleashes the potential of planning-oriented end-to-end methods, leading to more accurate and reliable driving behavior. Extensive experiments on the NAVSIM and Bench2Drive datasets demonstrate that our VeteranAD achieves state-of-the-art performance.

☆ Automated Building Heritage Assessment Using Street-Level Imagery

Kristina Dabrock, Tim Johansson, Anna Donarelli, Mikael Mangold, Noah Pflugradt, Jann Michael Weinand, Jochen Linßen

Detailed data is required to quantify energy conservation measures in buildings, such as envelop retrofits, without compromising cultural heritage. Novel artificial intelligence tools may improve efficiency in identifying heritage values in buildings compared to costly and time-consuming traditional inventories. In this study, the large language model GPT was used to detect various aspects of cultural heritage value in fa\c{c}ade images. Using this data and building register data as features, machine learning models were trained to classify multi-family and non-residential buildings in Stockholm, Sweden. Validation against an expert-created inventory shows a macro F1-score of 0.71 using a combination of register data and features retrieved from GPT, and a score of 0.60 using only GPT-derived data. The presented methodology can contribute to a higher-quality database and thus support careful energy efficiency measures and integrated consideration of heritage value in large-scale energetic refurbishment scenarios.

☆ CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models

Xiaoxue Wu, Bingjie Gao, Yu Qiao, Yaohui Wang, Xinyuan Chen

Despite significant advances in video synthesis, research into multi-shot video generation remains in its infancy. Even with scaled-up models and massive datasets, the shot transition capabilities remain rudimentary and unstable, largely confining generated videos to single-shot sequences. In this work, we introduce CineTrans, a novel framework for generating coherent multi-shot videos with cinematic, film-style transitions. To facilitate insights into the film editing style, we construct a multi-shot video-text dataset Cine250K with detailed shot annotations. Furthermore, our analysis of existing video diffusion models uncovers a correspondence between attention maps in the diffusion model and shot boundaries, which we leverage to design a mask-based control mechanism that enables transitions at arbitrary positions and transfers effectively in a training-free setting. After fine-tuning on our dataset with the mask mechanism, CineTrans produces cinematic multi-shot sequences while adhering to the film editing style, avoiding unstable transitions or naive concatenations. Finally, we propose specialized evaluation metrics for transition control, temporal consistency and overall quality, and demonstrate through extensive experiments that CineTrans significantly outperforms existing baselines across all criteria.

comment: 27 pages, 20 figures

☆ OpenConstruction: A Systematic Synthesis of Open Visual Datasets for Data-Centric Artificial Intelligence in Construction Monitoring

Ruoxin Xiong, Yanyu Wang, Jiannan Cai, Kaijian Liu, Yuansheng Zhu, Pingbo Tang, Nora El-Gohary

The construction industry increasingly relies on visual data to support Artificial Intelligence (AI) and Machine Learning (ML) applications for site monitoring. High-quality, domain-specific datasets, comprising images, videos, and point clouds, capture site geometry and spatiotemporal dynamics, including the location and interaction of objects, workers, and materials. However, despite growing interest in leveraging visual datasets, existing resources vary widely in sizes, data modalities, annotation quality, and representativeness of real-world construction conditions. A systematic review to categorize their data characteristics and application contexts is still lacking, limiting the community's ability to fully understand the dataset landscape, identify critical gaps, and guide future directions toward more effective, reliable, and scalable AI applications in construction. To address this gap, this study conducts an extensive search of academic databases and open-data platforms, yielding 51 publicly available visual datasets that span the 2005-2024 period. These datasets are categorized using a structured data schema covering (i) data fundamentals (e.g., size and license), (ii) data modalities (e.g., RGB and point cloud), (iii) annotation frameworks (e.g., bounding boxes), and (iv) downstream application domains (e.g., progress tracking). This study synthesizes these findings into an open-source catalog, OpenConstruction, supporting data-driven method development. Furthermore, the study discusses several critical limitations in the existing construction dataset landscape and presents a roadmap for future data infrastructure anchored in the Findability, Accessibility, Interoperability, and Reusability (FAIR) principles. By reviewing the current landscape and outlining strategic priorities, this study supports the advancement of data-centric solutions in the construction sector.

☆ TACR-YOLO: A Real-time Detection Framework for Abnormal Human Behaviors Enhanced with Coordinate and Task-Aware Representations

Xinyi Yin, Wenbo Yuan, Xuecheng Wu, Liangyu Fu, Danlei Huang

Abnormal Human Behavior Detection (AHBD) under special scenarios is becoming increasingly crucial. While YOLO-based detection methods excel in real-time tasks, they remain hindered by challenges including small objects, task conflicts, and multi-scale fusion in AHBD. To tackle them, we propose TACR-YOLO, a new real-time framework for AHBD. We introduce a Coordinate Attention Module to enhance small object detection, a Task-Aware Attention Module to deal with classification-regression conflicts, and a Strengthen Neck Network for refined multi-scale fusion, respectively. In addition, we optimize Anchor Box sizes using K-means clustering and deploy DIoU-Loss to improve bounding box regression. The Personnel Anomalous Behavior Detection (PABD) dataset, which includes 8,529 samples across four behavior categories, is also presented. Extensive experimental results indicate that TACR-YOLO achieves 91.92% mAP on PABD, with competitive speed and robustness. Ablation studies highlight the contribution of each improvement. This work provides new insights for abnormal behavior detection under special scenarios, advancing its progress.

comment: 8 pages, 4 figures, accepted by IJCNN 2025

☆ SPG: Style-Prompting Guidance for Style-Specific Content Creation

Qian Liang, Zichong Chen, Yang Zhou, Hui Huang

Although recent text-to-image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style-Prompting Guidance (SPG), a novel sampling strategy for style-specific image generation. SPG constructs a style noise vector and leverages its directional deviation from unconditional noise to guide the diffusion process toward the target style distribution. By integrating SPG with Classifier-Free Guidance (CFG), our method achieves both semantic fidelity and style consistency. SPG is simple, robust, and compatible with controllable frameworks like ControlNet and IPAdapter, making it practical and widely applicable. Extensive experiments demonstrate the effectiveness and generality of our approach compared to state-of-the-art methods. Code is available at https://github.com/Rumbling281441/SPG.

comment: Accepted to the Journal track of Pacific Graphics 2025

☆ CoFi: A Fast Coarse-to-Fine Few-Shot Pipeline for Glomerular Basement Membrane Segmentation

Hongjin Fang, Daniel Reisenbüchler, Kenji Ikemura, Mert R. Sabuncu, Yihe Yang, Ruining Deng

Accurate segmentation of the glomerular basement membrane (GBM) in electron microscopy (EM) images is fundamental for quantifying membrane thickness and supporting the diagnosis of various kidney diseases. While supervised deep learning approaches achieve high segmentation accuracy, their reliance on extensive pixel-level annotation renders them impractical for clinical workflows. Few-shot learning can reduce this annotation burden but often struggles to capture the fine structural details necessary for GBM analysis. In this study, we introduce CoFi, a fast and efficient coarse-to-fine few-shot segmentation pipeline designed for GBM delineation in EM images. CoFi first trains a lightweight neural network using only three annotated images to produce an initial coarse segmentation mask. This mask is then automatically processed to generate high-quality point prompts with morphology-aware pruning, which are subsequently used to guide SAM in refining the segmentation. The proposed method achieved exceptional GBM segmentation performance, with a Dice coefficient of 74.54% and an inference speed of 1.9 FPS. We demonstrate that CoFi not only alleviates the annotation and computational burdens associated with conventional methods, but also achieves accurate and reliable segmentation results. The pipeline's speed and annotation efficiency make it well-suited for research and hold strong potential for clinical applications in renal pathology. The pipeline is publicly available at: https://github.com/ddrrnn123/CoFi.

☆ Data-Driven Deepfake Image Detection Method -- The 2024 Global Deepfake Image Detection Challenge

Xiaoya Zhu, Yibing Nan, Shiguo Lian

With the rapid development of technology in the field of AI, deepfake technology has emerged as a double-edged sword. It has not only created a large amount of AI-generated content but also posed unprecedented challenges to digital security. The task of the competition is to determine whether a face image is a Deepfake image and output its probability score of being a Deepfake image. In the image track competition, our approach is based on the Swin Transformer V2-B classification network. And online data augmentation and offline sample generation methods are employed to enrich the diversity of training samples and increase the generalization ability of the model. Finally, we got the award of excellence in Deepfake image detection.

☆ Subcortical Masks Generation in CT Images via Ensemble-Based Cross-Domain Label Transfer

Augustine X. W. Lee, Pak-Hei Yeung, Jagath C. Rajapakse

Subcortical segmentation in neuroimages plays an important role in understanding brain anatomy and facilitating computer-aided diagnosis of traumatic brain injuries and neurodegenerative disorders. However, training accurate automatic models requires large amounts of labelled data. Despite the availability of publicly available subcortical segmentation datasets for Magnetic Resonance Imaging (MRI), a significant gap exists for Computed Tomography (CT). This paper proposes an automatic ensemble framework to generate high-quality subcortical segmentation labels for CT scans by leveraging existing MRI-based models. We introduce a robust ensembling pipeline to integrate them and apply it to unannotated paired MRI-CT data, resulting in a comprehensive CT subcortical segmentation dataset. Extensive experiments on multiple public datasets demonstrate the superior performance of our proposed framework. Furthermore, using our generated CT dataset, we train segmentation models that achieve improved performance on related segmentation tasks. To facilitate future research, we make our source code, generated dataset, and trained models publicly available at https://github.com/SCSE-Biomedical-Computing-Group/CT-Subcortical-Segmentation, marking the first open-source release for CT subcortical segmentation to the best of our knowledge.

☆ Inside Knowledge: Graph-based Path Generation with Explainable Data Augmentation and Curriculum Learning for Visual Indoor Navigation

Daniel Airinei, Elena Burceanu, Marius Leordeanu

Indoor navigation is a difficult task, as it generally comes with poor GPS access, forcing solutions to rely on other sources of information. While significant progress continues to be made in this area, deployment to production applications is still lacking, given the complexity and additional requirements of current solutions. Here, we introduce an efficient, real-time and easily deployable deep learning approach, based on visual input only, that can predict the direction towards a target from images captured by a mobile device. Our technical approach, based on a novel graph-based path generation method, combined with explainable data augmentation and curriculum learning, includes contributions that make the process of data collection, annotation and training, as automatic as possible, efficient and robust. On the practical side, we introduce a novel largescale dataset, with video footage inside a relatively large shopping mall, in which each frame is annotated with the correct next direction towards different specific target destinations. Different from current methods, ours relies solely on vision, avoiding the need of special sensors, additional markers placed along the path, knowledge of the scene map or internet access. We also created an easy to use application for Android, which we plan to make publicly available. We make all our data and code available along with visual demos on our project site

comment: Accepted at the International Conference on Computer Vision Workshops 2025

☆ MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation

Qian Liang, Yujia Wu, Kuncheng Li, Jiwei Wei, Shiyuan He, Jinyu Guo, Ning Xie

Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation. Specifically, we structure personalization as an integrated visual reasoning and generation process: (1) grounding subject concepts by interpreting and understanding user-provided images and contextual cues, and (2) generating personalized images conditioned on both the extracted subject representations and user prompts. To further enhance the reasoning capability, we adopt Grouped Reward Proximal Policy Optimization (GRPO) to explicitly align the generation. Experiments demonstrate that MM-R1 unleashes the personalization capability of unified MLLMs to generate images with high subject fidelity and strong text alignment in a zero-shot manner.

☆ Robust Convolution Neural ODEs via Contractivity-promoting regularization

Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate

Neural networks can be fragile to input noise and adversarial attacks. In this work, we consider Convolutional Neural Ordinary Differential Equations (NODEs), a family of continuous-depth neural networks represented by dynamical systems, and propose to use contraction theory to improve their robustness. For a contractive dynamical system two trajectories starting from different initial conditions converge to each other exponentially fast. Contractive Convolutional NODEs can enjoy increased robustness as slight perturbations of the features do not cause a significant change in the output. Contractivity can be induced during training by using a regularization term involving the Jacobian of the system dynamics. To reduce the computational burden, we show that it can also be promoted using carefully selected weight regularization terms for a class of NODEs with slope-restricted activation functions. The performance of the proposed regularizers is illustrated through benchmark image classification tasks on MNIST and FashionMNIST datasets, where images are corrupted by different kinds of noise and attacks.

comment: Accepted in IEEE CDC2025, Rio de Janeiro, Brazil

☆ Remove360: Benchmarking Residuals After Object Removal in 3D Gaussian Splatting

Simona Kocour, Assia Benbihi, Torsten Sattler

Understanding what semantic information persists after object removal is critical for privacy-preserving 3D reconstruction and editable scene representations. In this work, we introduce a novel benchmark and evaluation framework to measure semantic residuals, the unintended semantic traces left behind, after object removal in 3D Gaussian Splatting. We conduct experiments across a diverse set of indoor and outdoor scenes, showing that current methods can preserve semantic information despite the absence of visual geometry. We also release Remove360, a dataset of pre/post-removal RGB images and object-level masks captured in real-world environments. While prior datasets have focused on isolated object instances, Remove360 covers a broader and more complex range of indoor and outdoor scenes, enabling evaluation of object removal in the context of full-scene representations. Given ground truth images of a scene before and after object removal, we assess whether we can truly eliminate semantic presence, and if downstream models can still infer what was removed. Our findings reveal critical limitations in current 3D object removal techniques and underscore the need for more robust solutions capable of handling real-world complexity. The evaluation framework is available at github.com/spatial-intelligence-ai/Remove360.git. Data are available at huggingface.co/datasets/simkoc/Remove360.

comment: arXiv admin note: substantial text overlap with arXiv:2503.17574

☆ ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving

Jingyu Li, Bozhou Zhang, Xin Jin, Jiankang Deng, Xiatian Zhu, Li Zhang

Autonomous driving requires rich contextual comprehension and precise predictive reasoning to navigate dynamic and complex environments safely. Vision-Language Models (VLMs) and Driving World Models (DWMs) have independently emerged as powerful recipes addressing different aspects of this challenge. VLMs provide interpretability and robust action prediction through their ability to understand multi-modal context, while DWMs excel in generating detailed and plausible future driving scenarios essential for proactive planning. Integrating VLMs with DWMs is an intuitive, promising, yet understudied strategy to exploit the complementary strengths of accurate behavioral prediction and realistic scene generation. Nevertheless, this integration presents notable challenges, particularly in effectively connecting action-level decisions with high-fidelity pixel-level predictions and maintaining computational efficiency. In this paper, we propose ImagiDrive, a novel end-to-end autonomous driving framework that integrates a VLM-based driving agent with a DWM-based scene imaginer to form a unified imagination-and-planning loop. The driving agent predicts initial driving trajectories based on multi-modal inputs, guiding the scene imaginer to generate corresponding future scenarios. These imagined scenarios are subsequently utilized to iteratively refine the driving agent's planning decisions. To address efficiency and predictive accuracy challenges inherent in this integration, we introduce an early stopping mechanism and a trajectory selection strategy. Extensive experimental validation on the nuScenes and NAVSIM datasets demonstrates the robustness and superiority of ImagiDrive over previous alternatives under both open-loop and closed-loop conditions.

☆ Training-free Dimensionality Reduction via Feature Truncation: Enhancing Efficiency in Privacy-preserving Multi-Biometric Systems

Florian Bayer, Maximilian Russo, Christian Rathgeb

Biometric recognition is widely used, making the privacy and security of extracted templates a critical concern. Biometric Template Protection schemes, especially those utilizing Homomorphic Encryption, introduce significant computational challenges due to increased workload. Recent advances in deep neural networks have enabled state-of-the-art feature extraction for face, fingerprint, and iris modalities. The ubiquity and affordability of biometric sensors further facilitate multi-modal fusion, which can enhance security by combining features from different modalities. This work investigates the biometric performance of reduced multi-biometric template sizes. Experiments are conducted on an in-house virtual multi-biometric database, derived from DNN-extracted features for face, fingerprint, and iris, using the FRGC, MCYT, and CASIA databases. The evaluated approaches are (i) explainable and straightforward to implement under encryption, (ii) training-free, and (iii) capable of generalization. Dimensionality reduction of feature vectors leads to fewer operations in the Homomorphic Encryption (HE) domain, enabling more efficient encrypted processing while maintaining biometric accuracy and security at a level equivalent to or exceeding single-biometric recognition. Our results demonstrate that, by fusing feature vectors from multiple modalities, template size can be reduced by 67 % with no loss in Equal Error Rate (EER) compared to the best-performing single modality.

☆ SelfAdapt: Unsupervised Domain Adaptation of Cell Segmentation Models

Fabian H. Reith, Jannik Franzen, Dinesh R. Palli, J. Lorenz Rumberger, Dagmar Kainmueller

Deep neural networks have become the go-to method for biomedical instance segmentation. Generalist models like Cellpose demonstrate state-of-the-art performance across diverse cellular data, though their effectiveness often degrades on domains that differ from their training data. While supervised fine-tuning can address this limitation, it requires annotated data that may not be readily available. We propose SelfAdapt, a method that enables the adaptation of pre-trained cell segmentation models without the need for labels. Our approach builds upon student-teacher augmentation consistency training, introducing L2-SP regularization and label-free stopping criteria. We evaluate our method on the LiveCell and TissueNet datasets, demonstrating relative improvements in AP0.5 of up to 29.64% over baseline Cellpose. Additionally, we show that our unsupervised adaptation can further improve models that were previously fine-tuned with supervision. We release SelfAdapt as an easy-to-use extension of the Cellpose framework. The code for our method is publicly available at https: //github.com/Kainmueller-Lab/self_adapt.

comment: 8 pages, 3 figures. To appear in the proceedings of the BioImage Computing (BIC) Workshop @ ICCVW 2025. This is the accepted author manuscript (camera-ready version)

☆ RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator

Zhiming Liu, Nantheera Anantrasirichai

Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. Current state-of-the-art methods are based on transformer and 3D architectures and require multi-frame input, but their large computational cost and memory usage limit real-time deployment, especially in resource-constrained scenarios. In this work, we propose RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator, designed for efficient and temporally consistent video restoration under AT conditions. RMFAT adopts a lightweight recurrent framework that restores each frame using only two inputs at a time, significantly reducing temporal window size and computational burden. It further integrates multi-scale feature encoding and decoding with temporal warping modules at both encoder and decoder stages to enhance spatial detail and temporal coherence. Extensive experiments on synthetic and real-world atmospheric turbulence datasets demonstrate that RMFAT not only outperforms existing methods in terms of clarity restoration (with nearly a 9\% improvement in SSIM) but also achieves significantly improved inference speed (more than a fourfold reduction in runtime), making it particularly suitable for real-time atmospheric turbulence suppression tasks.

☆ LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution

Yinggan Tang, Quanwei Hu

The success of self-attention (SA) in Transformer demonstrates the importance of non-local information to image super-resolution (SR), but the huge computing power required makes it difficult to implement lightweight models. To solve this problem, we propose a pure convolutional neural network (CNN) model, LKFMixer, which utilizes large convolutional kernel to simulate the ability of self-attention to capture non-local features. Specifically, we increase the kernel size to 31 to obtain the larger receptive field as possible, and reduce the parameters and computations by coordinate decomposition. Meanwhile, a spatial feature modulation block (SFMB) is designed to enhance the focus of feature information on both spatial and channel dimension. In addition, by introducing feature selection block (FSB), the model can adaptively adjust the weights between local features and non-local features. Extensive experiments show that the proposed LKFMixer family outperform other state-of-the-art (SOTA) methods in terms of SR performance and reconstruction quality. In particular, compared with SwinIR-light on Manga109 dataset, LKFMixer-L achieves 0.6dB PSNR improvement at $\times$4 scale, while the inference speed is $\times$5 times faster. The code is available at https://github.com/Supereeeee/LKFMixer.

☆ Model Interpretability and Rationale Extraction by Input Mask Optimization

Marc Brinner, Sina Zarriess

Concurrent to the rapid progress in the development of neural-network based models in areas like natural language processing and computer vision, the need for creating explanations for the predictions of these black-box models has risen steadily. We propose a new method to generate extractive explanations for predictions made by neural networks, that is based on masking parts of the input which the model does not consider to be indicative of the respective class. The masking is done using gradient-based optimization combined with a new regularization scheme that enforces sufficiency, comprehensiveness and compactness of the generated explanation, three properties that are known to be desirable from the related field of rationale extraction in natural language processing. In this way, we bridge the gap between model interpretability and rationale extraction, thereby proving that the latter of which can be performed without training a specialized model, only on the basis of a trained classifier. We further apply the same method to image inputs and obtain high quality explanations for image classifications, which indicates that the conditions proposed for rationale extraction in natural language processing are more broadly applicable to different input types.

☆ G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

Ramil Khafizov, Artem Komarichev, Ruslan Rakhimov, Peter Wonka, Evgeny Burnaev

We introduce G-CUT3R, a novel feed-forward approach for guided 3D scene reconstruction that enhances the CUT3R model by integrating prior information. Unlike existing feed-forward methods that rely solely on input images, our method leverages auxiliary data, such as depth, camera calibrations, or camera positions, commonly available in real-world scenarios. We propose a lightweight modification to CUT3R, incorporating a dedicated encoder for each modality to extract features, which are fused with RGB image tokens via zero convolution. This flexible design enables seamless integration of any combination of prior information during inference. Evaluated across multiple benchmarks, including 3D reconstruction and other multi-view tasks, our approach demonstrates significant performance improvements, showing its ability to effectively utilize available priors while maintaining compatibility with varying input modalities.

☆ Unified Knowledge Distillation Framework: Fine-Grained Alignment and Geometric Relationship Preservation for Deep Face Recognition

Durgesh Mishra, Rishabh Uikey

Knowledge Distillation is crucial for optimizing face recognition models for deployment in computationally limited settings, such as edge devices. Traditional KD methods, such as Raw L2 Feature Distillation or Feature Consistency loss, often fail to capture both fine-grained instance-level details and complex relational structures, leading to suboptimal performance. We propose a unified approach that integrates two novel loss functions, Instance-Level Embedding Distillation and Relation-Based Pairwise Similarity Distillation. Instance-Level Embedding Distillation focuses on aligning individual feature embeddings by leveraging a dynamic hard mining strategy, thereby enhancing learning from challenging examples. Relation-Based Pairwise Similarity Distillation captures relational information through pairwise similarity relationships, employing a memory bank mechanism and a sample mining strategy. This unified framework ensures both effective instance-level alignment and preservation of geometric relationships between samples, leading to a more comprehensive distillation process. Our unified framework outperforms state-of-the-art distillation methods across multiple benchmark face recognition datasets, as demonstrated by extensive experimental evaluations. Interestingly, when using strong teacher networks compared to the student, our unified KD enables the student to even surpass the teacher's accuracy.

comment: The paper spans a total of 14 pages, 10 pages for the main content (including references) and 4 pages for the appendix. The main paper contains 3 figures and 1 table, while the appendix includes 1 pseudo-code algorithm and 4 tables. The work was recently accepted for publication at IJCB 2025

☆ AnatoMaskGAN: GNN-Driven Slice Feature Fusion and Noise Augmentation for Medical Semantic Image Synthesis

Zonglin Wu, Yule Xue, Qianxiang Hu, Yaoyao Feng, Yuqi Ma, Shanxiong Chen

Medical semantic-mask synthesis boosts data augmentation and analysis, yet most GAN-based approaches still produce one-to-one images and lack spatial consistency in complex scans. To address this, we propose AnatoMaskGAN, a novel synthesis framework that embeds slice-related spatial features to precisely aggregate inter-slice contextual dependencies, introduces diverse image-augmentation strategies, and optimizes deep feature learning to improve performance on complex medical images. Specifically, we design a GNN-based strongly correlated slice-feature fusion module to model spatial relationships between slices and integrate contextual information from neighboring slices, thereby capturing anatomical details more comprehensively; we introduce a three-dimensional spatial noise-injection strategy that weights and fuses spatial features with noise to enhance modeling of structural diversity; and we incorporate a grayscale-texture classifier to optimize grayscale distribution and texture representation during generation. Extensive experiments on the public L2R-OASIS and L2R-Abdomen CT datasets show that AnatoMaskGAN raises PSNR on L2R-OASIS to 26.50 dB (0.43 dB higher than the current state of the art) and achieves an SSIM of 0.8602 on L2R-Abdomen CT--a 0.48 percentage-point gain over the best model, demonstrating its superiority in reconstruction accuracy and perceptual quality. Ablation studies that successively remove the slice-feature fusion module, spatial 3D noise-injection strategy, and grayscale-texture classifier reveal that each component contributes significantly to PSNR, SSIM, and LPIPS, further confirming the independent value of each core design in enhancing reconstruction accuracy and perceptual quality.

comment: 8 pages

☆ Does the Skeleton-Recall Loss Really Work?

Devansh Arora, Nitin Kumar, Sukrit Gupta

Image segmentation is an important and widely performed task in computer vision. Accomplishing effective image segmentation in diverse settings often requires custom model architectures and loss functions. A set of models that specialize in segmenting thin tubular structures are topology preservation-based loss functions. These models often utilize a pixel skeletonization process claimed to generate more precise segmentation masks of thin tubes and better capture the structures that other models often miss. One such model, Skeleton Recall Loss (SRL) proposed by Kirchhoff et al.~\cite {kirchhoff2024srl}, was stated to produce state-of-the-art results on benchmark tubular datasets. In this work, we performed a theoretical analysis of the gradients for the SRL loss. Upon comparing the performance of the proposed method on some of the tubular datasets (used in the original work, along with some additional datasets), we found that the performance of SRL-based segmentation models did not exceed traditional baseline models. By providing both a theoretical explanation and empirical evidence, this work critically evaluates the limitations of topology-based loss functions, offering valuable insights for researchers aiming to develop more effective segmentation models for complex tubular structures.

☆ Leveraging the RETFound foundation model for optic disc segmentation in retinal images

Zhenyi Zhao, Muthu Rama Krishnan Mookiah, Emanuele Trucco

RETFound is a well-known foundation model (FM) developed for fundus camera and optical coherence tomography images. It has shown promising performance across multiple datasets in diagnosing diseases, both eye-specific and systemic, from retinal images. However, to our best knowledge, it has not been used for other tasks. We present the first adaptation of RETFound for optic disc segmentation, a ubiquitous and foundational task in retinal image analysis. The resulting segmentation system outperforms state-of-the-art, segmentation-specific baseline networks after training a head with only a very modest number of task-specific examples. We report and discuss results with four public datasets, IDRID, Drishti-GS, RIM-ONE-r3, and REFUGE, and a private dataset, GoDARTS, achieving about 96% Dice consistently across all datasets. Overall, our method obtains excellent performance in internal verification, domain generalization and domain adaptation, and exceeds most of the state-of-the-art baseline results. We discuss the results in the framework of the debate about FMs as alternatives to task-specific architectures. The code is available at: [link to be added after the paper is accepted]

☆ HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language Model

Zhenhao Zhang, Hanqing Wang, Xiangyu Zeng, Ziyu Cheng, Jiaxin Liu, Haoyu Yan, Zhirui Liu, Kaiyang Ji, Tianxiang Gui, Ke Hu, Kangyi Chen, Yahao Fan, Mokai Pan

Understanding and recognizing human-object interaction (HOI) is a pivotal application in AR/VR and robotics. Recent open-vocabulary HOI detection approaches depend exclusively on large language models for richer textual prompts, neglecting their inherent 3D spatial understanding capabilities. To address this shortcoming, we introduce HOID-R1, the first HOI detection framework that integrates chain-of-thought (CoT) guided supervised fine-tuning (SFT) with group relative policy optimization (GRPO) within a reinforcement learning (RL) paradigm. Specifically, we initially apply SFT to imbue the model with essential reasoning capabilities, forcing the model to articulate its thought process in the output. Subsequently, we integrate GRPO to leverage multi-reward signals for policy optimization, thereby enhancing alignment across diverse modalities. To mitigate hallucinations in the CoT reasoning, we introduce an "MLLM-as-a-judge" mechanism that supervises the CoT outputs, further improving generalization. Extensive experiments show that HOID-R1 achieves state-of-the-art performance on HOI detection benchmarks and outperforms existing methods in open-world generalization to novel scenarios.

☆ Semantically Guided Adversarial Testing of Vision Models Using Language Models

Katarzyna Filus, Jorge M. Cruz-Duarte

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to predict. Now, existing strategies typically rely on randomness, model predictions, or static semantic resources, limiting interpretability, reproducibility, or flexibility. This paper then proposes a semantics-guided framework for adversarial target selection using the cross-modal knowledge transfer from pretrained language and vision-language models. We evaluate several state-of-the-art models (BERT, TinyLLAMA, and CLIP) as similarity sources to select the most and least semantically related labels with respect to the ground truth, forming best- and worst-case adversarial scenarios. Our experiments on three vision models and five attack methods reveal that these models consistently render practical adversarial targets and surpass static lexical databases, such as WordNet, particularly for distant class relationships. We also observe that static testing of target labels offers a preliminary assessment of the effectiveness of similarity sources, \textit{a priori} testing. Our results corroborate the suitability of pretrained models for constructing interpretable, standardized, and scalable adversarial benchmarks across architectures and datasets.

comment: 12 pages, 4 figures, 3 tables. Submitted for peer review

☆ Cost-Effective Active Labeling for Data-Efficient Cervical Cell Classification

Yuanlin Liu, Zhihan Zhou, Mingqiang Wei, Youyi Song

Information on the number and category of cervical cells is crucial for the diagnosis of cervical cancer. However, existing classification methods capable of automatically measuring this information require the training dataset to be representative, which consumes an expensive or even unaffordable human cost. We herein propose active labeling that enables us to construct a representative training dataset using a much smaller human cost for data-efficient cervical cell classification. This cost-effective method efficiently leverages the classifier's uncertainty on the unlabeled cervical cell images to accurately select images that are most beneficial to label. With a fast estimation of the uncertainty, this new algorithm exhibits its validity and effectiveness in enhancing the representative ability of the constructed training dataset. The extensive empirical results confirm its efficacy again in navigating the usage of human cost, opening the avenue for data-efficient cervical cell classification.

comment: accepted by CW2025

☆ Index-Aligned Query Distillation for Transformer-based Incremental Object Detection

Mingxiao Ma, Shunyao Zhu, Guoliang Kang

Incremental object detection (IOD) aims to continuously expand the capability of a model to detect novel categories while preserving its performance on previously learned ones. When adopting a transformer-based detection model to perform IOD, catastrophic knowledge forgetting may inevitably occur, meaning the detection performance on previously learned categories may severely degenerate. Previous typical methods mainly rely on knowledge distillation (KD) to mitigate the catastrophic knowledge forgetting of transformer-based detection models. Specifically, they utilize Hungarian Matching to build a correspondence between the queries of the last-phase and current-phase detection models and align the classifier and regressor outputs between matched queries to avoid knowledge forgetting. However, we observe that in IOD task, Hungarian Matching is not a good choice. With Hungarian Matching, the query of the current-phase model may match different queries of the last-phase model at different iterations during KD. As a result, the knowledge encoded in each query may be reshaped towards new categories, leading to the forgetting of previously encoded knowledge of old categories. Based on our observations, we propose a new distillation approach named Index-Aligned Query Distillation (IAQD) for transformer-based IOD. Beyond using Hungarian Matching, IAQD establishes a correspondence between queries of the previous and current phase models that have the same index. Moreover, we perform index-aligned distillation only on partial queries which are critical for the detection of previous categories. In this way, IAQD largely preserves the previous semantic and spatial encoding capabilities without interfering with the learning of new categories. Extensive experiments on representative benchmarks demonstrate that IAQD effectively mitigates knowledge forgetting, achieving new state-of-the-art performance.

comment: 12 pages, 5 figures

☆ GANDiff FR: Hybrid GAN Diffusion Synthesis for Causal Bias Attribution in Face Recognition

Md Asgor Hossain Reaj, Rajan Das Gupta, Md Yeasin Rahat, Nafiz Fahad, Md Jawadul Hasan, Tze Hui Liew

We introduce GANDiff FR, the first synthetic framework that precisely controls demographic and environmental factors to measure, explain, and reduce bias with reproducible rigor. GANDiff FR unifies StyleGAN3-based identity-preserving generation with diffusion-based attribute control, enabling fine-grained manipulation of pose around 30 degrees, illumination (four directions), and expression (five levels) under ceteris paribus conditions. We synthesize 10,000 demographically balanced faces across five cohorts validated for realism via automated detection (98.2%) and human review (89%) to isolate and quantify bias drivers. Benchmarking ArcFace, CosFace, and AdaFace under matched operating points shows AdaFace reduces inter-group TPR disparity by 60% (2.5% vs. 6.3%), with illumination accounting for 42% of residual bias. Cross-dataset evaluation on RFW, BUPT, and CASIA WebFace confirms strong synthetic-to-real transfer (r 0.85). Despite around 20% computational overhead relative to pure GANs, GANDiff FR yields three times more attribute-conditioned variants, establishing a reproducible, regulation-aligned (EU AI Act) standard for fairness auditing. Code and data are released to support transparent, scalable bias evaluation.

comment: Accepted in ICCVDM '25

☆ Guiding WaveMamba with Frequency Maps for Image Debanding

Xinyi Wang, Smaranda Tasmoc, Nantheera Anantrasirichai, Angeliki Katsenou

Compression at low bitrates in modern codecs often introduces banding artifacts, especially in smooth regions such as skies. These artifacts degrade visual quality and are common in user-generated content due to repeated transcoding. We propose a banding restoration method that employs the Wavelet State Space Model and a frequency masking map to preserve high-frequency details. Furthermore, we provide a benchmark of open-source banding restoration methods and evaluate their performance on two public banding image datasets. Experimentation on the available datasets suggests that the proposed post-processing approach effectively suppresses banding compared to the state-of-the-art method (a DBI value of 0.082 on BAND-2k) while preserving image textures. Visual inspections of the results confirm this. Code and supplementary material are available at: https://github.com/xinyiW915/Debanding-PCS2025.

comment: 5 pages, 2 figures

☆ Noise Matters: Optimizing Matching Noise for Diffusion Classifiers

Yanghao Wang, Long Chen

Although today's pretrained discriminative vision-language models (e.g., CLIP) have demonstrated strong perception abilities, such as zero-shot image classification, they also suffer from the bag-of-words problem and spurious bias. To mitigate these problems, some pioneering studies leverage powerful generative models (e.g., pretrained diffusion models) to realize generalizable image classification, dubbed Diffusion Classifier (DC). Specifically, by randomly sampling a Gaussian noise, DC utilizes the differences of denoising effects with different category conditions to classify categories. Unfortunately, an inherent and notorious weakness of existing DCs is noise instability: different random sampled noises lead to significant performance changes. To achieve stable classification performance, existing DCs always ensemble the results of hundreds of sampled noises, which significantly reduces the classification speed. To this end, we firstly explore the role of noise in DC, and conclude that: there are some ``good noises'' that can relieve the instability. Meanwhile, we argue that these good noises should meet two principles: Frequency Matching and Spatial Matching. Regarding both principles, we propose a novel Noise Optimization method to learn matching (i.e., good) noise for DCs: NoOp. For frequency matching, NoOp first optimizes a dataset-specific noise: Given a dataset and a timestep t, optimize one randomly initialized parameterized noise. For Spatial Matching, NoOp trains a Meta-Network that adopts an image as input and outputs image-specific noise offset. The sum of optimized noise and noise offset will be used in DC to replace random noise. Extensive ablations on various datasets demonstrated the effectiveness of NoOp.

☆ Delving into Dynamic Scene Cue-Consistency for Robust 3D Multi-Object Tracking

Haonan Zhang, Xinyao Wang, Boxi Wu, Tu Zheng, Wang Yunhua, Zheng Yang

3D multi-object tracking is a critical and challenging task in the field of autonomous driving. A common paradigm relies on modeling individual object motion, e.g., Kalman filters, to predict trajectories. While effective in simple scenarios, this approach often struggles in crowded environments or with inaccurate detections, as it overlooks the rich geometric relationships between objects. This highlights the need to leverage spatial cues. However, existing geometry-aware methods can be susceptible to interference from irrelevant objects, leading to ambiguous features and incorrect associations. To address this, we propose focusing on cue-consistency: identifying and matching stable spatial patterns over time. We introduce the Dynamic Scene Cue-Consistency Tracker (DSC-Track) to implement this principle. Firstly, we design a unified spatiotemporal encoder using Point Pair Features (PPF) to learn discriminative trajectory embeddings while suppressing interference. Secondly, our cue-consistency transformer module explicitly aligns consistent feature representations between historical tracks and current detections. Finally, a dynamic update mechanism preserves salient spatiotemporal information for stable online tracking. Extensive experiments on the nuScenes and Waymo Open Datasets validate the effectiveness and robustness of our approach. On the nuScenes benchmark, for instance, our method achieves state-of-the-art performance, reaching 73.2% and 70.3% AMOTA on the validation and test sets, respectively.

☆ Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models

Yuchen Zhou, Jiayu Tang, Shuo Yang, Xiaoyan Xiao, Yuqin Dai, Wenhao Yang, Chao Gou, Xiaobo Xia, Tat-Seng Chua

Vision-Language Models (VLMs), exemplified by CLIP, have emerged as foundational for multimodal intelligence. However, their capacity for logical understanding remains significantly underexplored, resulting in critical ''logical blindspots'' that limit their reliability in practical applications. To systematically diagnose this, we introduce LogicBench, a comprehensive benchmark with over 50,000 vision-language pairs across 9 logical categories and 4 diverse scenarios: images, videos, anomaly detection, and medical diagnostics. Our evaluation reveals that existing VLMs, even the state-of-the-art ones, fall at over 40 accuracy points below human performance, particularly in challenging tasks like Causality and Conditionality, highlighting their reliance on surface semantics over critical logical structures. To bridge this gap, we propose LogicCLIP, a novel training framework designed to boost VLMs' logical sensitivity through advancements in both data generation and optimization objectives. LogicCLIP utilizes logic-aware data generation and a contrastive learning strategy that combines coarse-grained alignment, a fine-grained multiple-choice objective, and a novel logical structure-aware objective. Extensive experiments demonstrate LogicCLIP's substantial improvements in logical comprehension across all LogicBench domains, significantly outperforming baselines. Moreover, LogicCLIP retains, and often surpasses, competitive performance on general vision-language benchmarks, demonstrating that the enhanced logical understanding does not come at the expense of general alignment. We believe that LogicBench and LogicCLIP will be important resources for advancing VLM logical capabilities.

☆ Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval IJCAI 2025

Weijia Liu, Jiuxin Cao, Bo Miao, Zhiheng Fu, Xuelin Zhu, Jiawei Ge, Bo Liu, Mehwish Nasim, Ajmal Mian

Current text-driven Video Moment Retrieval (VMR) methods encode all video clips, including irrelevant ones, disrupting multimodal alignment and hindering optimization. To this end, we propose a denoise-then-retrieve paradigm that explicitly filters text-irrelevant clips from videos and then retrieves the target moment using purified multimodal representations. Following this paradigm, we introduce the Denoise-then-Retrieve Network (DRNet), comprising Text-Conditioned Denoising (TCD) and Text-Reconstruction Feedback (TRF) modules. TCD integrates cross-attention and structured state space blocks to dynamically identify noisy clips and produce a noise mask to purify multimodal video representations. TRF further distills a single query embedding from purified video representations and aligns it with the text embedding, serving as auxiliary supervision for denoising during training. Finally, we perform conditional retrieval using text embeddings on purified video representations for accurate VMR. Experiments on Charades-STA and QVHighlights demonstrate that our approach surpasses state-of-the-art methods on all metrics. Furthermore, our denoise-then-retrieve paradigm is adaptable and can be seamlessly integrated into advanced VMR models to boost performance.

comment: Accepted by IJCAI 2025

☆ Hyperspectral vs. RGB for Pedestrian Segmentation in Urban Driving Scenes: A Comparative Study

Jiarong Li, Imad Ali Shah, Enda Ward, Martin Glavin, Edward Jones, Brian Deegan

Pedestrian segmentation in automotive perception systems faces critical safety challenges due to metamerism in RGB imaging, where pedestrians and backgrounds appear visually indistinguishable.. This study investigates the potential of hyperspectral imaging (HSI) for enhanced pedestrian segmentation in urban driving scenarios using the Hyperspectral City v2 (H-City) dataset. We compared standard RGB against two dimensionality-reduction approaches by converting 128-channel HSI data into three-channel representations: Principal Component Analysis (PCA) and optimal band selection using Contrast Signal-to-Noise Ratio with Joint Mutual Information Maximization (CSNR-JMIM). Three semantic segmentation models were evaluated: U-Net, DeepLabV3+, and SegFormer. CSNR-JMIM consistently outperformed RGB with an average improvements of 1.44% in Intersection over Union (IoU) and 2.18% in F1-score for pedestrian segmentation. Rider segmentation showed similar gains with 1.43% IoU and 2.25% F1-score improvements. These improved performance results from enhanced spectral discrimination of optimally selected HSI bands effectively reducing false positives. This study demonstrates robust pedestrian segmentation through optimal HSI band selection, showing significant potential for safety-critical automotive applications.

comment: Submitted to IEEE ICVES, July, 2025

☆ Allen: Rethinking MAS Design through Step-Level Policy Autonomy

Qiangong Zhou, Zhiting Wang, Mingyou Yao, Zongyang Liu

We introduce a new Multi-Agent System (MAS) - Allen, designed to address two core challenges in current MAS design: (1) improve system's policy autonomy, empowering agents to dynamically adapt their behavioral strategies, and (2) achieving the trade-off between collaborative efficiency, task supervision, and human oversight in complex network topologies. Our core insight is to redefine the basic execution unit in the MAS, allowing agents to autonomously form different patterns by combining these units. We have constructed a four-tier state architecture (Task, Stage, Agent, Step) to constrain system behavior from both task-oriented and execution-oriented perspectives. This achieves a unification of topological optimization and controllable progress. Allen grants unprecedented Policy Autonomy, while making a trade-off for the controllability of the collaborative structure. The project code has been open source at: https://github.com/motern88/Allen

☆ Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent

Che Rin Yu, Daewon Chae, Dabin Seo, Sangwon Lee, Hyeongwoo Im, Jinkyu Kim

When humans perform everyday tasks, we naturally adjust our actions based on the current state of the environment. For instance, if we intend to put something into a drawer but notice it is closed, we open it first. However, many autonomous robots lack this adaptive awareness. They often follow pre-planned actions that may overlook subtle yet critical changes in the scene, which can result in actions being executed under outdated assumptions and eventual failure. While replanning is critical for robust autonomy, most existing methods respond only after failures occur, when recovery may be inefficient or infeasible. While proactive replanning holds promise for preventing failures in advance, current solutions often rely on manually designed rules and extensive supervision. In this work, we present a proactive replanning framework that detects and corrects failures at subtask boundaries by comparing scene graphs constructed from current RGB-D observations against reference graphs extracted from successful demonstrations. When the current scene fails to align with reference trajectories, a lightweight reasoning module is activated to diagnose the mismatch and adjust the plan. Experiments in the AI2-THOR simulator demonstrate that our approach detects semantic and spatial mismatches before execution failures occur, significantly improving task success and robustness.

☆ TimeMachine: Fine-Grained Facial Age Editing with Identity Preservation

Yilin Mi, Qixin Yan, Zheng-Peng Duan, Chunle Guo, Hubery Yin, Hao Liu, Chen Li, Chongyi Li

With the advancement of generative models, facial image editing has made significant progress. However, achieving fine-grained age editing while preserving personal identity remains a challenging task.In this paper, we propose TimeMachine, a novel diffusion-based framework that achieves accurate age editing while keeping identity features unchanged. To enable fine-grained age editing, we inject high-precision age information into the multi-cross attention module, which explicitly separates age-related and identity-related features. This design facilitates more accurate disentanglement of age attributes, thereby allowing precise and controllable manipulation of facial aging.Furthermore, we propose an Age Classifier Guidance (ACG) module that predicts age directly in the latent space, instead of performing denoising image reconstruction during training. By employing a lightweight module to incorporate age constraints, this design enhances age editing accuracy by modest increasing training cost. Additionally, to address the lack of large-scale, high-quality facial age datasets, we construct a HFFA dataset (High-quality Fine-grained Facial-Age dataset) which contains one million high-resolution images labeled with identity and facial attributes. Experimental results demonstrate that TimeMachine achieves state-of-the-art performance in fine-grained age editing while preserving identity consistency.

☆ Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction

Muzammil Khan, Enzo Kerkhof, Matteo Fusaglia, Koert Kuhlmann, Theo Ruers, Françoise J. Siepel

Accurate endoscope pose estimation and 3D tissue surface reconstruction significantly enhances monocular minimally invasive surgical procedures by enabling accurate navigation and improved spatial awareness. However, monocular endoscope pose estimation and tissue reconstruction face persistent challenges, including depth ambiguity, physiological tissue deformation, inconsistent endoscope motion, limited texture fidelity, and a restricted field of view. To overcome these limitations, a unified framework for monocular endoscopic tissue reconstruction that integrates scale-aware depth prediction with temporally-constrained perceptual refinement is presented. This framework incorporates a novel MAPIS-Depth module, which leverages Depth Pro for robust initialisation and Depth Anything for efficient per-frame depth prediction, in conjunction with L-BFGS-B optimisation, to generate pseudo-metric depth estimates. These estimates are temporally refined by computing pixel correspondences using RAFT and adaptively blending flow-warped frames based on LPIPS perceptual similarity, thereby reducing artefacts arising from physiological tissue deformation and motion. To ensure accurate registration of the synthesised pseudo-RGBD frames from MAPIS-Depth, a novel WEMA-RTDL module is integrated, optimising both rotation and translation. Finally, truncated signed distance function-based volumetric fusion and marching cubes are applied to extract a comprehensive 3D surface mesh. Evaluations on HEVD and SCARED, with ablation and comparative analyses, demonstrate the framework's robustness and superiority over state-of-the-art methods.

comment: 18 pages, 8 figures, 3 Tables, submitted to IEEE Access for review

☆ Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble

Jihang Wang, Dongcheng Zhao, Ruolin Chen, Qian Zhang, Yi Zeng

Spiking Neural Networks (SNNs) offer a promising direction for energy-efficient and brain-inspired computing, yet their vulnerability to adversarial perturbations remains poorly understood. In this work, we revisit the adversarial robustness of SNNs through the lens of temporal ensembling, treating the network as a collection of evolving sub-networks across discrete timesteps. This formulation uncovers two critical but underexplored challenges-the fragility of individual temporal sub-networks and the tendency for adversarial vulnerabilities to transfer across time. To overcome these limitations, we propose Robust Temporal self-Ensemble (RTE), a training framework that improves the robustness of each sub-network while reducing the temporal transferability of adversarial perturbations. RTE integrates both objectives into a unified loss and employs a stochastic sampling strategy for efficient optimization. Extensive experiments across multiple benchmarks demonstrate that RTE consistently outperforms existing training methods in robust-accuracy trade-off. Additional analyses reveal that RTE reshapes the internal robustness landscape of SNNs, leading to more resilient and temporally diversified decision boundaries. Our study highlights the importance of temporal structure in adversarial learning and offers a principled foundation for building robust spiking models.

☆ Probing the Representational Power of Sparse Autoencoders in Vision Models

Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from the high-dimensional internal representations of LLMs. Despite their popularity with language models, SAEs remain understudied in the visual domain. In this work, we provide an extensive evaluation the representational power of SAEs for vision models using a broad range of image-based tasks. Our experimental results demonstrate that SAE features are semantically meaningful, improve out-of-distribution generalization, and enable controllable generation across three vision model architectures: vision embedding models, multi-modal LMMs and diffusion models. In vision embedding models, we find that learned SAE features can be used for OOD detection and provide evidence that they recover the ontological structure of the underlying model. For diffusion models, we demonstrate that SAEs enable semantic steering through text encoder manipulation and develop an automated pipeline for discovering human-interpretable attributes. Finally, we conduct exploratory experiments on multi-modal LLMs, finding evidence that SAE features reveal shared representations across vision and language modalities. Our study provides a foundation for SAE evaluation in vision models, highlighting their strong potential improving interpretability, generalization, and steerability in the visual domain.

comment: ICCV 2025 Findings

☆ Enhancing Supervised Composed Image Retrieval via Reasoning-Augmented Representation Engineering

Jun Li, Kai Li, Shaoguo Liu, Tingting Gao

Composed Image Retrieval (CIR) presents a significant challenge as it requires jointly understanding a reference image and a modified textual instruction to find relevant target images. Some existing methods attempt to use a two-stage approach to further refine retrieval results. However, this often requires additional training of a ranking model. Despite the success of Chain-of-Thought (CoT) techniques in reducing training costs for language models, their application in CIR tasks remains limited -- compressing visual information into text or relying on elaborate prompt designs. Besides, existing works only utilize it for zero-shot CIR, as it is challenging to achieve satisfactory results in supervised CIR with a well-trained model. In this work, we proposed a framework that includes the Pyramid Matching Model with Training-Free Refinement (PMTFR) to address these challenges. Through a simple but effective module called Pyramid Patcher, we enhanced the Pyramid Matching Model's understanding of visual information at different granularities. Inspired by representation engineering, we extracted representations from COT data and injected them into the LVLMs. This approach allowed us to obtain refined retrieval scores in the Training-Free Refinement paradigm without relying on explicit textual reasoning, further enhancing performance. Extensive experiments on CIR benchmarks demonstrate that PMTFR surpasses state-of-the-art methods in supervised CIR tasks. The code will be made public.

☆ Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds

Pei He, Lingling Li, Licheng Jiao, Ronghua Shang, Fang Liu, Shuang Wang, Xu Liu, Wenping Ma

Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global geometric patterns in point clouds while ignoring the category-level distribution and alignment. In this paper, a category-level geometry learning framework is proposed to explore the domain-invariant geometric features for domain generalized 3D semantic segmentation. Specifically, Category-level Geometry Embedding (CGE) is proposed to perceive the fine-grained geometric properties of point cloud features, which constructs the geometric properties of each class and couples geometric embedding to semantic learning. Secondly, Geometric Consistent Learning (GCL) is proposed to simulate the latent 3D distribution and align the category-level geometric embeddings, allowing the model to focus on the geometric invariant information to improve generalization. Experimental results verify the effectiveness of the proposed method, which has very competitive segmentation accuracy compared with the state-of-the-art domain generalized point cloud methods.

comment: to be published in International Conference on Computer Vision, ICCV 2025

☆ Vision-Language Models display a strong gender bias

Aiswarya Konavoor, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat

Vision-language models (VLM) align images and text in a shared representation space that is useful for retrieval and zero-shot transfer. Yet, this alignment can encode and amplify social stereotypes in subtle ways that are not obvious from standard accuracy metrics. In this study, we test whether the contrastive vision-language encoder exhibits gender-linked associations when it places embeddings of face images near embeddings of short phrases that describe occupations and activities. We assemble a dataset of 220 face photographs split by perceived binary gender and a set of 150 unique statements distributed across six categories covering emotional labor, cognitive labor, domestic labor, technical labor, professional roles, and physical labor. We compute unit-norm image embeddings for every face and unit-norm text embeddings for every statement, then define a statement-level association score as the difference between the mean cosine similarity to the male set and the mean cosine similarity to the female set, where positive values indicate stronger association with the male set and negative values indicate stronger association with the female set. We attach bootstrap confidence intervals by resampling images within each gender group, aggregate by category with a separate bootstrap over statements, and run a label-swap null model that estimates the level of mean absolute association we would expect if no gender structure were present. The outcome is a statement-wise and category-wise map of gender associations in a contrastive vision-language space, accompanied by uncertainty, simple sanity checks, and a robust gender bias evaluation framework.

☆ Temporally-Similar Structure-Aware Spatiotemporal Fusion of Satellite Images

Ryosuke Isono, Shunsuke Ono

This paper proposes a novel spatiotemporal (ST) fusion framework for satellite images, named Temporally-Similar Structure-Aware ST fusion (TSSTF). ST fusion is a promising approach to address the trade-off between the spatial and temporal resolution of satellite images. In real-world scenarios, observed satellite images are severely degraded by noise due to measurement equipment and environmental conditions. Consequently, some recent studies have focused on enhancing the robustness of ST fusion methods against noise. However, existing noise-robust ST fusion approaches often fail to capture fine spatial structure, leading to oversmoothing and artifacts. To address this issue, TSSTF introduces two key mechanisms: Temporally-Guided Total Variation (TGTV) and Temporally-Guided Edge Constraint (TGEC). TGTV is a novel regularization function that promotes spatial piecewise smoothness while preserving structural details, guided by a reference high spatial resolution image acquired on a nearby date. TGEC enforces consistency in edge locations between two temporally adjacent images, while allowing for spectral variations. We formulate the ST fusion task as a constrained optimization problem incorporating TGTV and TGEC, and develop an efficient algorithm based on a preconditioned primal-dual splitting method. Experimental results demonstrate that TSSTF performs comparably to state-of-the-art methods under noise-free conditions and outperforms them under noisy conditions. Additionally, we provide a comprehensive set of recommended parameter values that consistently yield high performance across diverse target regions and noise conditions, aiming to enhance reproducibility and practical utility.

comment: Submitted to IEEE Transactions on Geoscience and Remote Sensing. arXiv admin note: text overlap with arXiv:2308.00500

☆ Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception

Junjie Wang, Keyu Chen, Yulin Li, Bin Chen, Hengshuang Zhao, Xiaojuan Qi, Zhuotao Tian

Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have shown promise in open-vocabulary tasks, their direct application to dense perception often leads to suboptimal performance due to limitations in local feature representation. In this work, we present our observation that CLIP's image tokens struggle to effectively aggregate information from spatially or semantically related regions, resulting in features that lack local discriminability and spatial consistency. To address this issue, we propose DeCLIP, a novel framework that enhances CLIP by decoupling the self-attention module to obtain ``content'' and ``context'' features respectively. \revise{The context features are enhanced by jointly distilling semantic correlations from Vision Foundation Models (VFMs) and object integrity cues from diffusion models, thereby enhancing spatial consistency. In parallel, the content features are aligned with image crop representations and constrained by region correlations from VFMs to improve local discriminability. Extensive experiments demonstrate that DeCLIP establishes a solid foundation for open-vocabulary dense perception, consistently achieving state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.} Code is available at https://github.com/xiaomoguhz/DeCLIP

comment: arXiv admin note: text overlap with arXiv:2505.04410

☆ FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

MengChao Wang, Qiang Wang, Fan Jiang, Mu Xu

Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync accuracy, and visual quality. This is due to the difficulty of optimizing among competing preference objectives, which often conflict with one another, and the scarcity of large-scale, high-quality datasets with multidimensional preference annotations. To address these, we first introduce Talking-Critic, a multimodal reward model that learns human-aligned reward functions to quantify how well generated videos satisfy multidimensional expectations. Leveraging this model, we curate Talking-NSQ, a large-scale multidimensional human preference dataset containing 410K preference pairs. Finally, we propose Timestep-Layer adaptive multi-expert Preference Optimization (TLPO), a novel framework for aligning diffusion-based portrait animation models with fine-grained, multidimensional preferences. TLPO decouples preferences into specialized expert modules, which are then fused across timesteps and network layers, enabling comprehensive, fine-grained enhancement across all dimensions without mutual interference. Experiments demonstrate that Talking-Critic significantly outperforms existing methods in aligning with human preference ratings. Meanwhile, TLPO achieves substantial improvements over baseline models in lip-sync accuracy, motion naturalness, and visual quality, exhibiting superior performance in both qualitative and quantitative evaluations. Ours project page: https://fantasy-amap.github.io/fantasy-talking2/

comment: https://fantasy-amap.github.io/fantasy-talking2/

☆ A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving

Jialin Li, Shuqi Wu, Ning Wang

Re-Identification (ReID) is a critical technology in intelligent perception systems, especially within autonomous driving, where onboard cameras must identify pedestrians across views and time in real-time to support safe navigation and trajectory prediction. However, the presence of uncertain or missing input modalities--such as RGB, infrared, sketches, or textual descriptions--poses significant challenges to conventional ReID approaches. While large-scale pre-trained models offer strong multimodal semantic modeling capabilities, their computational overhead limits practical deployment in resource-constrained environments. To address these challenges, we propose a lightweight Uncertainty Modal Modeling (UMM) framework, which integrates a multimodal token mapper, synthetic modality augmentation strategy, and cross-modal cue interactive learner. Together, these components enable unified feature representation, mitigate the impact of missing modalities, and extract complementary information across different data types. Additionally, UMM leverages CLIP's vision-language alignment ability to fuse multimodal inputs efficiently without extensive finetuning. Experimental results demonstrate that UMM achieves strong robustness, generalization, and computational efficiency under uncertain modality conditions, offering a scalable and practical solution for pedestrian re-identification in autonomous driving scenarios.

☆ Fluid Dynamics and Domain Reconstruction from Noisy Flow Images Using Physics-Informed Neural Networks and Quasi-Conformal Mapping

Han Zhang, Xue-Cheng Tai, Jean-Michel Morel, Raymond H. Chan

Blood flow imaging provides important information for hemodynamic behavior within the vascular system and plays an essential role in medical diagnosis and treatment planning. However, obtaining high-quality flow images remains a significant challenge. In this work, we address the problem of denoising flow images that may suffer from artifacts due to short acquisition times or device-induced errors. We formulate this task as an optimization problem, where the objective is to minimize the discrepancy between the modeled velocity field, constrained to satisfy the Navier-Stokes equations, and the observed noisy velocity data. To solve this problem, we decompose it into two subproblems: a fluid subproblem and a geometry subproblem. The fluid subproblem leverages a Physics-Informed Neural Network to reconstruct the velocity field from noisy observations, assuming a fixed domain. The geometry subproblem aims to infer the underlying flow region by optimizing a quasi-conformal mapping that deforms a reference domain. These two subproblems are solved in an alternating Gauss-Seidel fashion, iteratively refining both the velocity field and the domain. Upon convergence, the framework yields a high-quality reconstruction of the flow image. We validate the proposed method through experiments on synthetic flow data in a converging channel geometry under varying levels of Gaussian noise, and on real-like flow data in an aortic geometry with signal-dependent noise. The results demonstrate the effectiveness and robustness of the approach. Additionally, ablation studies are conducted to assess the influence of key hyperparameters.

☆ A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network

Zhangjian Ji, Wenjin Zhang, Shaotong Qiao, Kai Feng, Yuhua Qian

Human pose estimation has been widely applied in the human-centric understanding and generation, but most existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. In order to obtain an accurate, robust yet lightweight human pose estimator, one feasible way is to transfer pose knowledge from a powerful teacher model to a less-parameterized student model by knowledge distillation. However, the traditional knowledge distillation framework does not fully explore the contextual information among human joints. Thus, in this paper, we propose a novel coarse-to-fine two-stage knowledge distillation framework for human pose estimation. In the first-stage distillation, we introduce the human joints structure loss to mine the structural information among human joints so as to transfer high-level semantic knowledge from the teacher model to the student model. In the second-stage distillation, we utilize an Image-Guided Progressive Graph Convolutional Network (IGP-GCN) to refine the initial human pose obtained from the first-stage distillation and supervise the training of the IGP-GCN in the progressive way by the final output pose of teacher model. The extensive experiments on the benchmark dataset: COCO keypoint and CrowdPose datasets, show that our proposed method performs favorably against lots of the existing state-of-the-art human pose estimation methods, especially for the more complex CrowdPose dataset, the performance improvement of our model is more significant.

☆ Efficient Image-to-Image Schrödinger Bridge for CT Field of View Extension

Zhenhao Li, Long Yang, Xiaojie Yin, Haijun Yu, Jiazhou Wang, Hongbin Han, Weigang Hu, Yixing Huang

Computed tomography (CT) is a cornerstone imaging modality for non-invasive, high-resolution visualization of internal anatomical structures. However, when the scanned object exceeds the scanner's field of view (FOV), projection data are truncated, resulting in incomplete reconstructions and pronounced artifacts near FOV boundaries. Conventional reconstruction algorithms struggle to recover accurate anatomy from such data, limiting clinical reliability. Deep learning approaches have been explored for FOV extension, with diffusion generative models representing the latest advances in image synthesis. Yet, conventional diffusion models are computationally demanding and slow at inference due to their iterative sampling process. To address these limitations, we propose an efficient CT FOV extension framework based on the image-to-image Schr\"odinger Bridge (I$^2$SB) diffusion model. Unlike traditional diffusion models that synthesize images from pure Gaussian noise, I$^2$SB learns a direct stochastic mapping between paired limited-FOV and extended-FOV images. This direct correspondence yields a more interpretable and traceable generative process, enhancing anatomical consistency and structural fidelity in reconstructions. I$^2$SB achieves superior quantitative performance, with root-mean-square error (RMSE) values of 49.8\,HU on simulated noisy data and 152.0HU on real data, outperforming state-of-the-art diffusion models such as conditional denoising diffusion probabilistic models (cDDPM) and patch-based diffusion methods. Moreover, its one-step inference enables reconstruction in just 0.19s per 2D slice, representing over a 700-fold speedup compared to cDDPM (135s) and surpassing diffusionGAN (0.58s), the second fastest. This combination of accuracy and efficiency makes I$^2$SB highly suitable for real-time or clinical deployment.

comment: 10 pages

☆ StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

Seungmi Lee, Kwan Yun, Junyong Noh

We introduce StyleMM, a novel framework that can construct a stylized 3D Morphable Model (3DMM) based on user-defined text descriptions specifying a target style. Building upon a pre-trained mesh deformation network and a texture generator for original 3DMM-based realistic human faces, our approach fine-tunes these models using stylized facial images generated via text-guided image-to-image (i2i) translation with a diffusion model, which serve as stylization targets for the rendered mesh. To prevent undesired changes in identity, facial alignment, or expressions during i2i translation, we introduce a stylization method that explicitly preserves the facial attributes of the source image. By maintaining these critical attributes during image stylization, the proposed approach ensures consistent 3D style transfer across the 3DMM parameter space through image-based training. Once trained, StyleMM enables feed-forward generation of stylized face meshes with explicit control over shape, expression, and texture parameters, producing meshes with consistent vertex connectivity and animatability. Quantitative and qualitative evaluations demonstrate that our approach outperforms state-of-the-art methods in terms of identity-level facial diversity and stylization capability. The code and videos are available at [kwanyun.github.io/stylemm_page](kwanyun.github.io/stylemm_page).

comment: Pacific graphics 2025, CGF, 15 pages

☆ UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning

Jiajin Guan, Haibo Mei, Bonan Zhang, Dan Liu, Yuanshuang Fu, Yue Zhang

Recent advances in vision-language models (VLMs) have demonstrated strong generalization in natural image tasks. However, their performance often degrades on unmanned aerial vehicle (UAV)-based aerial imagery, which features high resolution, complex spatial semantics, and strict real-time constraints. These challenges limit the applicability of general-purpose VLMs to structured aerial reasoning tasks. To address these challenges, we propose UAV-VL-R1, a lightweight VLM explicitly designed for aerial visual reasoning. It is trained using a hybrid method that combines supervised fine-tuning (SFT) and multi-stage reinforcement learning (RL). We leverage the group relative policy optimization (GRPO) algorithm to promote structured and interpretable reasoning through rule-guided rewards and intra-group policy alignment. To support model training and evaluation, we introduce a high-resolution visual question answering dataset named HRVQA-VL, which consists of 50,019 annotated samples covering eight UAV-relevant reasoning tasks, including object counting, transportation recognition, and spatial scene inference. Experimental results show that UAV-VL-R1 achieves a 48.17% higher zero-shot accuracy than the Qwen2-VL-2B-Instruct baseline and even outperforms its 72B-scale variant, which is 36x larger, on multiple tasks. Ablation studies reveal that while SFT improves semantic alignment, it may reduce reasoning diversity in mathematical tasks. GRPO-based RL compensates for this limitation by enhancing logical flexibility and the robustness of inference. Additionally, UAV-VL-R1 requires only 3.9GB of memory under FP16 inference and can be quantized to 2.5GB with INT8, supporting real-time deployment on resource-constrained UAV platforms.

☆ Generating Dialogues from Egocentric Instructional Videos for Task Assistance: Dataset, Method and Benchmark

Lavisha Aggarwal, Vikas Bahirwani, Lin Li, Andrea Colaco

Many everyday tasks ranging from fixing appliances, cooking recipes to car maintenance require expert knowledge, especially when tasks are complex and multi-step. Despite growing interest in AI agents, there is a scarcity of dialogue-video datasets grounded for real world task assistance. In this paper, we propose a simple yet effective approach that transforms single-person instructional videos into task-guidance two-person dialogues, aligned with fine grained steps and video-clips. Our fully automatic approach, powered by large language models, offers an efficient alternative to the substantial cost and effort required for human-assisted data collection. Using this technique, we build HowToDIV, a large-scale dataset containing 507 conversations, 6636 question-answer pairs and 24 hours of videoclips across diverse tasks in cooking, mechanics, and planting. Each session includes multi-turn conversation where an expert teaches a novice user how to perform a task step by step, while observing user's surrounding through a camera and microphone equipped wearable device. We establish the baseline benchmark performance on HowToDIV dataset through Gemma-3 model for future research on this new task of dialogues for procedural-task assistance.

☆ CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector

Abhinav Kumar, Yuliang Guo, Zhihao Zhang, Xinyu Huang, Liu Ren, Xiaoming Liu

Monocular 3D object detectors, while effective on data from one ego camera height, struggle with unseen or out-of-distribution camera heights. Existing methods often rely on Plucker embeddings, image transformations or data augmentation. This paper takes a step towards this understudied problem by first investigating the impact of camera height variations on state-of-the-art (SoTA) Mono3D models. With a systematic analysis on the extended CARLA dataset with multiple camera heights, we observe that depth estimation is a primary factor influencing performance under height variations. We mathematically prove and also empirically observe consistent negative and positive trends in mean depth error of regressed and ground-based depth models, respectively, under camera height changes. To mitigate this, we propose Camera Height Robust Monocular 3D Detector (CHARM3R), which averages both depth estimates within the model. CHARM3R improves generalization to unseen camera heights by more than $45\%$, achieving SoTA performance on the CARLA dataset. Codes and Models at https://github.com/abhi1kumar/CHARM3R

comment: ICCV 2025

☆ Versatile Video Tokenization with Generative 2D Gaussian Splatting

Zhenghao Chen, Zicong Chen, Lei Liu, Yiming Wu, Dong Xu

Video tokenization procedure is critical for a wide range of video processing tasks. Most existing approaches directly transform video into fixed-grid and patch-wise tokens, which exhibit limited versatility. Spatially, uniformly allocating a fixed number of tokens often leads to over-encoding in low-information regions. Temporally, reducing redundancy remains challenging without explicitly distinguishing between static and dynamic content. In this work, we propose the Gaussian Video Transformer (GVT), a versatile video tokenizer built upon a generative 2D Gaussian Splatting (2DGS) strategy. We first extract latent rigid features from a video clip and represent them with a set of 2D Gaussians generated by our proposed Spatio-Temporal Gaussian Embedding (STGE) mechanism in a feed-forward manner. Such generative 2D Gaussians not only enhance spatial adaptability by assigning higher (resp., lower) rendering weights to regions with higher (resp., lower) information content during rasterization, but also improve generalization by avoiding per-video optimization.To enhance the temporal versatility, we introduce a Gaussian Set Partitioning (GSP) strategy that separates the 2D Gaussians into static and dynamic sets, which explicitly model static content shared across different time-steps and dynamic content specific to each time-step, enabling a compact representation.We primarily evaluate GVT on the video reconstruction, while also assessing its performance on action recognition and compression using the UCF101, Kinetics, and DAVIS datasets. Extensive experiments demonstrate that GVT achieves a state-of-the-art video reconstruction quality, outperforms the baseline MAGVIT-v2 in action recognition, and delivers comparable compression performance.

☆ HistoViT: Vision Transformer for Accurate and Scalable Histopathological Cancer Diagnosis

Faisal Ahmed

Accurate and scalable cancer diagnosis remains a critical challenge in modern pathology, particularly for malignancies such as breast, prostate, bone, and cervical, which exhibit complex histological variability. In this study, we propose a transformer-based deep learning framework for multi-class tumor classification in histopathological images. Leveraging a fine-tuned Vision Transformer (ViT) architecture, our method addresses key limitations of conventional convolutional neural networks, offering improved performance, reduced preprocessing requirements, and enhanced scalability across tissue types. To adapt the model for histopathological cancer images, we implement a streamlined preprocessing pipeline that converts tiled whole-slide images into PyTorch tensors and standardizes them through data normalization. This ensures compatibility with the ViT architecture and enhances both convergence stability and overall classification performance. We evaluate our model on four benchmark datasets: ICIAR2018 (breast), SICAPv2 (prostate), UT-Osteosarcoma (bone), and SipakMed (cervical) dataset -- demonstrating consistent outperformance over existing deep learning methods. Our approach achieves classification accuracies of 99.32%, 96.92%, 95.28%, and 96.94% for breast, prostate, bone, and cervical cancers respectively, with area under the ROC curve (AUC) scores exceeding 99% across all datasets. These results confirm the robustness, generalizability, and clinical potential of transformer-based architectures in digital pathology. Our work represents a significant advancement toward reliable, automated, and interpretable cancer diagnosis systems that can alleviate diagnostic burdens and improve healthcare outcomes.

comment: 13 pages, 3 Figures

☆ Fine-Grained VLM Fine-tuning via Latent Hierarchical Adapter Learning

Yumiao Zhao, Bo Jiang, Yuhe Ding, Xiao Wang, Jin Tang, Bin Luo

Adapter-based approaches have garnered attention for fine-tuning pre-trained Vision-Language Models (VLMs) on few-shot classification tasks. These methods strive to develop a lightweight module that better aligns visual and (category) textual representations, thereby enhancing performance on downstream few-shot learning tasks. However, existing adapters generally learn/align (category) textual-visual modalities via explicit spatial proximity in the underlying embedding space, which i) fails to capture the inherent one-to-many associations between categories and image samples and ii) struggles to establish accurate associations between the unknown categories and images. To address these issues, inspired by recent works on hyperbolic learning, we develop a novel Latent Hierarchical Adapter (LatHAdapter) for fine-tuning VLMs on downstream few-shot classification tasks. The core of LatHAdapter is to exploit the latent semantic hierarchy of downstream training data and employ it to provide richer, fine-grained guidance for the adapter learning process. Specifically, LatHAdapter first introduces some learnable `attribute' prompts as the bridge to align categories and images. Then, it projects the categories, attribute prompts, and images within each batch in a hyperbolic space, and employs hierarchical regularization to learn the latent semantic hierarchy of them, thereby fully modeling the inherent one-to-many associations among categories, learnable attributes, and image samples. Extensive experiments on four challenging few-shot tasks show that the proposed LatHAdapter consistently outperforms many other fine-tuning approaches, particularly in adapting known classes and generalizing to unknown classes.

☆ Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category Discovery

Ruobing Jiang, Yang Liu, Haobing Liu, Yanwei Yu, Chunyang Wang

Continuous category discovery (CCD) aims to automatically discover novel categories in continuously arriving unlabeled data. This is a challenging problem considering that there is no number of categories and labels in the newly arrived data, while also needing to mitigate catastrophic forgetting. Most CCD methods cannot handle the contradiction between novel class discovery and classification well. They are also prone to accumulate errors in the process of gradually discovering novel classes. Moreover, most of them use knowledge distillation and data replay to prevent forgetting, occupying more storage space. To address these limitations, we propose Independence-based Diversity and Orthogonality-based Discrimination (IDOD). IDOD mainly includes independent enrichment of diversity module, joint discovery of novelty module, and continuous increment by orthogonality module. In independent enrichment, the backbone is trained separately using contrastive loss to avoid it focusing only on features for classification. Joint discovery transforms multi-stage novel class discovery into single-stage, reducing error accumulation impact. Continuous increment by orthogonality module generates mutually orthogonal prototypes for classification and prevents forgetting with lower space overhead via representative representation replay. Experimental results show that on challenging fine-grained datasets, our method outperforms the state-of-the-art methods.

comment: Accepted by CIKM 2025. 10 pages, 5 figures,

☆ Better Supervised Fine-tuning for VQA: Integer-Only Loss

Baihong Qian, Haotian Fan, Wenjie Liao, Yunqiu Wang, Tao Li, Junhui Cui

With the rapid advancement of vision language models(VLM), their ability to assess visual content based on specific criteria and dimensions has become increasingly critical for applications such as video-theme consistency assessment and visual quality scoring. However, existing methods often suffer from imprecise results and inefficient loss calculation, which limit the focus of the model on key evaluation indicators. To address this, we propose IOVQA(Integer-only VQA), a novel fine-tuning approach tailored for VLMs to enhance their performance in video quality assessment tasks. The key innovation of IOVQA lies in its label construction and its targeted loss calculation mechanism. Specifically, during dataset curation, we constrain the model's output to integers within the range of [10,50], ensuring numerical stability, and convert decimal Overall_MOS to integer before using them as labels. We also introduce a target-mask strategy: when computing the loss, only the first two-digit-integer of the label is unmasked, forcing the model to learn the critical components of the numerical evaluation. After fine-tuning the Qwen2.5-VL model using the constructed dataset, experimental results demonstrate that the proposed method significantly improves the model's accuracy and consistency in the VQA task, ranking 3rd in VQualA 2025 GenAI-Bench AIGC Video Quality Assessment Challenge -- Track I. Our work highlights the effectiveness of merely leaving integer labels during fine-tuning, providing an effective idea for optimizing VLMs in quantitative evaluation scenarios.

☆ VFM-Guided Semi-Supervised Detection Transformer for Source-Free Object Detection in Remote Sensing Images

Jianhong Han, Yupei Wang, Liang Chen

Unsupervised domain adaptation methods have been widely explored to bridge domain gaps. However, in real-world remote-sensing scenarios, privacy and transmission constraints often preclude access to source domain data, which limits their practical applicability. Recently, Source-Free Object Detection (SFOD) has emerged as a promising alternative, aiming at cross-domain adaptation without relying on source data, primarily through a self-training paradigm. Despite its potential, SFOD frequently suffers from training collapse caused by noisy pseudo-labels, especially in remote sensing imagery with dense objects and complex backgrounds. Considering that limited target domain annotations are often feasible in practice, we propose a Vision foundation-Guided DEtection TRansformer (VG-DETR), built upon a semi-supervised framework for SFOD in remote sensing images. VG-DETR integrates a Vision Foundation Model (VFM) into the training pipeline in a "free lunch" manner, leveraging a small amount of labeled target data to mitigate pseudo-label noise while improving the detector's feature-extraction capability. Specifically, we introduce a VFM-guided pseudo-label mining strategy that leverages the VFM's semantic priors to further assess the reliability of the generated pseudo-labels. By recovering potentially correct predictions from low-confidence outputs, our strategy improves pseudo-label quality and quantity. In addition, a dual-level VFM-guided alignment method is proposed, which aligns detector features with VFM embeddings at both the instance and image levels. Through contrastive learning among fine-grained prototypes and similarity matching between feature maps, this dual-level alignment further enhances the robustness of feature representations against domain gaps. Extensive experiments demonstrate that VG-DETR achieves superior performance in source-free remote sensing detection tasks.

comment: Manuscript submitted to IEEE TGRS

☆ Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models

Bing Liu, Le Wang, Mingming Liu, Hao Liu, Rui Yao, Yong Zhou, Peng Liu, Tongqiang Xia

Existing dehazing methods deal with real-world haze images with difficulty, especially scenes with thick haze. One of the main reasons is the lack of real-world paired data and robust priors. To avoid the costly collection of paired hazy and clear images, we propose an efficient semi-supervised image dehazing method via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models (EM-B3DM) with a two-stage learning scheme. In the first stage, we employ the EM algorithm to decouple the joint distribution of paired hazy and clear images into two conditional distributions, which are then modeled using a unified Brownian Bridge diffusion model to directly capture the structural and content-related correlations between hazy and clear images. In the second stage, we leverage the pre-trained model and large-scale unpaired hazy and clear images to further improve the performance of image dehazing. Additionally, we introduce a detail-enhanced Residual Difference Convolution block (RDC) to capture gradient-level information, significantly enhancing the model's representation capability. Extensive experiments demonstrate that our EM-B3DM achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.

comment: 10 pages, 4 figures

☆ LEARN: A Story-Driven Layout-to-Image Generation Framework for STEM Instruction

Maoquan Zhang, Bisser Raytchev, Xiujuan Sun

LEARN is a layout-aware diffusion framework designed to generate pedagogically aligned illustrations for STEM education. It leverages a curated BookCover dataset that provides narrative layouts and structured visual cues, enabling the model to depict abstract and sequential scientific concepts with strong semantic alignment. Through layout-conditioned generation, contrastive visual-semantic training, and prompt modulation, LEARN produces coherent visual sequences that support mid-to-high-level reasoning in line with Bloom's taxonomy while reducing extraneous cognitive load as emphasized by Cognitive Load Theory. By fostering spatially organized and story-driven narratives, the framework counters fragmented attention often induced by short-form media and promotes sustained conceptual focus. Beyond static diagrams, LEARN demonstrates potential for integration with multimodal systems and curriculum-linked knowledge graphs to create adaptive, exploratory educational content. As the first generative approach to unify layout-based storytelling, semantic structure learning, and cognitive scaffolding, LEARN represents a novel direction for generative AI in education. The code and dataset will be released to facilitate future research and practical deployment.

comment: The International Conference on Neural Information Processing (ICONIP) 2025

☆ A Cross-Modal Rumor Detection Scheme via Contrastive Learning by Exploring Text and Image internal Correlations

Bin Ma, Yifei Zhang, Yongjin Xian, Qi Li, Linna Zhou, Gongxun Miao

Existing rumor detection methods often neglect the content within images as well as the inherent relationships between contexts and images across different visual scales, thereby resulting in the loss of critical information pertinent to rumor identification. To address these issues, this paper presents a novel cross-modal rumor detection scheme based on contrastive learning, namely the Multi-scale Image and Context Correlation exploration algorithm (MICC). Specifically, we design an SCLIP encoder to generate unified semantic embeddings for text and multi-scale image patches through contrastive pretraining, enabling their relevance to be measured via dot-product similarity. Building upon this, a Cross-Modal Multi-Scale Alignment module is introduced to identify image regions most relevant to the textual semantics, guided by mutual information maximization and the information bottleneck principle, through a Top-K selection strategy based on a cross-modal relevance matrix constructed between the text and multi-scale image patches. Moreover, a scale-aware fusion network is designed to integrate the highly correlated multi-scale image features with global text features by assigning adaptive weights to image regions based on their semantic importance and cross-modal relevance. The proposed methodology has been extensively evaluated on two real-world datasets. The experimental results demonstrate that it achieves a substantial performance improvement over existing state-of-the-art approaches in rumor detection, highlighting its effectiveness and potential for practical applications.

☆ Residual-based Efficient Bidirectional Diffusion Model for Image Dehazing and Haze Generation

Bing Liu, Le Wang, Hao Liu, Mingming Liu

Current deep dehazing methods only focus on removing haze from hazy images, lacking the capability to translate between hazy and haze-free images. To address this issue, we propose a residual-based efficient bidirectional diffusion model (RBDM) that can model the conditional distributions for both dehazing and haze generation. Firstly, we devise dual Markov chains that can effectively shift the residuals and facilitate bidirectional smooth transitions between them. Secondly, the RBDM perturbs the hazy and haze-free images at individual timesteps and predicts the noise in the perturbed data to simultaneously learn the conditional distributions. Finally, to enhance performance on relatively small datasets and reduce computational costs, our method introduces a unified score function learned on image patches instead of entire images. Our RBDM successfully implements size-agnostic bidirectional transitions between haze-free and hazy images with only 15 sampling steps. Extensive experiments demonstrate that the proposed method achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.

comment: 7 pages, 5 figures, 2025 ICME Accepted

♻ ☆ Diffusion Beats Autoregressive in Data-Constrained Settings

Mihir Prabhudesai, Mengning Wu, Amir Zadeh, Katerina Fragkiadaki, Deepak Pathak

Autoregressive (AR) models have long dominated the landscape of large language models, driving progress across a wide range of tasks. Recently, diffusion-based language models have emerged as a promising alternative, though their advantages over AR models remain underexplored. In this paper, we systematically study masked diffusion models in data-constrained settings-where training involves repeated passes over limited data and find that they significantly outperform AR models when compute is abundant but data is scarce. Diffusion models make better use of repeated data, achieving lower validation loss and superior downstream performance. We find new scaling laws for diffusion models and derive a closed-form expression for the critical compute threshold at which diffusion begins to outperform AR. Finally, we explain why diffusion models excel in this regime: their randomized masking objective implicitly trains over a rich distribution of token orderings, acting as an implicit data augmentation that AR's fixed left-to-right factorization lacks. Our results suggest that when data, not compute, is the bottleneck, diffusion models offer a compelling alternative to the standard AR paradigm. Our code is available at: https://diffusion-scaling.github.io.

comment: Project Webpage: https://diffusion-scaling.github.io

♻ ☆ Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition

Ashish Jha, Dimitrii Ermilov, Konstantin Sobolev, Anh Huy Phan, Salman Ahmadi-Asl, Naveed Ahmed, Imran Junejo, Zaher AL Aghbari, Thar Baker, Ahmed Mohamed Khedr, Andrzej Cichocki

Pedestrian Attribute Recognition (PAR) focuses on identifying various attributes in pedestrian images, with key applications in person retrieval, suspect re-identification, and soft biometrics. However, Deep Neural Networks (DNNs) for PAR often suffer from over-parameterization and high computational complexity, making them unsuitable for resource-constrained devices. Traditional tensor-based compression methods typically factorize layers without adequately preserving the gradient direction during compression, leading to inefficient compression and a significant accuracy loss. In this work, we propose a novel approach for determining the optimal ranks of low-rank layers, ensuring that the gradient direction of the compressed model closely aligns with that of the original model. This means that the compressed model effectively preserves the update direction of the full model, enabling more efficient compression for PAR tasks. The proposed procedure optimizes the compression ranks for each layer within the ALM model, followed by compression using CPD-EPC or truncated SVD. This results in a reduction in model complexity while maintaining high performance.

♻ ☆ PhysLab: A Benchmark Dataset for Multi-Granularity Visual Parsing of Physics Experiments

Minghao Zou, Qingtian Zeng, Yongping Miao, Shangkun Liu, Zilong Wang, Hantao Liu, Wei Zhou

Visual parsing of images and videos is critical for a wide range of real-world applications. However, progress in this field is constrained by limitations of existing datasets: (1) insufficient annotation granularity, which impedes fine-grained scene understanding and high-level reasoning; (2) limited coverage of domains, particularly a lack of datasets tailored for educational scenarios; and (3) lack of explicit procedural guidance, with minimal logical rules and insufficient representation of structured task process. To address these gaps, we introduce PhysLab, the first video dataset that captures students conducting complex physics experiments. The dataset includes four representative experiments that feature diverse scientific instruments and rich human-object interaction (HOI) patterns. PhysLab comprises 620 long-form videos and provides multilevel annotations that support a variety of vision tasks, including action recognition, object detection, HOI analysis, etc. We establish strong baselines and perform extensive evaluations to highlight key challenges in the parsing of procedural educational videos. We expect PhysLab to serve as a valuable resource for advancing fine-grained visual parsing, facilitating intelligent classroom systems, and fostering closer integration between computer vision and educational technologies. The dataset and the evaluation toolkit are publicly available at https://github.com/ZMH-SDUST/PhysLab.

♻ ☆ Omni-DPO: A Dual-Perspective Paradigm for Dynamic Preference Learning of LLMs

Shangpin Peng, Weinong Wang, Zhuotao Tian, Senqiao Yang, Xing Wu, Haotian Xu, Chengquan Zhang, Takashi Isobe, Baotian Hu, Min Zhang

Direct Preference Optimization (DPO) has become a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based approaches typically treat all preference pairs uniformly, ignoring critical variations in their inherent quality and learning utility, leading to suboptimal data utilization and performance. To address this challenge, we propose Omni-DPO, a dual-perspective optimization framework that jointly accounts for (1) the inherent quality of each preference pair and (2) the model's evolving performance on those pairs. By adaptively weighting samples according to both data quality and the model's learning dynamics during training, Omni-DPO enables more effective training data utilization and achieves better performance. Experimental results on various models and benchmarks demonstrate the superiority and generalization capabilities of Omni-DPO. On textual understanding tasks, Gemma-2-9b-it finetuned with Omni-DPO beats the leading LLM, Claude 3 Opus, by a significant margin of 6.7 points on the Arena-Hard benchmark. On mathematical reasoning tasks, Omni-DPO consistently outperforms the baseline methods across all benchmarks, providing strong empirical evidence for the effectiveness and robustness of our approach. Code and models will be available at https://github.com/pspdada/Omni-DPO.

♻ ☆ UI-Venus Technical Report: Building High-performance UI Agents with RFT

Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu, Xingran Zhou, Shuheng Shen, Yunfei Liu, Beitong Zhou, Changhua Meng, Tianyu Xia, Weizhi Chen, Yue Wen, Jingya Dou, Fei Tang, Jinzhen Lin, Yulin Liu, Zhenlin Guo, Yichen Gong, Heng Jia, Changlong Gao, Yuan Guo, Yong Deng, Zhenyu Guo, Liang Chen, Weiqiang Wang

We present UI-Venus, a native UI agent that takes only screenshots as input based on a multimodal large language model. UI-Venus achieves SOTA performance on both UI grounding and navigation tasks using only several hundred thousand high-quality training samples through reinforcement finetune (RFT) based on Qwen2.5-VL. Specifically, the 7B and 72B variants of UI-Venus obtain 94.1% / 50.8% and 95.3% / 61.9% on the standard grounding benchmarks, i.e., Screenspot-V2 / Pro, surpassing the previous SOTA baselines including open-source GTA1 and closed-source UI-TARS-1.5. To show UI-Venus's summary and planing ability, we also evaluate it on the AndroidWorld, an online UI navigation arena, on which our 7B and 72B variants achieve 49.1% and 65.9% success rate, also beating existing models. To achieve this, we introduce carefully designed reward functions for both UI grounding and navigation tasks and corresponding efficient data cleaning strategies. To further boost navigation performance, we propose Self-Evolving Trajectory History Alignment & Sparse Action Enhancement that refine historical reasoning traces and balances the distribution of sparse but critical actions, leading to more coherent planning and better generalization in complex UI tasks. Our contributions include the publish of SOTA open-source UI agents, comprehensive data cleaning protocols and a novel self-evolving framework for improving navigation performance, which encourage further research and development in the community. Code is available at https://github.com/inclusionAI/UI-Venus.

♻ ☆ Synthetic Data for Robust Stroke Segmentation

Liam Chalcroft, Ioannis Pappas, Cathy J. Price, John Ashburner

Current deep learning-based approaches to lesion segmentation in neuroimaging often depend on high-resolution images and extensive annotated data, limiting clinical applicability. This paper introduces a novel synthetic data framework tailored for stroke lesion segmentation, expanding the SynthSeg methodology to incorporate lesion-specific augmentations that simulate diverse pathological features. Using a modified nnUNet architecture, our approach trains models with label maps from healthy and stroke datasets, facilitating segmentation across both normal and pathological tissue without reliance on specific sequence-based training. Evaluation across in-domain and out-of-domain (OOD) datasets reveals that our method matches state-of-the-art performance within the training domain and significantly outperforms existing methods on OOD data. By minimizing dependence on large annotated datasets and allowing for cross-sequence applicability, our framework holds potential to improve clinical neuroimaging workflows, particularly in stroke pathology. PyTorch training code and weights are publicly available at https://github.com/liamchalcroft/SynthStroke, along with an SPM toolbox featuring a plug-and-play model at https://github.com/liamchalcroft/SynthStrokeSPM.

comment: Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2025:014

♻ ☆ Image-to-Text for Medical Reports Using Adaptive Co-Attention and Triple-LSTM Module

Yishen Liu, Shengda Luo, Zishao Zhong, Hudan Pan

Medical report generation requires specialized expertise that general large models often fail to accurately capture. Moreover, the inherent repetition and similarity in medical data make it difficult for models to extract meaningful features, resulting in a tendency to overfit. So in this paper, we propose a multimodal model, Co-Attention Triple-LSTM Network (CA-TriNet), a deep learning model that combines transformer architectures with a Multi-LSTM network. Its Co-Attention module synergistically links a vision transformer with a text transformer to better differentiate medical images with similarities, augmented by an adaptive weight operator to catch and amplify image labels with minor similarities. Furthermore, its Triple-LSTM module refines generated sentences using targeted image objects. Extensive evaluations over three public datasets have demonstrated that CA-TriNet outperforms state-of-the-art models in terms of comprehensive ability, even pre-trained large language models on some metrics.

♻ ☆ ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos ACL 2025

Mohammad Zia Ur Rehman, Anukriti Bhatnagar, Omkar Kabde, Shubhi Bansal, Nagendra Kumar

The existing research has primarily focused on text and image-based hate speech detection, video-based approaches remain underexplored. In this work, we introduce a novel dataset, ImpliHateVid, specifically curated for implicit hate speech detection in videos. ImpliHateVid consists of 2,009 videos comprising 509 implicit hate videos, 500 explicit hate videos, and 1,000 non-hate videos, making it one of the first large-scale video datasets dedicated to implicit hate detection. We also propose a novel two-stage contrastive learning framework for hate speech detection in videos. In the first stage, we train modality-specific encoders for audio, text, and image using contrastive loss by concatenating features from the three encoders. In the second stage, we train cross-encoders using contrastive learning to refine multimodal representations. Additionally, we incorporate sentiment, emotion, and caption-based features to enhance implicit hate detection. We evaluate our method on two datasets, ImpliHateVid for implicit hate speech detection and another dataset for general hate speech detection in videos, HateMM dataset, demonstrating the effectiveness of the proposed multimodal contrastive learning for hateful content detection in videos and the significance of our dataset.

comment: Published in ACL 2025

♻ ☆ AFR-CLIP: Enhancing Zero-Shot Industrial Anomaly Detection with Stateless-to-Stateful Anomaly Feature Rectification

Jingyi Yuan, Chenqiang Gao, Pengyu Jie, Xuan Xia, Shangri Huang, Wanquan Liu

♻ ☆ Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, Junbo Zhao, Wei Li

We introduce M3-Agent, a novel multimodal agent framework equipped with long-term memory. Like humans, M3-Agent can process real-time visual and auditory inputs to build and update its long-term memory. Beyond episodic memory, it also develops semantic memory, enabling it to accumulate world knowledge over time. Its memory is organized in an entity-centric, multimodal format, allowing deeper and more consistent understanding of the environment. Given an instruction, M3-Agent autonomously performs multi-turn, iterative reasoning and retrieves relevant information from memory to accomplish the task. To evaluate memory effectiveness and memory-based reasoning in multimodal agents, we develop M3-Bench, a new long-video question answering benchmark. M3-Bench comprises 100 newly recorded real-world videos captured from a robot's perspective (M3-Bench-robot) and 920 web-sourced videos across diverse scenarios (M3-Bench-web). We annotate question-answer pairs designed to test key capabilities essential for agent applications, such as human understanding, general knowledge extraction, and cross-modal reasoning. Experimental results show that M3-Agent, trained via reinforcement learning, outperforms the strongest baseline, a prompting agent using Gemini-1.5-pro and GPT-4o, achieving 6.7%, 7.7%, and 5.3% higher accuracy on M3-Bench-robot, M3-Bench-web and VideoMME-long, respectively. Our work advances the multimodal agents toward more human-like long-term memory and provides insights into their practical design. Model, code and data are available at https://github.com/bytedance-seed/m3-agent

♻ ☆ GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

GLM-V Team, :, Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, Shuaiqi Duan, Weihan Wang, Yan Wang, Yean Cheng, Zehai He, Zhe Su, Zhen Yang, Ziyang Pan, Aohan Zeng, Baoxu Wang, Bin Chen, Boyan Shi, Changyu Pang, Chenhui Zhang, Da Yin, Fan Yang, Guoqing Chen, Jiazheng Xu, Jiale Zhu, Jiali Chen, Jing Chen, Jinhao Chen, Jinghao Lin, Jinjiang Wang, Junjie Chen, Leqi Lei, Letian Gong, Leyi Pan, Mingdao Liu, Mingde Xu, Mingzhi Zhang, Qinkai Zheng, Sheng Yang, Shi Zhong, Shiyu Huang, Shuyuan Zhao, Siyan Xue, Shangqin Tu, Shengbiao Meng, Tianshu Zhang, Tianwei Luo, Tianxiang Hao, Tianyu Tong, Wenkai Li, Wei Jia, Xiao Liu, Xiaohan Zhang, Xin Lyu, Xinyue Fan, Xuancheng Huang, Yanling Wang, Yadong Xue, Yanfeng Wang, Yanzi Wang, Yifan An, Yifan Du, Yiming Shi, Yiheng Huang, Yilin Niu, Yuan Wang, Yuanchang Yue, Yuchen Li, Yutao Zhang, Yuting Wang, Yu Wang, Yuxuan Zhang, Zhao Xue, Zhenyu Hou, Zhengxiao Du, Zihan Wang, Peng Zhang, Debing Liu, Bin Xu, Juanzi Li, Minlie Huang, Yuxiao Dong, Jie Tang

We present GLM-4.1V-Thinking and GLM-4.5V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. Code, models and more information are released at https://github.com/zai-org/GLM-V.

♻ ☆ Introducing Unbiased Depth into 2D Gaussian Splatting for High-accuracy Surface Reconstruction

Yixin Yang, Yang Zhou, Hui Huang

Recently, 2D Gaussian Splatting (2DGS) has demonstrated superior geometry reconstruction quality than the popular 3DGS by using 2D surfels to approximate thin surfaces. However, it falls short when dealing with glossy surfaces, resulting in visible holes in these areas. We find that the reflection discontinuity causes the issue. To fit the jump from diffuse to specular reflection at different viewing angles, depth bias is introduced in the optimized Gaussian primitives. To address that, we first replace the depth distortion loss in 2DGS with a novel depth convergence loss, which imposes a strong constraint on depth continuity. Then, we rectify the depth criterion in determining the actual surface, which fully accounts for all the intersecting Gaussians along the ray. Qualitative and quantitative evaluations across various datasets reveal that our method significantly improves reconstruction quality, with more complete and accurate surfaces than 2DGS. Code is available at https://github.com/XiaoXinyyx/Unbiased_Surfel.

comment: Accepted to the Journal track of Pacific Graphics 2025

♻ ☆ Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis

Yu Xin, Gorkem Can Ates, Kuang Gong, Wei Shao

Vision-language models (VLMs) have shown promise in 2D medical image analysis, but extending them to 3D remains challenging due to the high computational demands of volumetric data and the difficulty of aligning 3D spatial features with clinical text. We present Med3DVLM, a 3D VLM designed to address these challenges through three key innovations: (1) DCFormer, an efficient encoder that uses decomposed 3D convolutions to capture fine-grained spatial features at scale; (2) SigLIP, a contrastive learning strategy with pairwise sigmoid loss that improves image-text alignment without relying on large negative batches; and (3) a dual-stream MLP-Mixer projector that fuses low- and high-level image features with text embeddings for richer multi-modal representations. We evaluate our model on the M3D dataset, which includes radiology reports and VQA data for 120,084 3D medical images. Results show that Med3DVLM achieves superior performance across multiple benchmarks. For image-text retrieval, it reaches 61.00% R@1 on 2,000 samples, significantly outperforming the current state-of-the-art M3D model (19.10%). For report generation, it achieves a METEOR score of 36.42% (vs. 14.38%). In open-ended visual question answering (VQA), it scores 36.76% METEOR (vs. 33.58%), and in closed-ended VQA, it achieves 79.95% accuracy (vs. 75.78%). These results highlight Med3DVLM's ability to bridge the gap between 3D imaging and language, enabling scalable, multi-task reasoning across clinical applications. Our code is publicly available at https://github.com/mirthAI/Med3DVLM.

♻ ☆ FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance IJCAI 2025

Jiasong Feng, Ao Ma, Jing Wang, Ke Cao, Zhanjie Zhang

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text control, equivalently guiding different frame generations without frame-specific textual guidance. Thus, the model's capacity to comprehend the temporal logic conveyed in prompts and generate videos with coherent motion is restricted. To tackle this limitation, we introduce FancyVideo, an innovative video generator that improves the existing text-control mechanism with the well-designed Cross-frame Textual Guidance Module (CTGM). Specifically, CTGM incorporates the Temporal Information Injector (TII) and Temporal Affinity Refiner (TAR) at the beginning and end of cross-attention, respectively, to achieve frame-specific textual guidance. Firstly, TII injects frame-specific information from latent features into text conditions, thereby obtaining cross-frame textual conditions. Then, TAR refines the correlation matrix between cross-frame textual conditions and latent features along the time dimension. Extensive experiments comprising both quantitative and qualitative evaluations demonstrate the effectiveness of FancyVideo. Our approach achieves state-of-the-art T2V generation results on the EvalCrafter benchmark and facilitates the synthesis of dynamic and consistent videos. Note that the T2V process of FancyVideo essentially involves a text-to-image step followed by T+I2V. This means it also supports the generation of videos from user images, i.e., the image-to-video (I2V) task. A significant number of experiments have shown that its performance is also outstanding.

comment: Accepted by IJCAI 2025

♻ ☆ Reconstructing Satellites in 3D from Amateur Telescope Images

Zhiming Chang, Boyang Liu, Yifei Xia, Youming Guo, Boxin Shi, He Sun

Monitoring space objects is crucial for space situational awareness, yet reconstructing 3D satellite models from ground-based telescope images is challenging due to atmospheric turbulence, long observation distances, limited viewpoints, and low signal-to-noise ratios. In this paper, we propose a novel computational imaging framework that overcomes these obstacles by integrating a hybrid image pre-processing pipeline with a joint pose estimation and 3D reconstruction module based on controlled Gaussian Splatting (GS) and Branch-and-Bound (BnB) search. We validate our approach on both synthetic satellite datasets and on-sky observations of China's Tiangong Space Station and the International Space Station, achieving robust 3D reconstructions of low-Earth orbit satellites from ground-based data. Quantitative evaluations using SSIM, PSNR, LPIPS, and Chamfer Distance demonstrate that our method outperforms state-of-the-art NeRF-based approaches, and ablation studies confirm the critical role of each component. Our framework enables high-fidelity 3D satellite monitoring from Earth, offering a cost-effective alternative for space situational awareness. Project page: https://ai4scientificimaging.org/ReconstructingSatellites

♻ ☆ GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution

Qiwei Zhu, Kai Li, Guojing Zhang, Xiaoying Wang, Jianqiang Huang, Xilai Li

In recent years, deep neural networks, including Convolutional Neural Networks, Transformers, and State Space Models, have achieved significant progress in Remote Sensing Image (RSI) Super-Resolution (SR). However, existing SR methods typically overlook the complementary relationship between global and local dependencies. These methods either focus on capturing local information or prioritize global information, which results in models that are unable to effectively capture both global and local features simultaneously. Moreover, their computational cost becomes prohibitive when applied to large-scale RSIs. To address these challenges, we introduce the novel application of Receptance Weighted Key Value (RWKV) to RSI-SR, which captures long-range dependencies with linear complexity. To simultaneously model global and local features, we propose the Global-Detail dual-branch structure, GDSR, which performs SR by paralleling RWKV and convolutional operations to handle large-scale RSIs. Furthermore, we introduce the Global-Detail Reconstruction Module (GDRM) as an intermediary between the two branches to bridge their complementary roles. In addition, we propose the Dual-Group Multi-Scale Wavelet Loss, a wavelet-domain constraint mechanism via dual-group subband strategy and cross-resolution frequency alignment for enhanced reconstruction fidelity in RSI-SR. Extensive experiments under two degradation methods on several benchmarks, including AID, UCMerced, and RSSRD-QH, demonstrate that GSDR outperforms the state-of-the-art Transformer-based method HAT by an average of 0.09 dB in PSNR, while using only 63% of its parameters and 51% of its FLOPs, achieving an inference speed 3.2 times faster.

comment: GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution

♻ ☆ Casual3DHDR: High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos

Shucheng Gong, Lingzhe Zhao, Wenpu Li, Hong Xie, Yin Zhang, Shiyu Zhao, Peidong Liu

Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low dynamic range (LDR) images, limiting their ability to capture detailed scenes in high-contrast environments. While some prior works address high dynamic range (HDR) scene reconstruction, they typically require multi-view sharp images with varying exposure times captured at fixed camera positions, which is time-consuming and impractical. To make data acquisition more flexible, we propose \textbf{Casual3DHDR}, a robust one-stage method that reconstructs 3D HDR scenes from casually-captured auto-exposure (AE) videos, even under severe motion blur and unknown, varying exposure times. Our approach integrates a continuous camera trajectory into a unified physical imaging model, jointly optimizing exposure times, camera trajectory, and the camera response function (CRF). Extensive experiments on synthetic and real-world datasets demonstrate that \textbf{Casual3DHDR} outperforms existing methods in robustness and rendering quality. Our source code and dataset will be available at https://lingzhezhao.github.io/CasualHDRSplat/

comment: Published in ACM Multimedia 2025. Project page: https://lingzhezhao.github.io/CasualHDRSplat/ (Previously titled "CasualHDRSplat: Robust High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos")

♻ ☆ SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

Heyi Sun, Cong Wang, Tian-Xing Xu, Jingwei Huang, Di Kang, Chunchao Guo, Song-Hai Zhang

Creating high-fidelity and editable head avatars is a pivotal challenge in computer vision and graphics, boosting many AR/VR applications. While recent advancements have achieved photorealistic renderings and plausible animation, head editing, especially real-time appearance editing, remains challenging due to the implicit representation and entangled modeling of the geometry and global appearance. To address this, we propose Surface-Volumetric Gaussian Head Avatar (SVG-Head), a novel hybrid representation that explicitly models the geometry with 3D Gaussians bound on a FLAME mesh and leverages disentangled texture images to capture the global appearance. Technically, it contains two types of Gaussians, in which surface Gaussians explicitly model the appearance of head avatars using learnable texture images, facilitating real-time texture editing, while volumetric Gaussians enhance the reconstruction quality of non-Lambertian regions (e.g., lips and hair). To model the correspondence between 3D world and texture space, we provide a mesh-aware Gaussian UV mapping method, which leverages UV coordinates given by the FLAME mesh to obtain sharp texture images and real-time rendering speed. A hierarchical optimization strategy is further designed to pursue the optimal performance in both reconstruction quality and editing flexibility. Experiments on the NeRSemble dataset show that SVG-Head not only generates high-fidelity rendering results, but also is the first method to obtain explicit texture images for Gaussian head avatars and support real-time appearance editing.

comment: Accepted by ICCV 2025. Project page: https://heyy-sun.github.io/SVG-Head/

♻ ☆ MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks

Zonglin Wu, Yule Xue, Yaoyao Feng, Xiaolong Wang, Yiren Song

As automated attack techniques rapidly advance, CAPTCHAs remain a critical defense mechanism against malicious bots. However, existing CAPTCHA schemes encompass a diverse range of modalities -- from static distorted text and obfuscated images to interactive clicks, sliding puzzles, and logic-based questions -- yet the community still lacks a unified, large-scale, multimodal benchmark to rigorously evaluate their security robustness. To address this gap, we introduce MCA-Bench, a comprehensive and reproducible benchmarking suite that integrates heterogeneous CAPTCHA types into a single evaluation protocol. Leveraging a shared vision-language model backbone, we fine-tune specialized cracking agents for each CAPTCHA category, enabling consistent, cross-modal assessments. Extensive experiments reveal that MCA-Bench effectively maps the vulnerability spectrum of modern CAPTCHA designs under varied attack settings, and crucially offers the first quantitative analysis of how challenge complexity, interaction depth, and model solvability interrelate. Based on these findings, we propose three actionable design principles and identify key open challenges, laying the groundwork for systematic CAPTCHA hardening, fair benchmarking, and broader community collaboration. Datasets and code are available online.

comment: we update the paper, add more experiments, and update the teammates

♻ ☆ Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization

Mu Li, Kanglong Fan, Kede Ma

Predicting human scanpaths when exploring panoramic videos is a challenging task due to the spherical geometry and the multimodality of the input, and the inherent uncertainty and diversity of the output. Most previous methods fail to give a complete treatment of these characteristics, and thus are prone to errors. In this paper, we present a simple new criterion for scanpath prediction based on principles from lossy data compression. This criterion suggests minimizing the expected code length of quantized scanpaths in a training set, which corresponds to fitting a discrete conditional probability model via maximum likelihood. Specifically, the probability model is conditioned on two modalities: a viewport sequence as the deformation-reduced visual input and a set of relative historical scanpaths projected onto respective viewports as the aligned path input. The probability model is parameterized by a product of discretized Gaussian mixture models to capture the uncertainty and the diversity of scanpaths from different users. Most importantly, the training of the probability model does not rely on the specification of "ground-truth" scanpaths for imitation learning. We also introduce a proportional-integral-derivative (PID) controller-based sampler to generate realistic human-like scanpaths from the learned probability model. Experimental results demonstrate that our method consistently produces better quantitative scanpath results in terms of prediction accuracy (by comparing to the assumed "ground-truths") and perceptual realism (through machine discrimination) over a wide range of prediction horizons. We additionally verify the perceptual realism improvement via a formal psychophysical experiment and the generalization improvement on several unseen panoramic video datasets.

♻ ☆ Tapping into the Black Box: Uncovering Aligned Representations in Pretrained Neural Networks

Maciej Satkiewicz

In ReLU networks, gradients of output units can be seen as their input-level representations, as they correspond to the units' pullbacks through the active subnetwork. However, gradients of deeper models are notoriously misaligned, significantly contributing to their black-box nature. We claim that this is because active subnetworks are inherently noisy due to the ReLU hard-gating. To tackle that noise, we propose soft-gating in the backward pass only. The resulting input-level vector field (called ''excitation pullback'') exhibits remarkable perceptual alignment, revealing high-resolution input- and target-specific features that ''just make sense'', therefore establishing a compelling novel explanation method. Furthermore, we speculate that excitation pullbacks approximate (directionally) the gradients of a simpler model, linear in the network's path space, learned implicitly during optimization and largely determining the network's decision; thus arguing for the faithfulness of the produced explanations and their overall significance.

comment: 11 pages, 3-page appendix, 4 figures, preprint; v2 changes: redacted abstract, slight reformulation of Hypothesis 1, extended motivation, unified notation, minor wording improvements

♻ ☆ Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries

Yin Wu, Quanyu Long, Jing Li, Jianfei Yu, Wenya Wang

Retrieval-augmented generation (RAG) is a paradigm that augments large language models (LLMs) with external knowledge to tackle knowledge-intensive question answering. While several benchmarks evaluate Multimodal LLMs (MLLMs) under Multimodal RAG settings, they predominantly retrieve from textual corpora and do not explicitly assess how models exploit visual evidence during generation. Consequently, there still lacks benchmark that isolates and measures the contribution of retrieved images in RAG. We introduce Visual-RAG, a question-answering benchmark that targets visually grounded, knowledge-intensive questions. Unlike prior work, Visual-RAG requires text-to-image retrieval and the integration of retrieved clue images to extract visual evidence for answer generation. With Visual-RAG, we evaluate 5 open-source and 3 proprietary MLLMs, showcasing that images provide strong evidence in augmented generation. However, even state-of-the-art models struggle to efficiently extract and utilize visual knowledge. Our results highlight the need for improved visual retrieval, grounding, and attribution in multimodal RAG systems.

comment: 21 pages, 6 figures, 17 tables

♻ ☆ ShoulderShot: Generating Over-the-Shoulder Dialogue Videos

Yuang Zhang, Junqi Cheng, Haoyu Zhao, Jiaxi Gu, Fangyuan Zou, Zenghui Lu, Peng Shu

Over-the-shoulder dialogue videos are essential in films, short dramas, and advertisements, providing visual variety and enhancing viewers' emotional connection. Despite their importance, such dialogue scenes remain largely underexplored in video generation research. The main challenges include maintaining character consistency across different shots, creating a sense of spatial continuity, and generating long, multi-turn dialogues within limited computational budgets. Here, we present ShoulderShot, a framework that combines dual-shot generation with looping video, enabling extended dialogues while preserving character consistency. Our results demonstrate capabilities that surpass existing methods in terms of shot-reverse-shot layout, spatial continuity, and flexibility in dialogue length, thereby opening up new possibilities for practical dialogue video generation. Videos and comparisons are available at https://shouldershot.github.io.

♻ ☆ LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition

Jinghan You, Shanglin Li, Yuanrui Sun, Jiangchuan Wei, Mingyu Guo, Chao Feng, Jiao Ran

Vision Transformers (ViTs) have revolutionized large-scale visual modeling, yet remain underexplored in face recognition (FR) where CNNs still dominate. We identify a critical bottleneck: CNN-inspired training paradigms fail to unlock ViT's potential, leading to suboptimal performance and convergence instability.To address this challenge, we propose LVFace, a ViT-based FR model that integrates Progressive Cluster Optimization (PCO) to achieve superior results. Specifically, PCO sequentially applies negative class sub-sampling (NCS) for robust and fast feature alignment from random initialization, feature expectation penalties for centroid stabilization, performing cluster boundary refinement through full-batch training without NCS constraints. LVFace establishes a new state-of-the-art face recognition baseline, surpassing leading approaches such as UniFace and TopoFR across multiple benchmarks. Extensive experiments demonstrate that LVFace delivers consistent performance gains, while exhibiting scalability to large-scale datasets and compatibility with mainstream VLMs and LLMs. Notably, LVFace secured 1st place in the ICCV 2021 Masked Face Recognition (MFR)-Ongoing Challenge (March 2025), proving its efficacy in real-world scenarios. Project is available at https://github.com/bytedance/LVFace.

comment: Accepted at ICCV25 as highlight paper, code released at https://github.com/bytedance/LVFace

♻ ☆ Automatic brain tumor segmentation in 2D intra-operative ultrasound images using magnetic resonance imaging tumor annotations

Mathilde Faanes, Ragnhild Holden Helland, Ole Solheim, Sébastien Muller, Ingerid Reinertsen

Automatic segmentation of brain tumors in intra-operative ultrasound (iUS) images could facilitate localization of tumor tissue during resection surgery. The lack of large annotated datasets limits the current models performances. In this paper, we investigated the use of tumor annotations in magnetic resonance imaging (MRI) scans, which are more accessible than annotations in iUS images, for training of deep learning models for iUS brain tumor segmentation. We used 180 annotated MRI scans with corresponding unannotated iUS images, and 29 annotated iUS images. Image registration was performed to transfer the MRI annotations to the corresponding iUS images before training the nnU-Net model with different configurations of the data and label origins. The results showed no significant difference in Dice score for a model trained with only MRI annotated tumors compared to models trained with only iUS annotations and both, and to expert annotations, indicating that MRI tumor annotations can be used as a substitute for iUS tumor annotations to train a deep learning model for automatic brain tumor segmentation in iUS images. The best model obtained an average Dice score of $0.62\pm0.31$, compared to $0.67\pm0.25$ for an expert neurosurgeon, where the performance on larger tumors were similar, but lower for the models on smaller tumors. In addition, the results showed that removing smaller tumors from the training sets improved the results. The main models are available here: https://github.com/mathildefaanes/us_brain_tumor_segmentation/tree/main

comment: 14 pages, 5 figures

♻ ☆ TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

Haokun Lin, Teng Wang, Yixiao Ge, Yuying Ge, Zhichao Lu, Ying Wei, Qingfu Zhang, Zhenan Sun, Ying Shan

Pioneering token-based works such as Chameleon and Emu3 have established a foundation for multimodal unification but face challenges of high training computational overhead and limited comprehension performance due to a lack of high-level semantics. In this paper, we introduce TokLIP, a visual tokenizer that enhances comprehension by semanticizing vector-quantized (VQ) tokens and incorporating CLIP-level semantics while enabling end-to-end multimodal autoregressive training with standard VQ tokens. TokLIP integrates a low-level discrete VQ tokenizer with a ViT-based token encoder to capture high-level continuous semantics. Unlike previous approaches (e.g., VILA-U) that discretize high-level features, TokLIP disentangles training objectives for comprehension and generation, allowing the direct application of advanced VQ tokenizers without the need for tailored quantization operations. Our empirical results demonstrate that TokLIP achieves exceptional data efficiency, empowering visual tokens with high-level semantic understanding while enhancing low-level generative capacity, making it well-suited for autoregressive Transformers in both comprehension and generation tasks. The code and models are available at https://github.com/TencentARC/TokLIP.

comment: Technical Report

♻ ☆ HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection

Han Wang, Zhuoran Wang, Roy Ka-Wei Lee

Detecting hate speech in videos remains challenging due to the complexity of multimodal content and the lack of fine-grained annotations in existing datasets. We present HateClipSeg, a large-scale multimodal dataset with both video-level and segment-level annotations, comprising over 11,714 segments labeled as Normal or across five Offensive categories: Hateful, Insulting, Sexual, Violence, Self-Harm, along with explicit target victim labels. Our three-stage annotation process yields high inter-annotator agreement (Krippendorff's alpha = 0.817). We propose three tasks to benchmark performance: (1) Trimmed Hateful Video Classification, (2) Temporal Hateful Video Localization, and (3) Online Hateful Video Classification. Results highlight substantial gaps in current models, emphasizing the need for more sophisticated multimodal and temporally aware approaches. The HateClipSeg dataset are publicly available at https://github.com/Social-AI-Studio/HateClipSeg.git.

comment: 6 pages, 3 figures

♻ ☆ DSConv: Dynamic Splitting Convolution for Pansharpening

Xuanyu Liu, Bonan An

Aiming to obtain a high-resolution image, pansharpening involves the fusion of a multi-spectral image (MS) and a panchromatic image (PAN), the low-level vision task remaining significant and challenging in contemporary research. Most existing approaches rely predominantly on standard convolutions, few making the effort to adaptive convolutions, which are effective owing to the inter-pixel correlations of remote sensing images. In this paper, we propose a novel strategy for dynamically splitting convolution kernels in conjunction with attention, selecting positions of interest, and splitting the original convolution kernel into multiple smaller kernels, named DSConv. The proposed DSConv more effectively extracts features of different positions within the receptive field, enhancing the network's generalization, optimization, and feature representation capabilities. Furthermore, we innovate and enrich concepts of dynamic splitting convolution and provide a novel network architecture for pansharpening capable of achieving the tasks more efficiently, building upon this methodology. Adequate fair experiments illustrate the effectiveness and the state-of-the-art performance attained by DSConv.Comprehensive and rigorous discussions proved the superiority and optimal usage conditions of DSConv.

comment: The content of the paper is not yet fully developed, and the proposed approach requires further optimization. Additionally, the experimental results are incomplete and need to be supplemented. Therefore, I request the withdrawal of this submission for further revision and improvements

♻ ☆ Towards Consumer-Grade Cybersickness Prediction: Multi-Model Alignment for Real-Time Vision-Only Inference

Yitong Zhu, Zhuowen Liang, Yiming Wu, Tangyao Li, Yuyang Wang

♻ ☆ GBR: Generative Bundle Refinement for High-fidelity Gaussian Splatting with Enhanced Mesh Reconstruction

Jianing Zhang, Yuchao Zheng, Ziwei Li, Qionghai Dai, Xiaoyun Yuan

Gaussian splatting has gained attention for its efficient representation and rendering of 3D scenes using continuous Gaussian primitives. However, it struggles with sparse-view inputs due to limited geometric and photometric information, causing ambiguities in depth, shape, and texture. we propose GBR: Generative Bundle Refinement, a method for high-fidelity Gaussian splatting and meshing using only 4-6 input views. GBR integrates a neural bundle adjustment module to enhance geometry accuracy and a generative depth refinement module to improve geometry fidelity. More specifically, the neural bundle adjustment module integrates a foundation network to produce initial 3D point maps and point matches from unposed images, followed by bundle adjustment optimization to improve multiview consistency and point cloud accuracy. The generative depth refinement module employs a diffusion-based strategy to enhance geometric details and fidelity while preserving the scale. Finally, for Gaussian splatting optimization, we propose a multimodal loss function incorporating depth and normal consistency, geometric regularization, and pseudo-view supervision, providing robust guidance under sparse-view conditions. Experiments on widely used datasets show that GBR significantly outperforms existing methods under sparse-view inputs. Additionally, GBR demonstrates the ability to reconstruct and render large-scale real-world scenes, such as the Pavilion of Prince Teng and the Great Wall, with remarkable details using only 6 views.

♻ ☆ PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks

Xinhao Wang, Zhiwei Lin, Zhongyu Xia, Yongtao Wang

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes substantial GPU memory requirements and extended training time due to weight fine-tuning. In this paper, we propose PTQAT, a novel general hybrid quantization algorithm for the efficient deployment of 3D perception networks. To address the speed accuracy trade-off between PTQ and QAT, our method selects critical layers for QAT fine-tuning and performs PTQ on the remaining layers. Contrary to intuition, fine-tuning the layers with smaller output discrepancies before and after quantization, rather than those with larger discrepancies, actually leads to greater improvements in the model's quantization accuracy. This means we better compensate for quantization errors during their propagation, rather than addressing them at the point where they occur. The proposed PTQAT achieves similar performance to QAT with more efficiency by freezing nearly 50% of quantifiable layers. Additionally, PTQAT is a universal quantization method that supports various quantization bit widths (4 bits) as well as different model architectures, including CNNs and Transformers. The experimental results on nuScenes across diverse 3D perception tasks, including object detection, semantic segmentation, and occupancy prediction, show that our method consistently outperforms QAT-only baselines. Notably, it achieves 0.2%-0.9% NDS and 0.3%-1.0% mAP gains in object detection, 0.3%-2.0% mIoU gains in semantic segmentation and occupancy prediction while fine-tuning fewer weights.

comment: 8 pages, Accepted by ICCVW 2025

♻ ☆ SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning

Weijian Mai, Jiamin Wu, Yu Zhu, Zhouheng Yao, Dongzhan Zhou, Andrew F. Luo, Qihao Zheng, Wanli Ouyang, Chunfeng Song

Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience. This visual-to-neural mapping is inherently a one-to-many relationship, as identical visual inputs reliably evoke variable hemodynamic responses across trials, contexts, and subjects. However, existing deterministic methods struggle to simultaneously model this biological variability while capturing the underlying functional consistency that encodes stimulus information. To address these limitations, we propose SynBrain, a generative framework that simulates the transformation from visual semantics to neural responses in a probabilistic and biologically interpretable manner. SynBrain introduces two key components: (i) BrainVAE models neural representations as continuous probability distributions via probabilistic learning while maintaining functional consistency through visual semantic constraints; (ii) A Semantic-to-Neural Mapper acts as a semantic transmission pathway, projecting visual semantics into the neural response manifold to facilitate high-fidelity fMRI synthesis. Experimental results demonstrate that SynBrain surpasses state-of-the-art methods in subject-specific visual-to-fMRI encoding performance. Furthermore, SynBrain adapts efficiently to new subjects with few-shot data and synthesizes high-quality fMRI signals that are effective in improving data-limited fMRI-to-image decoding performance. Beyond that, SynBrain reveals functional consistency across trials and subjects, with synthesized signals capturing interpretable patterns shaped by biological neural variability. The code will be made publicly available.

♻ ☆ Effective Message Hiding with Order-Preserving Mechanisms

Gao Yu, Qiu Xuchong, Ye Zihan

Message hiding, a technique that conceals secret message bits within a cover image, aims to achieve an optimal balance among message capacity, recovery accuracy, and imperceptibility. While convolutional neural networks have notably improved message capacity and imperceptibility, achieving high recovery accuracy remains challenging. This challenge arises because convolutional operations struggle to preserve the sequential order of message bits and effectively address the discrepancy between these two modalities. To address this, we propose StegaFormer, an innovative MLP-based framework designed to preserve bit order and enable global fusion between modalities. Specifically, StegaFormer incorporates three crucial components: Order-Preserving Message Encoder (OPME), Decoder (OPMD) and Global Message-Image Fusion (GMIF). OPME and OPMD aim to preserve the order of message bits by segmenting the entire sequence into equal-length segments and incorporating sequential information during encoding and decoding. Meanwhile, GMIF employs a cross-modality fusion mechanism to effectively fuse the features from the two uncorrelated modalities. Experimental results on the COCO and DIV2K datasets demonstrate that StegaFormer surpasses existing state-of-the-art methods in terms of recovery accuracy, message capacity, and imperceptibility. We will make our code publicly available.

comment: BMVC 2024

♻ ☆ Compositional Zero-shot Learning via Progressive Language-based Observations

Lin Li, Guikun Chen, Zhen Wang, Jun Xiao, Long Chen

Compositional zero-shot learning aims to recognize unseen state-object compositions by leveraging known primitives (state and object) during training. However, effectively modeling interactions between primitives and generalizing knowledge to novel compositions remains a perennial challenge. There are two key factors: object-conditioned and state-conditioned variance, i.e., the appearance of states (or objects) can vary significantly when combined with different objects (or states). For instance, the state "old" can signify a vintage design for a "car" or an advanced age for a "cat". In this paper, we argue that these variances can be mitigated by predicting composition categories based on pre-observed primitive. To this end, we propose Progressive Language-based Observations (PLO), which can dynamically determine a better observation order of primitives. These observations comprise a series of concepts or languages that allow the model to understand image content in a step-by-step manner. Specifically, PLO adopts pre-trained vision-language models (VLMs) to empower the model with observation capabilities. We further devise two variants: 1) PLO-VLM: a two-step method, where a pre-observing classifier dynamically determines the observation order of two primitives. 2) PLO-LLM: a multi-step scheme, which utilizes large language models (LLMs) to craft composition-specific prompts for step-by-step observing. Extensive ablations on three challenging datasets demonstrate the superiority of PLO compared with state-of-the-art methods, affirming its abilities in compositional recognition.

♻ ☆ IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model

Anqing Jiang, Yu Gao, Yiru Wang, Zhigang Sun, Shuo Wang, Yuwen Heng, Hao Sun, Shichen Tang, Lijuan Zhu, Jinhao Chai, Jijun Wang, Zichong Gu, Hao Jiang, Li Sun

Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup which tends to capture the recorded behaviors in the dataset, leading to suboptimal and constrained performance, (2) Close-loop training relies heavily on high-fidelity sensor simulation, where domain gaps and computational inefficiencies pose significant barriers. In this paper, we introduce IRL-VLA, a novel close-loop Reinforcement Learning via \textbf{I}nverse \textbf{R}einforcement \textbf{L}earning reward world model with a self-built VLA approach. Our framework proceeds in a three-stage paradigm: In the first stage, we propose a VLA architecture and pretrain the VLA policy via imitation learning. In the second stage, we construct a lightweight reward world model via inverse reinforcement learning to enable efficient close-loop reward computation. To further enhance planning performance, finally, we design specialized reward world model guidence reinforcement learning via PPO(Proximal Policy Optimization) to effectively balance the safety incidents, comfortable driving, and traffic efficiency. Our approach achieves state-of-the-art performance in NAVSIM v2 end-to-end driving benchmark, 1st runner up in CVPR2025 Autonomous Grand Challenge. We hope that our framework will accelerate VLA research in close-loop autonomous driving.

comment: 9 pagres, 2 figures

♻ ☆ Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking

You Wu, Yongxin Li, Mengyuan Liu, Xucheng Wang, Xiangyang Yang, Hengzhou Ye, Dan Zeng, Qijun Zhao, Shuiwang Li

Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and efficiency, we propose AVTrack, an adaptive computation tracking framework that adaptively activates transformer blocks through an Activation Module (AM), which dynamically optimizes the ViT architecture by selectively engaging relevant components. To address extreme viewpoint variations, we propose to learn view-invariant representations via mutual information (MI) maximization. In addition, we propose AVTrack-MD, an enhanced tracker incorporating a novel MI maximization-based multi-teacher knowledge distillation framework. Leveraging multiple off-the-shelf AVTrack models as teachers, we maximize the MI between their aggregated softened features and the corresponding softened feature of the student model, improving the generalization and performance of the student, especially under noisy conditions. Extensive experiments show that AVTrack-MD achieves performance comparable to AVTrack's performance while reducing model complexity and boosting average tracking speed by over 17\%. Codes is available at: https://github.com/wuyou3474/AVTrack.

♻ ☆ Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation

Hao Zhang, Yongqiang Ma, Wenqi Shao, Ping Luo, Nanning Zheng, Kaipeng Zhang

Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation. Vision Transformers (ViTs) have advanced global modeling through self-attention but suffer from quadratic computational complexity with respect to token count, limiting their efficiency and scalability to high-resolution inputs, especially on mobile and resource-constrained devices. State Space Models (SSMs), exemplified by Mamba, offer an efficient alternative by combining global receptive fields with linear computational complexity, enabling scalable and resource-friendly sequence modeling. However, when applied to dense prediction tasks, existing visual SSMs face key limitations: weak spatial inductive bias, long-range forgetting from hidden state decay, and low-resolution outputs that hinder fine-grained localization. To address these issues, we propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations to enhance local spatial representations and strengthen spatial inductive biases. Through architectural exploration and theoretical analysis, we incorporate deformable operation into the DVSS block, identifying it as an efficient and effective mechanism to enhance semantic aggregation and mitigate long-range forgetting via input-dependent, adaptive spatial sampling. We embed DVSS into a multi-branch high-resolution architecture to build HRVMamba, a novel model for efficient high-resolution representation learning. Extensive experiments on human pose estimation, image classification, and semantic segmentation show that HRVMamba performs competitively against leading CNN-, ViT-, and SSM-based baselines. Code is available at https://github.com/zhanghao5201/PoseVMamba.

♻ ☆ RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System

Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast

The proliferation of AI-powered cameras in Intelligent Transportation Systems (ITS) creates a severe conflict between the need for rich visual data and the right to privacy. Existing privacy-preserving methods, such as blurring or encryption, are often insufficient due to creating an undesirable trade-off where either privacy is compromised against advanced reconstruction attacks or data utility is critically degraded. To resolve this challenge, we propose RL-MoE, a novel framework that transforms sensitive visual data into privacy-preserving textual descriptions, eliminating the need for direct image transmission. RL-MoE uniquely combines a Mixture-of-Experts (MoE) architecture for nuanced, multi-aspect scene decomposition with a Reinforcement Learning (RL) agent that optimizes the generated text for a dual objective of semantic accuracy and privacy preservation. Extensive experiments demonstrate that RL-MoE provides superior privacy protection, reducing the success rate of replay attacks to just 9.4\% on the CFP-FP dataset, while simultaneously generating richer textual content than baseline methods. Our work provides a practical and scalable solution for building trustworthy AI systems in privacy-sensitive domains, paving the way for more secure smart city and autonomous vehicle networks.

♻ ☆ IMU: Influence-guided Machine Unlearning

Xindi Fan, Jing Wu, Mingyi Zhou, Pengwei Liang, Dinh Phung

Recent studies have shown that deep learning models are vulnerable to attacks and tend to memorize training data points, raising significant concerns about privacy leakage. This motivates the development of machine unlearning (MU), i.e., a paradigm that enables models to selectively forget specific data points upon request. However, most existing MU algorithms require partial or full fine-tuning on the retain set. This necessitates continued access to the original training data, which is often impractical due to privacy concerns and storage constraints. A few retain-data-free MU methods have been proposed, but some rely on access to auxiliary data and precomputed statistics of the retain set, while others scale poorly when forgetting larger portions of data. In this paper, we propose Influence-guided Machine Unlearning (IMU), a simple yet effective method that conducts MU using only the forget set. Specifically, IMU employs gradient ascent and innovatively introduces dynamic allocation of unlearning intensities across different data points based on their influences. This adaptive strategy significantly enhances unlearning effectiveness while maintaining model utility. Results across vision and language tasks demonstrate that IMU consistently outperforms existing retain-data-free MU methods.

♻ ☆ MUNBa: Machine Unlearning via Nash Bargaining

Jing Wu, Mehrtash Harandi

Machine Unlearning (MU) aims to selectively erase harmful behaviors from models while retaining the overall utility of the model. As a multi-task learning problem, MU involves balancing objectives related to forgetting specific concepts/data and preserving general performance. A naive integration of these forgetting and preserving objectives can lead to gradient conflicts and dominance, impeding MU algorithms from reaching optimal solutions. To address the gradient conflict and dominance issue, we reformulate MU as a two-player cooperative game, where the two players, namely, the forgetting player and the preservation player, contribute via their gradient proposals to maximize their overall gain and balance their contributions. To this end, inspired by the Nash bargaining theory, we derive a closed-form solution to guide the model toward the Pareto stationary point. Our formulation of MU guarantees an equilibrium solution, where any deviation from the final state would lead to a reduction in the overall objectives for both players, ensuring optimality in each objective. We evaluate our algorithm's effectiveness on a diverse set of tasks across image classification and image generation. Extensive experiments with ResNet, vision-language model CLIP, and text-to-image diffusion models demonstrate that our method outperforms state-of-the-art MU algorithms, achieving a better trade-off between forgetting and preserving. Our results also highlight improvements in forgetting precision, preservation of generalization, and robustness against adversarial attacks.

♻ ☆ Preacher: Paper-to-Video Agentic System

Jingwei Liu, Ling Yang, Hao Luo, Fan Wang, Hongyan Li, Mengdi Wang

The paper-to-video task converts a research paper into a structured video abstract, distilling key concepts, methods, and conclusions into an accessible, well-organized format. While state-of-the-art video generation models demonstrate potential, they are constrained by limited context windows, rigid video duration constraints, limited stylistic diversity, and an inability to represent domain-specific knowledge. To address these limitations, we introduce Preacher, the first paper-to-video agentic system. Preacher employs a topdown approach to decompose, summarize, and reformulate the paper, followed by bottom-up video generation, synthesizing diverse video segments into a coherent abstract. To align cross-modal representations, we define key scenes and introduce a Progressive Chain of Thought (P-CoT) for granular, iterative planning. Preacher successfully generates high-quality video abstracts across five research fields, demonstrating expertise beyond current video generation models. Code will be released at: https://github.com/GenVerse/Paper2Video

comment: Code not ready

♻ ☆ Marmot: Object-Level Self-Correction via Multi-Agent Reasoning

Jiayang Sun, Hongbo Wang, Jie Cao, Huaibo Huang, Ran He

While diffusion models excel at generating high-quality images, they often struggle with accurate counting, attributes, and spatial relationships in complex multi-object scenes. One potential solution involves employing Multimodal Large Language Model (MLLM) as an AI agent to construct a self-correction framework. However, these approaches heavily rely on the capabilities of the MLLMs used, often fail to account for all objects within the image, and suffer from cumulative distortions during multi-round editing processes. To address these challenges, we propose Marmot, a novel and generalizable framework that leverages Multi-Agent Reasoning for Multi-Object Self-Correcting to enhance image-text alignment. First, we employ a large language model as an Object-Aware Agent to perform object-level divide-and-conquer, automatically decomposing self-correction tasks into object-centric subtasks based on image descriptions. For each subtask, we construct an Object Correction System featuring a decision-execution-verification mechanism that operates exclusively on a single object's segmentation mask or the bounding boxes of object pairs, effectively mitigating inter-object interference and enhancing editing reliability. To efficiently integrate correction results from subtasks while avoiding cumulative distortions from multi-stage editing, we propose a Pixel-Domain Stitching Smoother, which employs mask-guided two-stage latent space optimization. This innovation enables parallel processing of subtasks, significantly improving runtime efficiency while preventing distortion accumulation. Extensive experiments demonstrate that Marmot significantly improves accuracy in object counting, attribute assignment, and spatial relationships for image generation tasks.

♻ ☆ Towards Generalizable Forgery Detection and Reasoning

Yueying Gao, Dongliang Chang, Bingyao Yu, Haotian Qin, Muxi Diao, Lei Chen, Kongming Liang, Zhanyu Ma

Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain gap among generative models makes it challenging to develop a generalizable forgery detection model. Moreover, since every pixel in an AI-generated image is synthesized, traditional saliency-based forgery explanation methods are not well suited for this task. To address these challenges, we formulate detection and explanation as a unified Forgery Detection and Reasoning task (FDR-Task), leveraging Multi-Modal Large Language Models (MLLMs) to provide accurate detection through reliable reasoning over forgery attributes. To facilitate this task, we introduce the Multi-Modal Forgery Reasoning dataset (MMFR-Dataset), a large-scale dataset containing 120K images across 10 generative models, with 378K reasoning annotations on forgery attributes, enabling comprehensive evaluation of the FDR-Task. Furthermore, we propose FakeReasoning, a forgery detection and reasoning framework with three key components: 1) a dual-branch visual encoder that integrates CLIP and DINO to capture both high-level semantics and low-level artifacts; 2) a Forgery-Aware Feature Fusion Module that leverages DINO's attention maps and cross-attention mechanisms to guide MLLMs toward forgery-related clues; 3) a Classification Probability Mapper that couples language modeling and forgery detection, enhancing overall performance. Experiments across multiple generative models demonstrate that FakeReasoning not only achieves robust generalization but also outperforms state-of-the-art methods on both detection and reasoning tasks.

♻ ☆ LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding

Feng Xiao, Hongbin Xu, Guocan Zhao, Wenxiong Kang

3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the described spatial relationships. Current methods attempt to achieve cross-modal understanding in complex scenes via a target-centered learning mechanism, ignoring the modeling of referred objects. We propose a novel 3D visual grounding framework that constructs language-guided scene graphs with referred object discrimination to improve relational perception. The framework incorporates a dual-branch visual encoder that leverages pre-trained 2D semantics to enhance and supervise the multi-modal 3D encoding. Furthermore, we employ graph attention to promote relationship-oriented information fusion in cross-modal interaction. The learned object representations and scene graph structure enable effective alignment between 3D visual content and textual descriptions. Experimental results on popular benchmarks demonstrate our superior performance compared to state-of-the-art methods, especially in handling the challenges of multiple similar distractors.

♻ ☆ HealthiVert-GAN: A Novel Framework of Pseudo-Healthy Vertebral Image Synthesis for Interpretable Compression Fracture Grading

Qi Zhang, Cheng Chuang, Shunan Zhang, Ziqi Zhao, Kun Wang, Jun Xu, Jianqi Sun

Osteoporotic vertebral compression fractures (OVCFs) are prevalent in the elderly population, typically assessed on computed tomography (CT) scans by evaluating vertebral height loss. This assessment helps determine the fracture's impact on spinal stability and the need for surgical intervention. However, the absence of pre-fracture CT scans and standardized vertebral references leads to measurement errors and inter-observer variability, while irregular compression patterns further challenge the precise grading of fracture severity. While deep learning methods have shown promise in aiding OVCFs screening, they often lack interpretability and sufficient sensitivity, limiting their clinical applicability. To address these challenges, we introduce a novel vertebra synthesis-height loss quantification-OVCFs grading framework. Our proposed model, HealthiVert-GAN, utilizes a coarse-to-fine synthesis network designed to generate pseudo-healthy vertebral images that simulate the pre-fracture state of fractured vertebrae. This model integrates three auxiliary modules that leverage the morphology and height information of adjacent healthy vertebrae to ensure anatomical consistency. Additionally, we introduce the Relative Height Loss of Vertebrae (RHLV) as a quantification metric, which divides each vertebra into three sections to measure height loss between pre-fracture and post-fracture states, followed by fracture severity classification using a Support Vector Machine (SVM). Our approach achieves state-of-the-art classification performance on both the Verse2019 dataset and in-house dataset, and it provides cross-sectional distribution maps of vertebral height loss. This practical tool enhances diagnostic accuracy in clinical settings and assisting in surgical decision-making.

♻ ☆ Pathology-Guided AI System for Accurate Segmentation and Diagnosis of Cervical Spondylosis

Qi Zhang, Xiuyuan Chen, Ziyi He, Lianming Wu, Kun Wang, Jianqi Sun, Hongxing Shen

Cervical spondylosis, a complex and prevalent condition, demands precise and efficient diagnostic techniques for accurate assessment. While MRI offers detailed visualization of cervical spine anatomy, manual interpretation remains labor-intensive and prone to error. To address this, we developed an innovative AI-assisted Expert-based Diagnosis System that automates both segmentation and diagnosis of cervical spondylosis using MRI. Leveraging multi-center datasets of cervical MRI images from patients with cervical spondylosis, our system features a pathology-guided segmentation model capable of accurately segmenting key cervical anatomical structures. The segmentation is followed by an expert-based diagnostic framework that automates the calculation of critical clinical indicators. Our segmentation model achieved an impressive average Dice coefficient exceeding 0.90 across four cervical spinal anatomies and demonstrated enhanced accuracy in herniation areas. Diagnostic evaluation further showcased the system's precision, with the lowest mean average errors (MAE) for the C2-C7 Cobb angle and the Maximum Spinal Cord Compression (MSCC) coefficient. In addition, our method delivered high accuracy, precision, recall, and F1 scores in herniation localization, K-line status assessment, T2 hyperintensity detection, and Kang grading. Comparative analysis and external validation demonstrate that our system outperforms existing methods, establishing a new benchmark for segmentation and diagnostic tasks for cervical spondylosis.

♻ ☆ PRS-Med: Position Reasoning Segmentation with Vision-Language Model in Medical Imaging

Quoc-Huy Trinh, Minh-Van Nguyen, Jung Zeng, Ulas Bagci, Debesh Jha

Recent advancements in prompt-based medical image segmentation have enabled clinicians to identify tumors using simple input like bounding boxes or text prompts. However, existing methods face challenges when doctors need to interact through natural language or when position reasoning is required - understanding spatial relationships between anatomical structures and pathologies. We present PRS-Med, a framework that integrates vision-language models with segmentation capabilities to generate both accurate segmentation masks and corresponding spatial reasoning outputs. Additionally, we introduce the MMRS dataset (Multimodal Medical in Positional Reasoning Segmentation), which provides diverse, spatially-grounded question-answer pairs to address the lack of position reasoning data in medical imaging. PRS-Med demonstrates superior performance across six imaging modalities (CT, MRI, X-ray, ultrasound, endoscopy, RGB), significantly outperforming state-of-the-art methods in both segmentation accuracy and position reasoning. Our approach enables intuitive doctor-system interaction through natural language, facilitating more efficient diagnoses. Our dataset pipeline, model, and codebase will be released to foster further research in spatially-aware multimodal reasoning for medical applications.

♻ ☆ From Explainable to Explained AI: Ideas for Falsifying and Quantifying Explanations

Yoni Schirris, Eric Marcus, Jonas Teuwen, Hugo Horlings, Efstratios Gavves

Explaining deep learning models is essential for clinical integration of medical image analysis systems. A good explanation highlights if a model depends on spurious features that undermines generalization and harms a subset of patients or, conversely, may present novel biological insights. Although techniques like GradCAM can identify influential features, they are measurement tools that do not themselves form an explanation. We propose a human-machine-VLM interaction system tailored to explaining classifiers in computational pathology, including multi-instance learning for whole-slide images. Our proof of concept comprises (1) an AI-integrated slide viewer to run sliding-window experiments to test claims of an explanation, and (2) quantification of an explanation's predictiveness using general-purpose vision-language models. The results demonstrate that this allows us to qualitatively test claims of explanations and can quantifiably distinguish competing explanations. This offers a practical path from explainable AI to explained AI in digital pathology and beyond. Code and prompts are available at https://github.com/nki-ai/x2x.

comment: 10 pages, 2 figures, 2 tables, submitted at MICCAI IMIMIC workshop

♻ ☆ Learning Camera-Agnostic White-Balance Preferences

Luxi Zhao, Mahmoud Afifi, Michael S. Brown

The image signal processor (ISP) pipeline in modern cameras consists of several modules that transform raw sensor data into visually pleasing images in a display color space. Among these, the auto white balance (AWB) module is essential for compensating for scene illumination. However, commercial AWB systems often strive to compute aesthetic white-balance preferences rather than accurate neutral color correction. While learning-based methods have improved AWB accuracy, they typically struggle to generalize across different camera sensors -- an issue for smartphones with multiple cameras. Recent work has explored cross-camera AWB, but most methods remain focused on achieving neutral white balance. In contrast, this paper is the first to address aesthetic consistency by learning a post-illuminant-estimation mapping that transforms neutral illuminant corrections into aesthetically preferred corrections in a camera-agnostic space. Once trained, our mapping can be applied after any neutral AWB module to enable consistent and stylized color rendering across unseen cameras. Our proposed model is lightweight -- containing only $\sim$500 parameters -- and runs in just 0.024 milliseconds on a typical flagship mobile CPU. Evaluated on a dataset of 771 smartphone images from three different cameras, our method achieves state-of-the-art performance while remaining fully compatible with existing cross-camera AWB techniques, introducing minimal computational and memory overhead.

♻ ☆ Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation

Meng Chen, Jiawei Tu, Chao Qi, Yonghao Dang, Feng Zhou, Wei Wei, Jianqin Yin

The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is crucial, especially given the threat of 3D physical attacks that could pose risks to human safety. However, existing attack methods for embodied vision navigation often lack physical feasibility due to challenges in transferring digital perturbations into the physical world. Moreover, current physical attacks for object detection struggle to achieve both multi-view effectiveness and visual naturalness in navigation scenarios. To address this, we propose a practical attack method for embodied navigation by attaching adversarial patches to objects, where both opacity and textures are learnable. Specifically, to ensure effectiveness across varying viewpoints, we employ a multi-view optimization strategy based on object-aware sampling, which optimizes the patch's texture based on feedback from the vision-based perception model used in navigation. To make the patch inconspicuous to human observers, we introduce a two-stage opacity optimization mechanism, in which opacity is fine-tuned after texture optimization. Experimental results demonstrate that our adversarial patches decrease the navigation success rate by an average of 22.39%, outperforming previous methods in practicality, effectiveness, and naturalness. Code is available at: https://github.com/chen37058/Physical-Attacks-in-Embodied-Nav

comment: 7 pages, 7 figures, Accept by IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025

♻ ☆ Physics-Guided Image Dehazing Diffusion

Shijun Zhou, Baojie Fan, Jiandong Tian

Due to the domain gap between real-world and synthetic hazy images, current data-driven dehazing algorithms trained on synthetic datasets perform well on synthetic data but struggle to generalize to real-world scenarios. To address this challenge, we propose \textbf{I}mage \textbf{D}ehazing \textbf{D}iffusion \textbf{M}odels (IDDM), a novel diffusion process that incorporates the atmospheric scattering model into noise diffusion. IDDM aims to use the gradual haze formation process to help the denoising Unet robustly learn the distribution of clear images from the conditional input hazy images. We design a specialized training strategy centered around IDDM. Diffusion models are leveraged to bridge the domain gap from synthetic to real-world, while the atmospheric scattering model provides physical guidance for haze formation. During the forward process, IDDM simultaneously introduces haze and noise into clear images, and then robustly separates them during the sampling process. By training with physics-guided information, IDDM shows the ability of domain generalization, and effectively restores the real-world hazy images despite being trained on synthetic datasets. Extensive experiments demonstrate the effectiveness of our method through both quantitative and qualitative comparisons with state-of-the-art approaches.

♻ ☆ Reverse Convolution and Its Applications to Image Restoration

Xuhong Huang, Shiqi Liu, Kai Zhang, Ying Tai, Jian Yang, Hui Zeng, Lei Zhang

Convolution and transposed convolution are fundamental operators widely used in neural networks. However, transposed convolution (a.k.a. deconvolution) does not serve as a true inverse of convolution due to inherent differences in their mathematical formulations. To date, no reverse convolution operator has been established as a standard component in neural architectures. In this paper, we propose a novel depthwise reverse convolution operator as an initial attempt to effectively reverse depthwise convolution by formulating and solving a regularized least-squares optimization problem. We thoroughly investigate its kernel initialization, padding strategies, and other critical aspects to ensure its effective implementation. Building upon this operator, we further construct a reverse convolution block by combining it with layer normalization, 1$\times$1 convolution, and GELU activation, forming a Transformer-like structure. The proposed operator and block can directly replace conventional convolution and transposed convolution layers in existing architectures, leading to the development of ConverseNet. Corresponding to typical image restoration models such as DnCNN, SRResNet and USRNet, we train three variants of ConverseNet for Gaussian denoising, super-resolution and deblurring, respectively. Extensive experiments demonstrate the effectiveness of the proposed reverse convolution operator as a basic building module. We hope this work could pave the way for developing new operators in deep model design and applications.

comment: ICCV 2025; https://github.com/cszn/ConverseNet

♻ ☆ Zero-Shot Anomaly Detection with Dual-Branch Prompt Selection

Zihan Wang, Samira Ebrahimi Kahou, Narges Armanfard

Zero-shot anomaly detection (ZSAD) enables identifying and localizing defects in unseen categories by relying solely on generalizable features rather than requiring any labeled examples of anomalies. However, existing ZSAD methods, whether using fixed or learned prompts, struggle under domain shifts because their training data are derived from limited training domains and fail to generalize to new distributions. In this paper, we introduce PILOT, a framework designed to overcome these challenges through two key innovations: (1) a novel dual-branch prompt learning mechanism that dynamically integrates a pool of learnable prompts with structured semantic attributes, enabling the model to adaptively weight the most relevant anomaly cues for each input image; and (2) a label-free test-time adaptation strategy that updates the learnable prompt parameters using high-confidence pseudo-labels from unlabeled test data. Extensive experiments on 13 industrial and medical benchmarks demonstrate that PILOT achieves state-of-the-art performance in both anomaly detection and localization under domain shift.

comment: Accepted at BMVC 2025

♻ ☆ FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing

Jinya Sakurai, Issei Sato

The proliferation of Text-to-Image (T2I) models has revolutionized content creation, providing powerful tools for diverse applications ranging from artistic expression to educational material development and marketing. Despite these technological advancements, significant ethical concerns arise from these models' reliance on large-scale datasets that often contain inherent societal biases. These biases are further amplified when AI-generated content is included in training data, potentially reinforcing and perpetuating stereotypes in the generated outputs. In this paper, we introduce FairT2I, a novel framework that harnesses large language models to detect and mitigate social biases in T2I generation. Our framework comprises two key components: (1) an LLM-based bias detection module that identifies potential social biases in generated images based on text prompts, and (2) an attribute rebalancing module that fine-tunes sensitive attributes within the T2I model to mitigate identified biases. Our extensive experiments across various T2I models and datasets show that FairT2I can significantly reduce bias while maintaining high-quality image generation. We conducted both qualitative user studies and quantitative non-parametric analyses in the generated image feature space, building upon the occupational dataset introduced in the Stable Bias study. Our results show that FairT2I successfully mitigates social biases and enhances the diversity of sensitive attributes in generated images. We further demonstrate, using the P2 dataset, that our framework can detect subtle biases that are challenging for human observers to perceive, extending beyond occupation-related prompts. On the basis of these findings, we introduce a new benchmark dataset for evaluating bias in T2I models.

♻ ☆ SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models

Nader Zantout, Haochen Zhang, Pujith Kachana, Jinkai Qiu, Guofei Chen, Ji Zhang, Wenshan Wang

Interpreting object-referential language and grounding objects in 3D with spatial relations and attributes is essential for robots operating alongside humans. However, this task is often challenging due to the diversity of scenes, large number of fine-grained objects, and complex free-form nature of language references. Furthermore, in the 3D domain, obtaining large amounts of natural language training data is difficult. Thus, it is important for methods to learn from little data and zero-shot generalize to new environments. To address these challenges, we propose SORT3D, an approach that utilizes rich object attributes from 2D data and merges a heuristics-based spatial reasoning toolbox with the ability of large language models (LLMs) to perform sequential reasoning. Importantly, our method does not require text-to-3D data for training and can be applied zero-shot to unseen environments. We show that SORT3D achieves state-of-the-art zero-shot performance on complex view-dependent grounding tasks on two benchmarks. We also implement the pipeline to run real-time on two autonomous vehicles and demonstrate that our approach can be used for object-goal navigation on previously unseen real-world environments. All source code for the system pipeline is publicly released at https://github.com/nzantout/SORT3D.

comment: 8 pages, 6 figures, published in IROS 2025

♻ ☆ Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment

Ziheng Jia, Jiaying Qian, Zicheng Zhang, Zijian Chen, Xiongkuo Min

Reinforcement fine-tuning (RFT) is a proliferating paradigm for LMM training. Analogous to high-level reasoning tasks, RFT is similarly applicable to low-level vision domains, including image quality assessment (IQA). Existing RFT-based IQA methods typically use rule-based output rewards to verify the model's rollouts but provide no reward supervision for the "think" process, leaving its correctness and efficacy uncontrolled. Furthermore, these methods typically fine-tune directly on downstream IQA tasks without explicitly enhancing the model's native low-level visual quality perception, which may constrain its performance upper bound. In response to these gaps, we propose the multi-stage RFT IQA framework (Refine-IQA). In Stage-1, we build the Refine-Perception-20K dataset (with 12 main distortions, 20,907 locally-distorted images, and over 55K RFT samples) and design multi-task reward functions to strengthen the model's visual quality perception. In Stage-2, targeting the quality scoring task, we introduce a probability difference reward involved strategy for "think" process supervision. The resulting Refine-IQA Series Models achieve outstanding performance on both perception and scoring tasks-and, notably, our paradigm activates a robust "think" (quality interpreting) capability that also attains exceptional results on the corresponding quality interpreting benchmark.

2025-08-14

Sound 13

☆ Advances in Speech Separation: Techniques, Challenges, and Future Trends

Kai Li, Guo Chen, Wendi Sang, Yi Luo, Zhuo Chen, Shuai Wang, Shulin He, Zhong-Qiu Wang, Andong Li, Zhiyong Wu, Xiaolin Hu

The field of speech separation, addressing the "cocktail party problem", has seen revolutionary advances with DNNs. Speech separation enhances clarity in complex acoustic environments and serves as crucial pre-processing for speech recognition and speaker recognition. However, current literature focuses narrowly on specific architectures or isolated approaches, creating fragmented understanding. This survey addresses this gap by providing systematic examination of DNN-based speech separation techniques. Our work differentiates itself through: (I) Comprehensive perspective: We systematically investigate learning paradigms, separation scenarios with known/unknown speakers, comparative analysis of supervised/self-supervised/unsupervised frameworks, and architectural components from encoders to estimation strategies. (II) Timeliness: Coverage of cutting-edge developments ensures access to current innovations and benchmarks. (III) Unique insights: Beyond summarization, we evaluate technological trajectories, identify emerging patterns, and highlight promising directions including domain-robust frameworks, efficient architectures, multimodal integration, and novel self-supervised paradigms. (IV) Fair evaluation: We provide quantitative evaluations on standard datasets, revealing true capabilities and limitations of different methods. This comprehensive survey serves as an accessible reference for experienced researchers and newcomers navigating speech separation's complex landscape.

comment: 34 pages, 10 figures

☆ Ensembling Synchronisation-based and Face-Voice Association Paradigms for Robust Active Speaker Detection in Egocentric Recordings

Jason Clarke, Yoshihiko Gotoh, Stefan Goetze

Audiovisual active speaker detection (ASD) in egocentric recordings is challenged by frequent occlusions, motion blur, and audio interference, which undermine the discernability of temporal synchrony between lip movement and speech. Traditional synchronisation-based systems perform well under clean conditions but degrade sharply in first-person recordings. Conversely, face-voice association (FVA)-based methods forgo synchronisation modelling in favour of cross-modal biometric matching, exhibiting robustness to transient visual corruption but suffering when overlapping speech or front-end segmentation errors occur. In this paper, a simple yet effective ensemble approach is proposed to fuse synchronisation-dependent and synchronisation-agnostic model outputs via weighted averaging, thereby harnessing complementary cues without introducing complex fusion architectures. A refined preprocessing pipeline for the FVA-based component is also introduced to optimise ensemble integration. Experiments on the Ego4D-AVD validation set demonstrate that the ensemble attains 70.2% and 66.7% mean Average Precision (mAP) with TalkNet and Light-ASD backbones, respectively. A qualitative analysis stratified by face image quality and utterance masking prevalence further substantiates the complementary strengths of each component.

comment: Accepted to SPECOM 2025, 13 pages, 4 figures. To appear in the Proceedings of the 27th International Conference on Speech and Computer (SPECOM) 2025, October 13-14, 2025, Szeged, Hungary

☆ Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform

Yuankun Xie, Ruibo Fu, Xiaopeng Wang, Zhiyong Wang, Ya Li, Zhengqi Wen, Haonnan Cheng, Long Ye

The rapid advancement of speech generation technology has led to the widespread proliferation of deepfake speech across social media platforms. While deepfake audio countermeasures (CMs) achieve promising results on public datasets, their performance degrades significantly in cross-domain scenarios. To advance CMs for real-world deepfake detection, we first propose the Fake Speech Wild (FSW) dataset, which includes 254 hours of real and deepfake audio from four different media platforms, focusing on social media. As CMs, we establish a benchmark using public datasets and advanced selfsupervised learning (SSL)-based CMs to evaluate current CMs in real-world scenarios. We also assess the effectiveness of data augmentation strategies in enhancing CM robustness for detecting deepfake speech on social media. Finally, by augmenting public datasets and incorporating the FSW training set, we significantly advanced real-world deepfake audio detection performance, achieving an average equal error rate (EER) of 3.54% across all evaluation sets.

☆ Motive-level Analysis of Form-functions Association in Korean Folk song

Danbinaerin Han, Dasaem Jeong, Juhan Nam

Computational analysis of folk song audio is challenging due to structural irregularities and the need for manual annotation. We propose a method for automatic motive segmentation in Korean folk songs by fine-tuning a speech transcription model on audio lyric with motif boundary annotation. Applying this to 856 songs, we extracted motif count and duration entropy as structural features. Statistical analysis revealed that these features vary systematically according to the social function of the songs. Songs associated with collective labor, for instance, showed different structural patterns from those for entertainment or personal settings. This work offers a scalable approach for quantitative structural analysis of oral music traditions.

☆ Alternating Approach-Putt Models for Multi-Stage Speech Enhancement

Iksoon Jeong, Kyung-Joong Kim, Kang-Hun Ahn

Speech enhancement using artificial neural networks aims to remove noise from noisy speech signals while preserving the speech content. However, speech enhancement networks often introduce distortions to the speech signal, referred to as artifacts, which can degrade audio quality. In this work, we propose a post-processing neural network designed to mitigate artifacts introduced by speech enhancement models. Inspired by the analogy of making a `Putt' after an `Approach' in golf, we name our model PuttNet. We demonstrate that alternating between a speech enhancement model and the proposed Putt model leads to improved speech quality, as measured by perceptual quality scores (PESQ), objective intelligibility (STOI), and background noise intrusiveness (CBAK) scores. Furthermore, we illustrate with graphical analysis why this alternating Approach outperforms repeated application of either model alone.

comment: This work has been submitted to the IEEE for possible publication

☆ MCP2OSC: Parametric Control by Natural Language

Yuan-Yi Fan

Text prompts enable intuitive content creation but may fall short in achieving high precision for intricate tasks; knob or slider controls offer precise adjustments at the cost of increased complexity. To address the gap between knobs and prompts, a new MCP (Model Context Protocol) server and a unique set of prompt design criteria are presented to enable exploring parametric OSC (OpenSoundControl) control by natural language prompts. Demonstrated by 14 practical QA examples with best practices and the generalized prompt templates, this study finds Claude integrated with the MCP2OSC server effective in generating OSC messages by natural language, interpreting, searching, and visualizing OSC messages, validating and debugging OSC messages, and managing OSC address patterns. MCP2OSC enhances human-machine collaboration by leveraging LLM (Large Language Model) to handle intricate OSC development tasks, and by empowering human creativity with an intuitive language interface featuring flexible precision controls: a prompt-based OSC tool. This study provides a novel perspective on the creative MCP application at the network protocol level by utilizing LLM's strength in directly processing and generating human-readable OSC messages. The results suggest its potential for a LLM-based universal control mechanism for multimedia devices.

☆ Facilitating Personalized TTS for Dysarthric Speakers Using Knowledge Anchoring and Curriculum Learning

Yejin Jeon, Solee Im, Youngjae Kim, Gary Geunbae Lee

Dysarthric speakers experience substantial communication challenges due to impaired motor control of the speech apparatus, which leads to reduced speech intelligibility. This creates significant obstacles in dataset curation since actual recording of long, articulate sentences for the objective of training personalized TTS models becomes infeasible. Thus, the limited availability of audio data, in addition to the articulation errors that are present within the audio, complicates personalized speech synthesis for target dysarthric speaker adaptation. To address this, we frame the issue as a domain transfer task and introduce a knowledge anchoring framework that leverages a teacher-student model, enhanced by curriculum learning through audio augmentation. Experimental results show that the proposed zero-shot multi-speaker TTS model effectively generates synthetic speech with markedly reduced articulation errors and high speaker fidelity, while maintaining prosodic naturalness.

comment: Interspeech 2025

☆ A dataset and model for recognition of audiologically relevant environments for hearing aids: AHEAD-DS and YAMNet+

Henry Zhong, Jörg M. Buchholz, Julian Maclaren, Simon Carlile, Richard Lyon

Scene recognition of audiologically relevant environments is important for hearing aids; however, it is challenging, in part because of the limitations of existing datasets. Datasets often lack public accessibility, completeness, or audiologically relevant labels, hindering systematic comparison of machine learning models. Deploying these models on resource-constrained edge devices presents another challenge. Our solution is two-fold: we leverage several open source datasets to create AHEAD-DS, a dataset designed for scene recognition of audiologically relevant environments, and introduce YAMNet+, a sound recognition model. AHEAD-DS aims to provide a standardised, publicly available dataset with consistent labels relevant to hearing aids, facilitating model comparison. YAMNet+ is designed for deployment on edge devices like smartphones connected to hearing devices, such as hearing aids and wireless earphones with hearing aid functionality; serving as a baseline model for sound-based scene recognition. YAMNet+ achieved a mean average precision of 0.83 and accuracy of 0.93 on the testing set of AHEAD-DS across fourteen categories of audiologically relevant environments. We found that applying transfer learning from the pretrained YAMNet model was essential. We demonstrated real-time sound-based scene recognition capabilities on edge devices by deploying YAMNet+ to an Android smartphone. Even with a Google Pixel 3 (a phone with modest specifications, released in 2018), the model processes audio with approximately 50ms of latency to load the model, and an approximate linear increase of 30ms per 1 second of audio. Our website and code https://github.com/Australian-Future-Hearing-Initiative .

☆ Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech

Abhijit Sinha, Harishankar Kumar, Mohit Joshi, Hemant Kumar Kathania, Shrikanth Narayanan, Sudarsana Reddy Kadiri

Children's speech presents challenges for age and gender classification due to high variability in pitch, articulation, and developmental traits. While self-supervised learning (SSL) models perform well on adult speech tasks, their ability to encode speaker traits in children remains underexplored. This paper presents a detailed layer-wise analysis of four Wav2Vec2 variants using the PFSTAR and CMU Kids datasets. Results show that early layers (1-7) capture speaker-specific cues more effectively than deeper layers, which increasingly focus on linguistic information. Applying PCA further improves classification, reducing redundancy and highlighting the most informative components. The Wav2Vec2-large-lv60 model achieves 97.14% (age) and 98.20% (gender) on CMU Kids; base-100h and large-lv60 models reach 86.05% and 95.00% on PFSTAR. These results reveal how speaker traits are structured across SSL model depth and support more targeted, adaptive strategies for child-aware speech interfaces.

comment: Accepted at Workshop on Child Computer Interaction (WOCCI 2025)

☆ LD-LAudio-V1: Video-to-Long-Form-Audio Generation Extension with Dual Lightweight Adapters

Haomin Zhang, Kristin Qi, Shuxin Yang, Zihao Chen, Chaofan Ding, Xinhan Di

Generating high-quality and temporally synchronized audio from video content is essential for video editing and post-production tasks, enabling the creation of semantically aligned audio for silent videos. However, most existing approaches focus on short-form audio generation for video segments under 10 seconds or rely on noisy datasets for long-form video-to-audio zsynthesis. To address these limitations, we introduce LD-LAudio-V1, an extension of state-of-the-art video-to-audio models and it incorporates dual lightweight adapters to enable long-form audio generation. In addition, we release a clean and human-annotated video-to-audio dataset that contains pure sound effects without noise or artifacts. Our method significantly reduces splicing artifacts and temporal inconsistencies while maintaining computational efficiency. Compared to direct fine-tuning with short training videos, LD-LAudio-V1 achieves significant improvements across multiple metrics: $FD_{\text{passt}}$ 450.00 $\rightarrow$ 327.29 (+27.27%), $FD_{\text{panns}}$ 34.88 $\rightarrow$ 22.68 (+34.98%), $FD_{\text{vgg}}$ 3.75 $\rightarrow$ 1.28 (+65.87%), $KL_{\text{panns}}$ 2.49 $\rightarrow$ 2.07 (+16.87%), $KL_{\text{passt}}$ 1.78 $\rightarrow$ 1.53 (+14.04%), $IS_{\text{panns}}$ 4.17 $\rightarrow$ 4.30 (+3.12%), $IB_{\text{score}}$ 0.25 $\rightarrow$ 0.28 (+12.00%), $Energy\Delta10\text{ms}$ 0.3013 $\rightarrow$ 0.1349 (+55.23%), $Energy\Delta10\text{ms(vs.GT)}$ 0.0531 $\rightarrow$ 0.0288 (+45.76%), and $Sem.\,Rel.$ 2.73 $\rightarrow$ 3.28 (+20.15%). Our dataset aims to facilitate further research in long-form video-to-audio generation and is available at https://github.com/deepreasonings/long-form-video2audio.

comment: Gen4AVC@ICCV: 1st Workshop on Generative AI for Audio-Visual Content Creation

♻ ☆ Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition

Leonora Vesterbacka, Faton Rekathati, Robin Kurtz, Justyna Sikora, Agnes Toftgård

This work presents a suite of fine-tuned Whisper models for Swedish, trained on a dataset of unprecedented size and variability for this mid-resourced language. As languages of smaller sizes are often underrepresented in multilingual training datasets, substantial improvements in performance can be achieved by fine-tuning existing multilingual models, as shown in this work. This work reports an overall improvement across model sizes compared to OpenAI's Whisper evaluated on Swedish. Most notably, we report an average 47% reduction in WER comparing our best performing model to OpenAI's whisper-large-v3, in evaluations across FLEURS, Common Voice, and NST.

comment: Accepted at Interspeech 2025

♻ ☆ Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions

Aditya Ashvin, Rimita Lahiri, Aditya Kommineni, Somer Bishop, Catherine Lord, Sudarsana Reddy Kadiri, Shrikanth Narayanan

Reliable transcription of child-adult conversations in clinical settings is crucial for diagnosing developmental disorders like Autism. Recent advances in deep learning and availability of large scale transcribed data has led to development of speech foundation models that have shown dramatic improvements in ASR performance. However, their performance on conversational child-adult interactions remains underexplored. In this work, we provide a comprehensive evaluation of ASR performance on a dataset containing child-adult interactions from autism diagnostic sessions, using Whisper, Wav2Vec2, HuBERT, and WavLM. We find that speech foundation models show a noticeable performance drop (15-20% absolute WER) for child speech compared to adult speech in the conversational setting. Then, we fine-tune the best-performing zero-shot model (Whisper-large) using LoRA in a low-resource setting, yielding 8% and 13% absolute WER improvements for child and adult speech, respectively.

comment: Accepted at Workshop on Child Computer Interaction (WOCCI 2025)

♻ ☆ Marco-Voice Technical Report

Fengping Tian, Chenyang Lyu, Xuanfan Ni, Haoqin Sun, Qingjuan Li, Zhiqiang Qian, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo, Kaifu Zhang

This paper presents a multifunctional speech synthesis system that integrates voice cloning and emotion control speech synthesis within a unified framework. The goal of this work is to address longstanding challenges in achieving highly expressive, controllable, and natural speech generation that faithfully preserves speaker identity across diverse linguistic and emotional contexts. Our approach introduces an effective speaker-emotion disentanglement mechanism with in-batch contrastive learning, enabling independent manipulation of speaker identity and eemotional style, as well as rotational emotional embedding integration method for smooth emotion control. To support comprehensive training and evaluation, we construct CSEMOTIONS, a high-quality emotional speech dataset containing 10 hours of Mandarin speech from six professional speakers across seven emotional categories. Extensive experiments demonstrate that our system, Marco-Voice, achieves substantial improvements in both objective and subjective metrics. Comprehensive evaluations and analysis were conducted, results show that MarcoVoice delivers competitive performance in terms of speech clarity and emotional richness, representing a substantial advance in the field of expressive neural speech synthesis. Our code and dataset are publicly available at https://github.com/AIDC-AI/Marco-Voice and https://huggingface.co/datasets/AIDC-AI/CSEMOTIONS respectively.

comment: Technical Report. Our code and dataset are publicly available at https://github.com/AIDC-AI/Marco-Voice and https://huggingface.co/datasets/AIDC-AI/CSEMOTIONS respectively

Audio and Speech Processing 13

☆ Advances in Speech Separation: Techniques, Challenges, and Future Trends

Kai Li, Guo Chen, Wendi Sang, Yi Luo, Zhuo Chen, Shuai Wang, Shulin He, Zhong-Qiu Wang, Andong Li, Zhiyong Wu, Xiaolin Hu

comment: 34 pages, 10 figures

☆ Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems

Mingyu Cui, Mengzhe Geng, Jiajun Deng, Chengxi Deng, Jiawen Kang, Shujie Hu, Guinan Li, Tianzi Wang, Zhaoqing Li, Xie Chen, Xunying Liu

This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding concatenation; iii) cross-utterance Encoder embedding pooling projection; or iv) a novel chunk-based approach applied to C-T models for the first time. An efficient batch-training scheme is proposed for contextual C-Ts that uses spliced speech utterances within each minibatch to minimize the synchronization overhead while preserving the sequential order of cross-utterance speech contexts. Experiments are conducted on four benchmark speech datasets across three languages: the English GigaSpeech and Mandarin Wenetspeech corpora used in contextual C-T models pre-training; and the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech datasets used in domain fine-tuning. The best performing contextual C-T systems consistently outperform their respective baselines using no cross-utterance speech contexts in pre-training and fine-tuning stages with statistically significant average word error rate (WER) or character error rate (CER) reductions up to 0.9%, 1.1%, 0.51%, and 0.98% absolute (6.0%, 5.4%, 2.0%, and 3.4% relative) on the four tasks respectively. Their performance competitiveness against Wav2vec2.0-Conformer, XLSR-128, and Whisper models highlights the potential benefit of incorporating cross-utterance speech contexts into current speech foundation models.

☆ Alternating Approach-Putt Models for Multi-Stage Speech Enhancement

Iksoon Jeong, Kyung-Joong Kim, Kang-Hun Ahn

comment: This work has been submitted to the IEEE for possible publication

☆ MCP2OSC: Parametric Control by Natural Language

Yuan-Yi Fan

☆ Towards Frame-level Quality Predictions of Synthetic Speech

Michael Kuhlmann, Fritz Seebauer, Petra Wagner, Reinhold Haeb-Umbach

While automatic subjective speech quality assessment has witnessed much progress, an open question is whether an automatic quality assessment at frame resolution is possible. This would be highly desirable, as it adds explainability to the assessment of speech synthesis systems. Here, we take first steps towards this goal by identifying issues of existing quality predictors that prevent sensible frame-level prediction. Further, we define criteria that a frame-level predictor should fulfill. We also suggest a chunk-based processing that avoids the impact of a localized distortion on the score of neighboring frames. Finally, we measure in experiments with localized artificial distortions the localization performance of a set of frame-level quality predictors and show that they can outperform detection performance of human annotations obtained from a crowd-sourced perception experiment.

comment: Accepted at Interspeech 2025

☆ A dataset and model for recognition of audiologically relevant environments for hearing aids: AHEAD-DS and YAMNet+

Henry Zhong, Jörg M. Buchholz, Julian Maclaren, Simon Carlile, Richard Lyon

☆ Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech

Abhijit Sinha, Harishankar Kumar, Mohit Joshi, Hemant Kumar Kathania, Shrikanth Narayanan, Sudarsana Reddy Kadiri

comment: Accepted at Workshop on Child Computer Interaction (WOCCI 2025)

☆ LD-LAudio-V1: Video-to-Long-Form-Audio Generation Extension with Dual Lightweight Adapters

Haomin Zhang, Kristin Qi, Shuxin Yang, Zihao Chen, Chaofan Ding, Xinhan Di

comment: Gen4AVC@ICCV: 1st Workshop on Generative AI for Audio-Visual Content Creation

♻ ☆ Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition

Leonora Vesterbacka, Faton Rekathati, Robin Kurtz, Justyna Sikora, Agnes Toftgård

comment: Accepted at Interspeech 2025

♻ ☆ Speech Enhancement based on cascaded two flow

Seonggyu Lee, Sein Cheong, Sangwook Han, Kihyuk Kim, Jong Won Shin

comment: Accepted at Interspeech 2025

♻ ☆ Navigating PESQ: Up-to-Date Versions and Open Implementations

Matteo Torcoli, Mhd Modar Halimeh, Emanuël A. P. Habets

Perceptual Evaluation of Speech Quality (PESQ) is an objective quality measure that remains widely used despite its withdrawal by the International Telecommunication Union (ITU). PESQ has evolved over two decades, with multiple versions and publicly available implementations emerging during this time. Different versions and their updates can be overwhelming, especially for new PESQ users. This work provides practical guidance on the different versions and implementations of PESQ. We show that differences can be significant, especially between PESQ versions. We stress the importance of specifying the exact version and implementation that is used to compute PESQ, and possibly to detail how multi-channel signals are handled. These practices would facilitate the interpretation of results and allow comparisons of PESQ scores between different studies. We also provide a repository that implements the latest corrections to PESQ, i.e., Corrigendum 2, which is not implemented by any other openly available distribution: https://github.com/audiolabs/PESQ.

comment: Accepted for presentation at ITG Conference on Speech Communication 2025

♻ ☆ Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions

Aditya Ashvin, Rimita Lahiri, Aditya Kommineni, Somer Bishop, Catherine Lord, Sudarsana Reddy Kadiri, Shrikanth Narayanan

comment: Accepted at Workshop on Child Computer Interaction (WOCCI 2025)

♻ ☆ Marco-Voice Technical Report

Fengping Tian, Chenyang Lyu, Xuanfan Ni, Haoqin Sun, Qingjuan Li, Zhiqiang Qian, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo, Kaifu Zhang

comment: Technical Report. Our code and dataset are publicly available at https://github.com/AIDC-AI/Marco-Voice and https://huggingface.co/datasets/AIDC-AI/CSEMOTIONS respectively

Computer Vision and Pattern Recognition 160

☆ Quantum Visual Fields with Neural Amplitude Encoding

Shuteng Wang, Christian Theobalt, Vladislav Golyanik

Quantum Implicit Neural Representations (QINRs) include components for learning and execution on gate-based quantum computers. While QINRs recently emerged as a promising new paradigm, many challenges concerning their architecture and ansatz design, the utility of quantum-mechanical properties, training efficiency and the interplay with classical modules remain. This paper advances the field by introducing a new type of QINR for 2D image and 3D geometric field learning, which we collectively refer to as Quantum Visual Field (QVF). QVF encodes classical data into quantum statevectors using neural amplitude encoding grounded in a learnable energy manifold, ensuring meaningful Hilbert space embeddings. Our ansatz follows a fully entangled design of learnable parametrised quantum circuits, with quantum (unitary) operations performed in the real Hilbert space, resulting in numerically stable training with fast convergence. QVF does not rely on classical post-processing -- in contrast to the previous QINR learning approach -- and directly employs projective measurement to extract learned signals encoded in the ansatz. Experiments on a quantum hardware simulator demonstrate that QVF outperforms the existing quantum approach and widely used classical foundational baselines in terms of visual representation accuracy across various metrics and model characteristics, such as learning of high-frequency details. We also show applications of QVF in 2D and 3D field completion and 3D shape interpolation, highlighting its practical potential.

comment: 17 pages, 15 figures and four tables; project page: https://4dqv.mpi-inf.mpg.de/QVF/

☆ Puppeteer: Rig and Animate Your 3D Models

Chaoyue Song, Xiu Li, Fan Yang, Zhongcong Xu, Jiacheng Wei, Fayao Liu, Jiashi Feng, Guosheng Lin, Jianfeng Zhang

Modern interactive applications increasingly demand dynamic 3D content, yet the transformation of static 3D models into animated assets constitutes a significant bottleneck in content creation pipelines. While recent advances in generative AI have revolutionized static 3D model creation, rigging and animation continue to depend heavily on expert intervention. We present Puppeteer, a comprehensive framework that addresses both automatic rigging and animation for diverse 3D objects. Our system first predicts plausible skeletal structures via an auto-regressive transformer that introduces a joint-based tokenization strategy for compact representation and a hierarchical ordering methodology with stochastic perturbation that enhances bidirectional learning capabilities. It then infers skinning weights via an attention-based architecture incorporating topology-aware joint attention that explicitly encodes inter-joint relationships based on skeletal graph distances. Finally, we complement these rigging advances with a differentiable optimization-based animation pipeline that generates stable, high-fidelity animations while being computationally more efficient than existing approaches. Extensive evaluations across multiple benchmarks demonstrate that our method significantly outperforms state-of-the-art techniques in both skeletal prediction accuracy and skinning quality. The system robustly processes diverse 3D content, ranging from professionally designed game assets to AI-generated shapes, producing temporally coherent animations that eliminate the jittering issues common in existing methods.

comment: Project page: https://chaoyuesong.github.io/Puppeteer/

☆ Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning

Mengyuan Liu, Xinshun Wang, Zhongbin Fang, Deheng Ye, Xia Li, Tao Tang, Songtao Wu, Xiangtai Li, Ming-Hsuan Yang

This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training, which limits their practicality and scalability. To overcome these challenges, we propose a new setting to train a unified cross-domain model through a single process, eliminating the need for domain-specific components and multi-stage training. We first introduce Pose-in-Context (PiC), which leverages in-context learning to create a pose-centric cross-domain model. While PiC generalizes across multiple pose-based tasks and datasets, it encounters difficulties with modality diversity, prompting strategy, and contextual dependency handling. We thus propose Human-in-Context (HiC), an extension of PiC that broadens generalization across modalities, tasks, and datasets. HiC combines pose and mesh representations within a unified framework, expands task coverage, and incorporates larger-scale datasets. Additionally, HiC introduces a max-min similarity prompt sampling strategy to enhance generalization across diverse domains and a network architecture with dual-branch context injection for improved handling of contextual dependencies. Extensive experimental results show that HiC performs better than PiC in terms of generalization, data scale, and performance across a wide range of domains. These results demonstrate the potential of HiC for building a unified cross-domain 3D human motion model with improved flexibility and scalability. The source codes and models are available at https://github.com/BradleyWang0416/Human-in-Context.

☆ ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning

Jongseo Lee, Kyungho Bae, Kyle Min, Gyeong-Moon Park, Jinwoo Choi

In this work, we tackle the problem of video classincremental learning (VCIL). Many existing VCIL methods mitigate catastrophic forgetting by rehearsal training with a few temporally dense samples stored in episodic memory, which is memory-inefficient. Alternatively, some methods store temporally sparse samples, sacrificing essential temporal information and thereby resulting in inferior performance. To address this trade-off between memory-efficiency and performance, we propose EpiSodic and SEmaNTIc memory integrAtion for video class-incremental Learning (ESSENTIAL). ESSENTIAL consists of episodic memory for storing temporally sparse features and semantic memory for storing general knowledge represented by learnable prompts. We introduce a novel memory retrieval (MR) module that integrates episodic memory and semantic prompts through cross-attention, enabling the retrieval of temporally dense features from temporally sparse features. We rigorously validate ESSENTIAL on diverse datasets: UCF-101, HMDB51, and Something-Something-V2 from the TCD benchmark and UCF-101, ActivityNet, and Kinetics-400 from the vCLIMB benchmark. Remarkably, with significantly reduced memory, ESSENTIAL achieves favorable performance on the benchmarks.

comment: 2025 ICCV Highlight paper, 17 pages including supplementary material

☆ MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

Antoine Labatie, Michael Vaccaro, Nina Lardiere, Anatol Garioud, Nicolas Gonthier

Self-supervised learning holds great promise for remote sensing, but standard self-supervised methods must be adapted to the unique characteristics of Earth observation data. We take a step in this direction by conducting a comprehensive benchmark of fusion strategies and reconstruction target normalization schemes for multimodal, multitemporal, and multispectral Earth observation data. Based on our findings, we propose MAESTRO, a novel adaptation of the Masked Autoencoder, featuring optimized fusion strategies and a tailored target normalization scheme that introduces a spectral prior as a self-supervisory signal. Evaluated on four Earth observation datasets, MAESTRO sets a new state-of-the-art on tasks that strongly rely on multitemporal dynamics, while remaining highly competitive on tasks dominated by a single mono-temporal modality. Code to reproduce all our experiments is available at https://github.com/ignf/maestro.

☆ STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

Yushi Lan, Yihang Luo, Fangzhou Hong, Shangchen Zhou, Honghua Chen, Zhaoyang Lyu, Shuai Yang, Bo Dai, Chen Change Loy, Xingang Pan

We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global optimization or rely on simplistic memory mechanisms that scale poorly with sequence length. In contrast, STream3R introduces an streaming framework that processes image sequences efficiently using causal attention, inspired by advances in modern language modeling. By learning geometric priors from large-scale 3D datasets, STream3R generalizes well to diverse and challenging scenarios, including dynamic scenes where traditional methods often fail. Extensive experiments show that our method consistently outperforms prior work across both static and dynamic scene benchmarks. Moreover, STream3R is inherently compatible with LLM-style training infrastructure, enabling efficient large-scale pretraining and fine-tuning for various downstream 3D tasks. Our results underscore the potential of causal Transformer models for online 3D perception, paving the way for real-time 3D understanding in streaming environments. More details can be found in our project page: https://nirvanalan.github.io/projects/stream3r.

comment: TL;DR: Streaming 4D reconstruction using causal transformer. Project page: https://nirvanalan.github.io/projects/stream3r

☆ ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

Lingen Li, Guangzhi Wang, Zhaoyang Zhang, Yaowei Li, Xiaoyu Li, Qi Dou, Jinwei Gu, Tianfan Xue, Ying Shan

Traditional cartoon and anime production involves keyframing, inbetweening, and colorization stages, which require intensive manual effort. Despite recent advances in AI, existing methods often handle these stages separately, leading to error accumulation and artifacts. For instance, inbetweening approaches struggle with large motions, while colorization methods require dense per-frame sketches. To address this, we introduce ToonComposer, a generative model that unifies inbetweening and colorization into a single post-keyframing stage. ToonComposer employs a sparse sketch injection mechanism to provide precise control using keyframe sketches. Additionally, it uses a cartoon adaptation method with the spatial low-rank adapter to tailor a modern video foundation model to the cartoon domain while keeping its temporal prior intact. Requiring as few as a single sketch and a colored reference frame, ToonComposer excels with sparse inputs, while also supporting multiple sketches at any temporal location for more precise motion control. This dual capability reduces manual workload and improves flexibility, empowering artists in real-world scenarios. To evaluate our model, we further created PKBench, a benchmark featuring human-drawn sketches that simulate real-world use cases. Our evaluation demonstrates that ToonComposer outperforms existing methods in visual quality, motion consistency, and production efficiency, offering a superior and more flexible solution for AI-assisted cartoon production.

comment: Project Page: https://lg-li.github.io/project/tooncomposer

☆ Medico 2025: Visual Question Answering for Gastrointestinal Imaging

Sushant Gautam, Vajira Thambawita, Michael Riegler, Pål Halvorsen, Steven Hicks

The Medico 2025 challenge addresses Visual Question Answering (VQA) for Gastrointestinal (GI) imaging, organized as part of the MediaEval task series. The challenge focuses on developing Explainable Artificial Intelligence (XAI) models that answer clinically relevant questions based on GI endoscopy images while providing interpretable justifications aligned with medical reasoning. It introduces two subtasks: (1) answering diverse types of visual questions using the Kvasir-VQA-x1 dataset, and (2) generating multimodal explanations to support clinical decision-making. The Kvasir-VQA-x1 dataset, created from 6,500 images and 159,549 complex question-answer (QA) pairs, serves as the benchmark for the challenge. By combining quantitative performance metrics and expert-reviewed explainability assessments, this task aims to advance trustworthy Artificial Intelligence (AI) in medical image analysis. Instructions, data access, and an updated guide for participation are available in the official competition repository: https://github.com/simula/MediaEval-Medico-2025

☆ TexVerse: A Universe of 3D Objects with High-Resolution Textures

Yibo Zhang, Li Zhang, Rui Ma, Nan Cao

We introduce TexVerse, a large-scale 3D dataset featuring high-resolution textures. While recent advances in large-scale 3D datasets have enhanced high-resolution geometry generation, creating high-resolution textures end-to-end remains underexplored due to the lack of suitable datasets. TexVerse fills this gap with a curated collection of over 858K unique high-resolution 3D models sourced from Sketchfab, including more than 158K models with physically based rendering (PBR) materials. Each model encompasses all of its high-resolution variants, bringing the total to 1.6M 3D instances. TexVerse also includes specialized subsets: TexVerse-Skeleton, with 69K rigged models, and TexVerse-Animation, with 54K animated models, both preserving original skeleton and animation data uploaded by the user. We also provide detailed model annotations describing overall characteristics, structural components, and intricate features. TexVerse offers a high-quality data resource with wide-ranging potential applications in texture synthesis, PBR material development, animation, and various 3D vision and graphics tasks.

☆ Performance of GPT-5 in Brain Tumor MRI Reasoning

Mojtaba Safari, Shansong Wang, Mingzhe Hu, Zach Eidex, Qiang Li, Xiaofeng Yang

Accurate differentiation of brain tumor types on magnetic resonance imaging (MRI) is critical for guiding treatment planning in neuro-oncology. Recent advances in large language models (LLMs) have enabled visual question answering (VQA) approaches that integrate image interpretation with natural language reasoning. In this study, we evaluated GPT-4o, GPT-5-nano, GPT-5-mini, and GPT-5 on a curated brain tumor VQA benchmark derived from 3 Brain Tumor Segmentation (BraTS) datasets - glioblastoma (GLI), meningioma (MEN), and brain metastases (MET). Each case included multi-sequence MRI triplanar mosaics and structured clinical features transformed into standardized VQA items. Models were assessed in a zero-shot chain-of-thought setting for accuracy on both visual and reasoning tasks. Results showed that GPT-5-mini achieved the highest macro-average accuracy (44.19%), followed by GPT-5 (43.71%), GPT-4o (41.49%), and GPT-5-nano (35.85%). Performance varied by tumor subtype, with no single model dominating across all cohorts. These findings suggest that GPT-5 family models can achieve moderate accuracy in structured neuro-oncological VQA tasks, but not at a level acceptable for clinical use.

☆ Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

Harold Haodong Chen, Haojian Huang, Qifeng Chen, Harry Yang, Ser-Nam Lim

Recent advancements in video generation have enabled the creation of high-quality, visually compelling videos. However, generating videos that adhere to the laws of physics remains a critical challenge for applications requiring realism and accuracy. In this work, we propose PhysHPO, a novel framework for Hierarchical Cross-Modal Direct Preference Optimization, to tackle this challenge by enabling fine-grained preference alignment for physically plausible video generation. PhysHPO optimizes video alignment across four hierarchical granularities: a) Instance Level, aligning the overall video content with the input prompt; b) State Level, ensuring temporal consistency using boundary frames as anchors; c) Motion Level, modeling motion trajectories for realistic dynamics; and d) Semantic Level, maintaining logical consistency between narrative and visuals. Recognizing that real-world videos are the best reflections of physical phenomena, we further introduce an automated data selection pipeline to efficiently identify and utilize "good data" from existing large-scale text-video datasets, thereby eliminating the need for costly and time-intensive dataset construction. Extensive experiments on both physics-focused and general capability benchmarks demonstrate that PhysHPO significantly improves physical plausibility and overall video generation quality of advanced models. To the best of our knowledge, this is the first work to explore fine-grained preference alignment and data selection for video generation, paving the way for more realistic and human-preferred video generation paradigms.

comment: Project Page: https://haroldchen19.github.io/PhysHPO-Page/

☆ Generalizable Federated Learning using Client Adaptive Focal Modulation

Tajamul Ashraf, Iqra Altaf Gillani

Federated learning (FL) has proven essential for privacy-preserving, collaborative training across distributed clients. Our prior work, TransFed, introduced a robust transformer-based FL framework that leverages a learn-to-adapt hypernetwork to generate personalized focal modulation layers per client, outperforming traditional methods in non-IID and cross-domain settings. In this extended version, we propose AdaptFED, where we deepen the investigation of focal modulation in generalizable FL by incorporating: (1) a refined adaptation strategy that integrates task-aware client embeddings to personalize modulation dynamics further, (2) enhanced theoretical bounds on adaptation performance, and (3) broader empirical validation across additional modalities, including time-series and multilingual data. We also introduce an efficient variant of TransFed that reduces server-client communication overhead via low-rank hypernetwork conditioning, enabling scalable deployment in resource-constrained environments. Extensive experiments on eight diverse datasets reaffirm the superiority of our method over state-of-the-art baselines, particularly in source-free and cross-task federated setups. Our findings not only extend the capabilities of focal modulation in FL but also pave the way for more adaptive, scalable, and generalizable transformer-based federated systems. The code is available at http://github.com/Tajamul21/TransFed

comment: WACV 2024 Extended Paper

☆ Self-Supervised Stereo Matching with Multi-Baseline Contrastive Learning

Peng Xu, Zhiyu Xiang, Jingyun Fu, Tianyu Pu, Kai Wang, Chaojie Ji, Tingming Bai, Eryun Liu

Current self-supervised stereo matching relies on the photometric consistency assumption, which breaks down in occluded regions due to ill-posed correspondences. To address this issue, we propose BaCon-Stereo, a simple yet effective contrastive learning framework for self-supervised stereo network training in both non-occluded and occluded regions. We adopt a teacher-student paradigm with multi-baseline inputs, in which the stereo pairs fed into the teacher and student share the same reference view but differ in target views. Geometrically, regions occluded in the student's target view are often visible in the teacher's, making it easier for the teacher to predict in these regions. The teacher's prediction is rescaled to match the student's baseline and then used to supervise the student. We also introduce an occlusion-aware attention map to better guide the student in learning occlusion completion. To support training, we synthesize a multi-baseline dataset BaCon-20k. Extensive experiments demonstrate that BaCon-Stereo improves prediction in both occluded and non-occluded regions, achieves strong generalization and robustness, and outperforms state-of-the-art self-supervised methods on both KITTI 2015 and 2012 benchmarks. Our code and dataset will be released upon paper acceptance.

☆ UI-Venus Technical Report: Building High-performance UI Agents with RFT

We present UI-Venus, a native UI agent that takes only screenshots as input based on a multimodal large language model. UI-Venus achieves SOTA performance on both UI grounding and navigation tasks using only several hundred thousand high-quality training samples through reinforcement finetune (RFT) based on Qwen2.5-VL. Specifically, the 7B and 72B variants of UI-Venus obtain 94.1% / 50.8% and 95.3% / 61.9% on the standard grounding benchmarks, i.e., Screenspot-V2 / Pro, surpassing the previous SOTA baselines including open-source GTA1 and closed-source UI-TARS-1.5.To show UI-Venus's summary and planing ability, we also evaluate it on the AndroidWorld, an online UI navigation arena, on which our 7B and 72B variants achieve 49.1% and 65.9% success rate, also beating existing models.To achieve this, we introduce carefully designed reward functions for both UI grounding and navigation tasks and corresponding efficient data cleaning strategies.To further boost navigation performance, we propose Self-Evolving Trajectory History Alignment \& Sparse Action Enhancement that refine historical reasoning traces and balances the distribution of sparse but critical actions, leading to more coherent planning and better generalization in complex UI tasks. Our contributions include the publish of SOTA open-source UI agents, comprehensive data cleaning protocols and a novel self-evolving framework for improving navigation performance, which encourage further research and development in the community. Code is available at https://github.com/antgroup/UI-Venus.

☆ Mobile-Friendly Deep Learning for Plant Disease Detection: A Lightweight CNN Benchmark Across 101 Classes of 33 Crops

Anand Kumar, Harminder Pal Monga, Tapasi Brahma, Satyam Kalra, Navas Sherif

Plant diseases are a major threat to food security globally. It is important to develop early detection systems which can accurately detect. The advancement in computer vision techniques has the potential to solve this challenge. We have developed a mobile-friendly solution which can accurately classify 101 plant diseases across 33 crops. We built a comprehensive dataset by combining different datasets, Plant Doc, PlantVillage, and PlantWild, all of which are for the same purpose. We evaluated performance across several lightweight architectures - MobileNetV2, MobileNetV3, MobileNetV3-Large, and EfficientNet-B0, B1 - specifically chosen for their efficiency on resource-constrained devices. The results were promising, with EfficientNet-B1 delivering our best performance at 94.7% classification accuracy. This architecture struck an optimal balance between accuracy and computational efficiency, making it well-suited for real-world deployment on mobile devices.

comment: 15 pages, 5 figures, 2 tables

☆ Object Fidelity Diffusion for Remote Sensing Image Generation

Ziqi Ye, Shuran Ma, Jie Yang, Xiaoyi Yang, Ziyang Gong, Xue Yang, Haipeng Wang

High-precision controllable remote sensing image generation is both meaningful and challenging. Existing diffusion models often produce low-fidelity images due to their inability to adequately capture morphological details, which may affect the robustness and reliability of object detection models. To enhance the accuracy and fidelity of generated objects in remote sensing, this paper proposes Object Fidelity Diffusion (OF-Diff), which effectively improves the fidelity of generated objects. Specifically, we are the first to extract the prior shapes of objects based on the layout for diffusion models in remote sensing. Then, we introduce a dual-branch diffusion model with diffusion consistency loss, which can generate high-fidelity remote sensing images without providing real images during the sampling phase. Furthermore, we introduce DDPO to fine-tune the diffusion process, making the generated remote sensing images more diverse and semantically consistent. Comprehensive experiments demonstrate that OF-Diff outperforms state-of-the-art methods in the remote sensing across key quality metrics. Notably, the performance of several polymorphic and small object classes shows significant improvement. For instance, the mAP increases by 8.3%, 7.7%, and 4.0% for airplanes, ships, and vehicles, respectively.

☆ When Experts Disagree: Characterizing Annotator Variability for Vessel Segmentation in DSA Images

M. Geshvadi, G. So, D. D. Chlorogiannis, C. Galvin, E. Torio, A. Azimi, Y. Tachie-Baffour, N. Haouchine, A. Golby, M. Vangel, W. M. Wells, Y. Epelboym, R. Du, F. Durupinar, S. Frisken

We analyze the variability among segmentations of cranial blood vessels in 2D DSA performed by multiple annotators in order to characterize and quantify segmentation uncertainty. We use this analysis to quantify segmentation uncertainty and discuss ways it can be used to guide additional annotations and to develop uncertainty-aware automatic segmentation methods.

☆ VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation

De-Xing Huang, Xiao-Hu Zhou, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Shuang-Yi Wang, Tian-Yu Xiang, Rui-Ze Ma, Nu-Fang Xiao, Zeng-Guang Hou

Accurate vessel segmentation in X-ray angiograms is crucial for numerous clinical applications. However, the scarcity of annotated data presents a significant challenge, which has driven the adoption of self-supervised learning (SSL) methods such as masked image modeling (MIM) to leverage large-scale unlabeled data for learning transferable representations. Unfortunately, conventional MIM often fails to capture vascular anatomy because of the severe class imbalance between vessel and background pixels, leading to weak vascular representations. To address this, we introduce Vascular anatomy-aware Masked Image Modeling (VasoMIM), a novel MIM framework tailored for X-ray angiograms that explicitly integrates anatomical knowledge into the pre-training process. Specifically, it comprises two complementary components: anatomy-guided masking strategy and anatomical consistency loss. The former preferentially masks vessel-containing patches to focus the model on reconstructing vessel-relevant regions. The latter enforces consistency in vascular semantics between the original and reconstructed images, thereby improving the discriminability of vascular representations. Empirically, VasoMIM achieves state-of-the-art performance across three datasets. These findings highlight its potential to facilitate X-ray angiogram analysis.

comment: 14 pages, 11 figures

☆ Cooperative Face Liveness Detection from Optical Flow

Artem Sokolov, Mikhail Nikitin, Anton Konushin

In this work, we proposed a novel cooperative video-based face liveness detection method based on a new user interaction scenario where participants are instructed to slowly move their frontal-oriented face closer to the camera. This controlled approaching face protocol, combined with optical flow analysis, represents the core innovation of our approach. By designing a system where users follow this specific movement pattern, we enable robust extraction of facial volume information through neural optical flow estimation, significantly improving discrimination between genuine faces and various presentation attacks (including printed photos, screen displays, masks, and video replays). Our method processes both the predicted optical flows and RGB frames through a neural classifier, effectively leveraging spatial-temporal features for more reliable liveness detection compared to passive methods.

☆ Insights from the Algonauts 2025 Winners

Paul S. Scotti, Mihir Tripathy

The Algonauts 2025 Challenge just wrapped up a few weeks ago. It is a biennial challenge in computational neuroscience in which teams attempt to build models that predict human brain activity from carefully curated stimuli. Previous editions (2019, 2021, 2023) focused on still images and short videos; the 2025 edition, which concluded last month (late July), pushed the field further by using long, multimodal movies. Teams were tasked with predicting fMRI responses across 1,000 whole-brain parcels across four participants in the dataset who were scanned while watching nearly 80 hours of naturalistic movie stimuli. These recordings came from the CNeuroMod project and included 65 hours of training data, about 55 hours of Friends (seasons 1-6) plus four feature films (The Bourne Supremacy, Hidden Figures, Life, and The Wolf of Wall Street). The remaining data were used for validation: Season 7 of Friends for in-distribution tests, and the final winners for the Challenge were those who could best predict brain activity for six films in their held-out out-of-distribution (OOD) set. The winners were just announced and the top team reports are now publicly available. As members of the MedARC team which placed 4th in the competition, we reflect on the approaches that worked, what they reveal about the current state of brain encoding, and what might come next.

comment: Perspective piece on Algonauts 2025 Challenge conclusion

☆ Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior

Zhenning Shi, Zizheng Yan, Yuhang Yu, Clara Xue, Jingyu Zhuang, Qi Zhang, Jinwei Chen, Tao Li, Qingnan Fan

Reference-based Image Super-Resolution (RefSR) aims to restore a low-resolution (LR) image by utilizing the semantic and texture information from an additional reference high-resolution (reference HR) image. Existing diffusion-based RefSR methods are typically built upon ControlNet, which struggles to effectively align the information between the LR image and the reference HR image. Moreover, current RefSR datasets suffer from limited resolution and poor image quality, resulting in the reference images lacking sufficient fine-grained details to support high-quality restoration. To overcome the limitations above, we propose TriFlowSR, a novel framework that explicitly achieves pattern matching between the LR image and the reference HR image. Meanwhile, we introduce Landmark-4K, the first RefSR dataset for Ultra-High-Definition (UHD) landmark scenarios. Considering the UHD scenarios with real-world degradation, in TriFlowSR, we design a Reference Matching Strategy to effectively match the LR image with the reference HR image. Experimental results show that our approach can better utilize the semantic and texture information of the reference HR image compared to previous methods. To the best of our knowledge, we propose the first diffusion-based RefSR pipeline for ultra-high definition landmark scenarios under real-world degradation. Our code and model will be available at https://github.com/nkicsl/TriFlowSR.

☆ Video-BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation

Youping Gu, Xiaolong Li, Yuhao Hu, Bohan Zhuang

Diffusion transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequences create significant inference bottlenecks. While both step distillation and sparse attention mechanisms have shown promise as independent acceleration strategies, effectively combining these approaches presents critical challenges -- training-free integration yields suboptimal results, while separately training sparse attention after step distillation requires prohibitively expensive high-quality video data. To overcome these limitations, we propose BLADE, an innovative data-free joint training framework that introduces: (1) an Adaptive Block-Sparse Attention (ASA) mechanism for dynamically generating content-aware sparsity masks to focus computation on salient spatiotemporal features, and (2) a sparsity-aware step distillation paradigm built upon Trajectory Distribution Matching (TDM) that directly incorporates sparsity into the distillation process rather than treating it as a separate compression step, with fast convergence. We validate BLADE on text-to-video models like CogVideoX-5B and Wan2.1-1.3B. Our framework demonstrates remarkable efficiency gains across different scales. On Wan2.1-1.3B, BLADE achieves a 14.10x end-to-end inference acceleration over a 50-step baseline. Moreover, on models such as CogVideoX-5B with short video sequence lengths, our framework delivers a robust 8.89x speedup. Crucially, the acceleration is accompanied by a consistent quality improvement. On the VBench-2.0 benchmark, BLADE boosts the score of CogVideoX-5B to 0.569 (from 0.534) and Wan2.1-1.3B to 0.570 (from 0.563), results that are further corroborated by superior ratings in human evaluations. Our code and model weights are publicly available at: http://ziplab.co/BLADE-Homepage/.

comment: Tech report

☆ AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences

Jieyu Li, Xin Zhang, Joey Tianyi Zhou

Recent advances in AI-generated content have fueled the rise of highly realistic synthetic videos, posing severe risks to societal trust and digital integrity. Existing benchmarks for video authenticity detection typically suffer from limited realism, insufficient scale, and inadequate complexity, failing to effectively evaluate modern vision-language models against sophisticated forgeries. To address this critical gap, we introduce AEGIS, a novel large-scale benchmark explicitly targeting the detection of hyper-realistic and semantically nuanced AI-generated videos. AEGIS comprises over 10,000 rigorously curated real and synthetic videos generated by diverse, state-of-the-art generative models, including Stable Video Diffusion, CogVideoX-5B, KLing, and Sora, encompassing open-source and proprietary architectures. In particular, AEGIS features specially constructed challenging subsets enhanced with robustness evaluation. Furthermore, we provide multimodal annotations spanning Semantic-Authenticity Descriptions, Motion Features, and Low-level Visual Features, facilitating authenticity detection and supporting downstream tasks such as multimodal fusion and forgery localization. Extensive experiments using advanced vision-language models demonstrate limited detection capabilities on the most challenging subsets of AEGIS, highlighting the dataset's unique complexity and realism beyond the current generalization capabilities of existing models. In essence, AEGIS establishes an indispensable evaluation benchmark, fundamentally advancing research toward developing genuinely robust, reliable, broadly generalizable video authenticity detection methodologies capable of addressing real-world forgery threats. Our dataset is available on https://huggingface.co/datasets/Clarifiedfish/AEGIS.

comment: Proceedings of the 33rd ACM International Conference on Multimedia

☆ From Diagnosis to Improvement: Probing Spatio-Physical Reasoning in Vision Language Models

Tiancheng Han, Yunfei Gao, Yong Li, Wuzhou Yu, Qiaosheng Zhang, Wenqi Shao

Spatio-physical reasoning, a foundation capability for understanding the real physics world, is a critical step towards building robust world models. While recent vision language models (VLMs) have shown remarkable progress in specialized domains like multimodal mathematics and pure spatial understanding, their capability for spatio-physical reasoning remains largely unexplored. This paper provides a comprehensive diagnostic analysis of mainstream VLMs, revealing that current models perform inadequately on this crucial task. Further detailed analysis shows that this underperformance is largely attributable to biases caused by human-like prior and a lack of deep reasoning. To address these challenges, we apply supervised fine-tuning followed by rule-based reinforcement learning to Qwen2.5-VL-7B, resulting in significant improvements in spatio-physical reasoning capabilities and surpassing leading proprietary models. Nevertheless, despite this success, the model's generalization to new physics scenarios remains limited -- underscoring the pressing need for new approaches in spatio-physical reasoning.

comment: 9 pages, 6 figures

☆ Agentic Design Review System

Sayan Nag, K J Joseph, Koustava Goswami, Vlad I Morariu, Balaji Vasan Srinivasan

Evaluating graphic designs involves assessing it from multiple facets like alignment, composition, aesthetics and color choices. Evaluating designs in a holistic way involves aggregating feedback from individual expert reviewers. Towards this, we propose an Agentic Design Review System (AgenticDRS), where multiple agents collaboratively analyze a design, orchestrated by a meta-agent. A novel in-context exemplar selection approach based on graph matching and a unique prompt expansion method plays central role towards making each agent design aware. Towards evaluating this framework, we propose DRS-BENCH benchmark. Thorough experimental evaluation against state-of-the-art baselines adapted to the problem setup, backed-up with critical ablation experiments brings out the efficacy of Agentic-DRS in evaluating graphic designs and generating actionable feedback. We hope that this work will attract attention to this pragmatic, yet under-explored research direction.

☆ An Efficient Model-Driven Groupwise Approach for Atlas Construction

Ziwei Zou, Bei Zou, Xiaoyan Kui, Wenqi Lu, Haoran Dou, Arezoo Zakeri, Timothy Cootes, Alejandro F Frangi, Jinming Duan

Atlas construction is fundamental to medical image analysis, offering a standardized spatial reference for tasks such as population-level anatomical modeling. While data-driven registration methods have recently shown promise in pairwise settings, their reliance on large training datasets, limited generalizability, and lack of true inference phases in groupwise contexts hinder their practical use. In contrast, model-driven methods offer training-free, theoretically grounded, and data-efficient alternatives, though they often face scalability and optimization challenges when applied to large 3D datasets. In this work, we introduce DARC (Diffeomorphic Atlas Registration via Coordinate descent), a novel model-driven groupwise registration framework for atlas construction. DARC supports a broad range of image dissimilarity metrics and efficiently handles arbitrary numbers of 3D images without incurring GPU memory issues. Through a coordinate descent strategy and a centrality-enforcing activation function, DARC produces unbiased, diffeomorphic atlases with high anatomical fidelity. Beyond atlas construction, we demonstrate two key applications: (1) One-shot segmentation, where labels annotated only on the atlas are propagated to subjects via inverse deformations, outperforming state-of-the-art few-shot methods; and (2) shape synthesis, where new anatomical variants are generated by warping the atlas mesh using synthesized diffeomorphic deformation fields. Overall, DARC offers a flexible, generalizable, and resource-efficient framework for atlas construction and applications.

☆ Forgery Guided Learning Strategy with Dual Perception Network for Deepfake Cross-domain Detection

Lixin Jia, Zhiqing Guo, Gaobo Yang, Liejun Wang, Keqin Li

The emergence of deepfake technology has introduced a range of societal problems, garnering considerable attention. Current deepfake detection methods perform well on specific datasets, but exhibit poor performance when applied to datasets with unknown forgery techniques. Moreover, as the gap between emerging and traditional forgery techniques continues to widen, cross-domain detection methods that rely on common forgery traces are becoming increasingly ineffective. This situation highlights the urgency of developing deepfake detection technology with strong generalization to cope with fast iterative forgery techniques. To address these challenges, we propose a Forgery Guided Learning (FGL) strategy designed to enable detection networks to continuously adapt to unknown forgery techniques. Specifically, the FGL strategy captures the differential information between known and unknown forgery techniques, allowing the model to dynamically adjust its learning process in real time. To further improve the ability to perceive forgery traces, we design a Dual Perception Network (DPNet) that captures both differences and relationships among forgery traces. In the frequency stream, the network dynamically perceives and extracts discriminative features across various forgery techniques, establishing essential detection cues. These features are then integrated with spatial features and projected into the embedding space. In addition, graph convolution is employed to perceive relationships across the entire feature space, facilitating a more comprehensive understanding of forgery trace correlations. Extensive experiments show that our approach generalizes well across different scenarios and effectively handles unknown forgery challenges, providing robust support for deepfake detection. Our code is available on https://github.com/vpsg-research/FGL.

☆ Axis-level Symmetry Detection with Group-Equivariant Representation

Wongyun Yu, Ahyun Seo, Minsu Cho

Symmetry is a fundamental concept that has been extensively studied, yet detecting it in complex scenes remains a significant challenge in computer vision. Recent heatmap-based approaches can localize potential regions of symmetry axes but often lack precision in identifying individual axes. In this work, we propose a novel framework for axis-level detection of the two most common symmetry types-reflection and rotation-by representing them as explicit geometric primitives, i.e. lines and points. Our method employs a dual-branch architecture that is equivariant to the dihedral group, with each branch specialized to exploit the structure of dihedral group-equivariant features for its respective symmetry type. For reflection symmetry, we introduce orientational anchors, aligned with group components, to enable orientation-specific detection, and a reflectional matching that measures similarity between patterns and their mirrored counterparts across candidate axes. For rotational symmetry, we propose a rotational matching that compares patterns at fixed angular intervals to identify rotational centers. Extensive experiments demonstrate that our method achieves state-of-the-art performance, outperforming existing approaches.

comment: Accepted to ICCV 2025

☆ Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025

Matej Vitek, Darian Tomašević, Abhijit Das, Sabari Nathan, Gökhan Özbulak, Gözde Ayşe Tataroğlu Özbulak, Jean-Paul Calbimonte, André Anjos, Hariohm Hemant Bhatt, Dhruv Dhirendra Premani, Jay Chaudhari, Caiyong Wang, Jian Jiang, Chi Zhang, Qi Zhang, Iyyakutti Iyappan Ganapathi, Syed Sadaf Ali, Divya Velayudan, Maregu Assefa, Naoufel Werghi, Zachary A. Daniels, Leeon John, Ritesh Vyas, Jalil Nourmohammadi Khiarak, Taher Akbari Saeed, Mahsa Nasehi, Ali Kianfar, Mobina Pashazadeh Panahi, Geetanjali Sharma, Pushp Raj Panth, Raghavendra Ramachandra, Aditya Nigam, Umapada Pal, Peter Peer, Vitomir Štruc

This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models trained using synthetically generated ocular images. The goal of the competition was to evaluate how well models trained on synthetic data perform in comparison to those trained on real-world datasets. The competition featured two tracks: $(i)$ one relying solely on synthetic data for model development, and $(ii)$ one combining/mixing synthetic with (a limited amount of) real-world data. A total of nine research groups submitted diverse segmentation models, employing a variety of architectural designs, including transformer-based solutions, lightweight models, and segmentation networks guided by generative frameworks. Experiments were conducted across three evaluation datasets containing both synthetic and real-world images, collected under diverse conditions. Results show that models trained entirely on synthetic data can achieve competitive performance, particularly when dedicated training strategies are employed, as evidenced by the top performing models that achieved $F_1$ scores of over $0.8$ in the synthetic data track. Moreover, performance gains in the mixed track were often driven more by methodological choices rather than by the inclusion of real data, highlighting the promise of synthetic data for privacy-aware biometric development. The code and data for the competition is available at: https://github.com/dariant/SSBC_2025.

comment: IEEE International Joint Conference on Biometrics (IJCB) 2025, 13 pages

☆ Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction

Luyao Tang, Kunze Huang, Chaoqi Chen, Yuxuan Yuan, Chenxin Li, Xiaotong Tu, Xinghao Ding, Yue Huang

Human perceptual systems excel at inducing and recognizing objects across both known and novel categories, a capability far beyond current machine learning frameworks. While generalized category discovery (GCD) aims to bridge this gap, existing methods predominantly focus on optimizing objective functions. We present an orthogonal solution, inspired by the human cognitive process for novel object understanding: decomposing objects into visual primitives and establishing cross-knowledge comparisons. We propose ConGCD, which establishes primitive-oriented representations through high-level semantic reconstruction, binding intra-class shared attributes via deconstruction. Mirroring human preference diversity in visual processing, where distinct individuals leverage dominant or contextual cues, we implement dominant and contextual consensus units to capture class-discriminative patterns and inherent distributional invariants, respectively. A consensus scheduler dynamically optimizes activation pathways, with final predictions emerging through multiplex consensus integration. Extensive evaluations across coarse- and fine-grained benchmarks demonstrate ConGCD's effectiveness as a consensus-aware paradigm. Code is available at github.com/lytang63/ConGCD.

comment: Accepted by ICCV 2025 as *** Highlight ***!

☆ EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering

Yanjun Li, Yuqian Fu, Tianwen Qian, Qi'ao Xu, Silong Dai, Danda Pani Paudel, Luc Van Gool, Xiaoling Wang

Recent advances in Multimodal Large Language Models (MLLMs) have significantly pushed the frontier of egocentric video question answering (EgocentricQA). However, existing benchmarks and studies are mainly limited to common daily activities such as cooking and cleaning. In contrast, real-world deployment inevitably encounters domain shifts, where target domains differ substantially in both visual style and semantic content. To bridge this gap, we introduce \textbf{EgoCross}, a comprehensive benchmark designed to evaluate the cross-domain generalization of MLLMs in EgocentricQA. EgoCross covers four diverse and challenging domains, including surgery, industry, extreme sports, and animal perspective, representing realistic and high-impact application scenarios. It comprises approximately 1,000 QA pairs across 798 video clips, spanning four key QA tasks: prediction, recognition, localization, and counting. Each QA pair provides both OpenQA and CloseQA formats to support fine-grained evaluation. Extensive experiments show that most existing MLLMs, whether general-purpose or egocentric-specialized, struggle to generalize to domains beyond daily life, highlighting the limitations of current models. Furthermore, we conduct several pilot studies, \eg, fine-tuning and reinforcement learning, to explore potential improvements. We hope EgoCross and our accompanying analysis will serve as a foundation for advancing domain-adaptive, robust egocentric video understanding. Data and codes will be released at: \href{https://github.com/MyUniverse0726/EgoCross}{https://github.com/MyUniverse0726/EgoCross.}

☆ Exploiting Discriminative Codebook Prior for Autoregressive Image Generation

Longxiang Tang, Ruihang Chu, Xiang Wang, Yujin Han, Pingyu Wu, Chunming He, Yingya Zhang, Shiwei Zhang, Jiaya Jia

Advanced discrete token-based autoregressive image generation systems first tokenize images into sequences of token indices with a codebook, and then model these sequences in an autoregressive paradigm. While autoregressive generative models are trained only on index values, the prior encoded in the codebook, which contains rich token similarity information, is not exploited. Recent studies have attempted to incorporate this prior by performing naive k-means clustering on the tokens, helping to facilitate the training of generative models with a reduced codebook. However, we reveal that k-means clustering performs poorly in the codebook feature space due to inherent issues, including token space disparity and centroid distance inaccuracy. In this work, we propose the Discriminative Codebook Prior Extractor (DCPE) as an alternative to k-means clustering for more effectively mining and utilizing the token similarity information embedded in the codebook. DCPE replaces the commonly used centroid-based distance, which is found to be unsuitable and inaccurate for the token feature space, with a more reasonable instance-based distance. Using an agglomerative merging technique, it further addresses the token space disparity issue by avoiding splitting high-density regions and aggregating low-density ones. Extensive experiments demonstrate that DCPE is plug-and-play and integrates seamlessly with existing codebook prior-based paradigms. With the discriminative prior extracted, DCPE accelerates the training of autoregressive models by 42% on LlamaGen-B and improves final FID and IS performance.

comment: Submitted to TPAMI

☆ Revisiting Cross-View Localization from Image Matching

Panwang Xia, Qiong Wu, Lei Yu, Yi Liu, Mingtao Xiong, Lei Liang, Yongjun Zhang, Yi Wan

Cross-view localization aims to estimate the 3 degrees of freedom pose of a ground-view image by registering it to aerial or satellite imagery. It is essential in GNSS-denied environments such as urban canyons and disaster zones. Existing methods either regress poses directly or align features in a shared bird's-eye view (BEV) space, both built upon accurate spatial correspondences between perspectives. However, these methods fail to establish strict cross-view correspondences, yielding only coarse or geometrically inconsistent matches. Consequently, fine-grained image matching between ground and aerial views remains an unsolved problem, which in turn constrains the interpretability of localization results. In this paper, we revisit cross-view localization from the perspective of cross-view image matching and propose a novel framework that improves both matching and localization. Specifically, we introduce a Surface Model to model visible regions for accurate BEV projection, and a SimRefiner module to refine the similarity matrix through local-global residual correction, eliminating the reliance on post-processing like RANSAC. To further support research in this area, we introduce CVFM, the first benchmark with 32,509 cross-view image pairs annotated with pixel-level correspondences. Extensive experiments demonstrate that our approach substantially improves both localization accuracy and image matching quality, setting new baselines under extreme viewpoint disparity.

☆ Lightweight CNNs for Embedded SAR Ship Target Detection and Classification

Fabian Kresse, Georgios Pilikos, Mario Azcueta, Nicolas Floury

Synthetic Aperture Radar (SAR) data enables large-scale surveillance of maritime vessels. However, near-real-time monitoring is currently constrained by the need to downlink all raw data, perform image focusing, and subsequently analyze it on the ground. On-board processing to generate higher-level products could reduce the data volume that needs to be downlinked, alleviating bandwidth constraints and minimizing latency. However, traditional image focusing and processing algorithms face challenges due to the satellite's limited memory, processing power, and computational resources. This work proposes and evaluates neural networks designed for real-time inference on unfocused SAR data acquired in Stripmap and Interferometric Wide (IW) modes captured with Sentinel-1. Our results demonstrate the feasibility of using one of our models for on-board processing and deployment on an FPGA. Additionally, by investigating a binary classification task between ships and windmills, we demonstrate that target classification is possible.

comment: Accepted at Big Data from Space 2025 (BiDS'25)

☆ NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

comment: Code: https://github.com/stepfun-ai/NextStep-1

☆ CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation

Joohyeon Lee, Jin-Seop Lee, Jee-Hyong Lee

Diffusion-based text-to-image generation models have demonstrated strong performance in terms of image quality and diversity. However, they still struggle to generate images that accurately reflect the number of objects specified in the input prompt. Several approaches have been proposed that rely on either external counting modules for iterative refinement or quantity representations derived from learned tokens or latent features. However, they still have limitations in accurately reflecting the specified number of objects and overlook an important structural characteristic--The number of object instances in the generated image is largely determined in the early timesteps of the denoising process. To correctly reflect the object quantity for image generation, the highly activated regions in the object cross-attention map at the early timesteps should match the input object quantity, while each region should be clearly separated. To address this issue, we propose \textit{CountCluster}, a method that guides the object cross-attention map to be clustered according to the specified object count in the input, without relying on any external tools or additional training. The proposed method partitions the object cross-attention map into $k$ clusters at inference time based on attention scores, defines an ideal distribution in which each cluster is spatially well-separated, and optimizes the latent to align with this target distribution. Our method achieves an average improvement of 18.5\%p in object count accuracy compared to existing methods, and demonstrates superior quantity control performance across a variety of prompts. Code will be released at: https://github.com/JoohyeonL22/CountCluster .

comment: Under review

☆ Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios

Zhanwen Liu, Yujing Sun, Yang Wang, Nan Yang, Shengbo Eben Li, Xiangmo Zhao

The dynamic range limitation of conventional RGB cameras reduces global contrast and causes loss of high-frequency details such as textures and edges in complex traffic environments (e.g., nighttime driving, tunnels), hindering discriminative feature extraction and degrading frame-based object detection. To address this, we integrate a bio-inspired event camera with an RGB camera to provide high dynamic range information and propose a motion cue fusion network (MCFNet), which achieves optimal spatiotemporal alignment and adaptive cross-modal feature fusion under challenging lighting. Specifically, an event correction module (ECM) temporally aligns asynchronous event streams with image frames via optical-flow-based warping, jointly optimized with the detection network to learn task-aware event representations. The event dynamic upsampling module (EDUM) enhances spatial resolution of event frames to match image structures, ensuring precise spatiotemporal alignment. The cross-modal mamba fusion module (CMM) uses adaptive feature fusion with a novel interlaced scanning mechanism, effectively integrating complementary information for robust detection. Experiments conducted on the DSEC-Det and PKU-DAVIS-SOD datasets demonstrate that MCFNet significantly outperforms existing methods in various poor lighting and fast moving traffic scenarios. Notably, on the DSEC-Det dataset, MCFNet achieves a remarkable improvement, surpassing the best existing methods by 7.4% in mAP50 and 1.7% in mAP metrics, respectively. The code is available at https://github.com/Charm11492/MCFNet.

☆ Novel View Synthesis using DDIM Inversion

Sehajdeep SIngh, A V Subramanyam

Synthesizing novel views from a single input image is a challenging task. It requires extrapolating the 3D structure of a scene while inferring details in occluded regions, and maintaining geometric consistency across viewpoints. Many existing methods must fine-tune large diffusion backbones using multiple views or train a diffusion model from scratch, which is extremely expensive. Additionally, they suffer from blurry reconstruction and poor generalization. This gap presents the opportunity to explore an explicit lightweight view translation framework that can directly utilize the high-fidelity generative capabilities of a pretrained diffusion model while reconstructing a scene from a novel view. Given the DDIM-inverted latent of a single input image, we employ a camera pose-conditioned translation U-Net, TUNet, to predict the inverted latent corresponding to the desired target view. However, the image sampled using the predicted latent may result in a blurry reconstruction. To this end, we propose a novel fusion strategy that exploits the inherent noise correlation structure observed in DDIM inversion. The proposed fusion strategy helps preserve the texture and fine-grained details. To synthesize the novel view, we use the fused latent as the initial condition for DDIM sampling, leveraging the generative prior of the pretrained diffusion model. Extensive experiments on MVImgNet demonstrate that our method outperforms existing methods.

☆ IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning

Mengyang Zhao, Teng Fu, Haiyang Yu, Ke Niu, Bin Li

Few-Shot Industrial Anomaly Detection (FS-IAD) has important applications in automating industrial quality inspection. Recently, some FS-IAD methods based on Large Vision-Language Models (LVLMs) have been proposed with some achievements through prompt learning or fine-tuning. However, existing LVLMs focus on general tasks but lack basic industrial knowledge and reasoning capabilities related to FS-IAD, making these methods far from specialized human quality inspectors. To address these challenges, we propose a unified framework, IADGPT, designed to perform FS-IAD in a human-like manner, while also handling associated localization and reasoning tasks, even for diverse and novel industrial products. To this end, we introduce a three-stage progressive training strategy inspired by humans. Specifically, the first two stages gradually guide IADGPT in acquiring fundamental industrial knowledge and discrepancy awareness. In the third stage, we design an in-context learning-based training paradigm, enabling IADGPT to leverage a few-shot image as the exemplars for improved generalization to novel products. In addition, we design a strategy that enables IADGPT to output image-level and pixel-level anomaly scores using the logits output and the attention map, respectively, in conjunction with the language output to accomplish anomaly reasoning. To support our training, we present a new dataset comprising 100K images across 400 diverse industrial product categories with extensive attribute-level textual annotations. Experiments indicate IADGPT achieves considerable performance gains in anomaly detection and demonstrates competitiveness in anomaly localization and reasoning. We will release our dataset in camera-ready.

☆ Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping

Busra Bulut, Maik Dannecker, Thomas Sanchez, Sara Neves Silva, Vladyslav Zalevskyi, Steven Jia, Jean-Baptiste Ledoux, Guillaume Auzias, François Rousseau, Jana Hutter, Daniel Rueckert, Meritxell Bach Cuadra

T2 mapping in fetal brain MRI has the potential to improve characterization of the developing brain, especially at mid-field (0.55T), where T2 decay is slower. However, this is challenging as fetal MRI acquisition relies on multiple motion-corrupted stacks of thick slices, requiring slice-to-volume reconstruction (SVR) to estimate a high-resolution (HR) 3D volume. Currently, T2 mapping involves repeated acquisitions of these stacks at each echo time (TE), leading to long scan times and high sensitivity to motion. We tackle this challenge with a method that jointly reconstructs data across TEs, addressing severe motion. Our approach combines implicit neural representations with a physics-informed regularization that models T2 decay, enabling information sharing across TEs while preserving anatomical and quantitative T2 fidelity. We demonstrate state-of-the-art performance on simulated fetal brain and in vivo adult datasets with fetal-like motion. We also present the first in vivo fetal T2 mapping results at 0.55T. Our study shows potential for reducing the number of stacks per TE in T2 mapping by leveraging anatomical redundancy.

☆ HyperTea: A Hypergraph-based Temporal Enhancement and Alignment Network for Moving Infrared Small Target Detection

Zhaoyuan Qi, Weihua Gao, Wenlong Niu, Jie Tang, Yun Li, Xiaodong Peng

In practical application scenarios, moving infrared small target detection (MIRSTD) remains highly challenging due to the target's small size, weak intensity, and complex motion pattern. Existing methods typically only model low-order correlations between feature nodes and perform feature extraction and enhancement within a single temporal scale. Although hypergraphs have been widely used for high-order correlation learning, they have received limited attention in MIRSTD. To explore the potential of hypergraphs and enhance multi-timescale feature representation, we propose HyperTea, which integrates global and local temporal perspectives to effectively model high-order spatiotemporal correlations of features. HyperTea consists of three modules: the global temporal enhancement module (GTEM) realizes global temporal context enhancement through semantic aggregation and propagation; the local temporal enhancement module (LTEM) is designed to capture local motion patterns between adjacent frames and then enhance local temporal context; additionally, we further develop a temporal alignment module (TAM) to address potential cross-scale feature misalignment. To our best knowledge, HyperTea is the first work to integrate convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hypergraph neural networks (HGNNs) for MIRSTD, significantly improving detection performance. Experiments on DAUB and IRDST demonstrate its state-of-the-art (SOTA) performance. Our source codes are available at https://github.com/Lurenjia-LRJ/HyperTea.

☆ Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation

Feiran Li, Qianqian Xu, Shilong Bao, Boyu Han, Zhiyong Yang, Qingming Huang

comment: This paper has been accpeted to ICCV 2025 DataCV Workshop

☆ AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models

Shixiong Xu, Chenghao Zhang, Lubin Fan, Yuan Zhou, Bin Fan, Shiming Xiang, Gaofeng Meng, Jieping Ye

Large visual language models (LVLMs) have demonstrated impressive performance in coarse-grained geo-localization at the country or city level, but they struggle with fine-grained street-level localization within urban areas. In this paper, we explore integrating city-wide address localization capabilities into LVLMs, facilitating flexible address-related question answering using street-view images. A key challenge is that the street-view visual question-and-answer (VQA) data provides only microscopic visual cues, leading to subpar performance in fine-tuned models. To tackle this issue, we incorporate perspective-invariant satellite images as macro cues and propose cross-view alignment tuning including a satellite-view and street-view image grafting mechanism, along with an automatic label generation mechanism. Then LVLM's global understanding of street distribution is enhanced through cross-view matching. Our proposed model, named AddressVLM, consists of two-stage training protocols: cross-view alignment tuning and address localization tuning. Furthermore, we have constructed two street-view VQA datasets based on image address localization datasets from Pittsburgh and San Francisco. Qualitative and quantitative evaluations demonstrate that AddressVLM outperforms counterpart LVLMs by over 9% and 12% in average address localization accuracy on these two datasets, respectively.

☆ Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking

Zhangyong Tang, Tianyang Xu, Xuefeng Zhu, Chunyang Cheng, Tao Zhou, Xiaojun Wu, Josef Kittler

Unifying multiple multi-modal visual object tracking (MMVOT) tasks draws increasing attention due to the complementary nature of different modalities in building robust tracking systems. Existing practices mix all data sensor types in a single training procedure, structuring a parallel paradigm from the data-centric perspective and aiming for a global optimum on the joint distribution of the involved tasks. However, the absence of a unified benchmark where all types of data coexist forces evaluations on separated benchmarks, causing \textit{inconsistency} between training and testing, thus leading to performance \textit{degradation}. To address these issues, this work advances in two aspects: \ding{182} A unified benchmark, coined as UniBench300, is introduced to bridge the inconsistency by incorporating multiple task data, reducing inference passes from three to one and cutting time consumption by 27\%. \ding{183} The unification process is reformulated in a serial format, progressively integrating new tasks. In this way, the performance degradation can be specified as knowledge forgetting of previous tasks, which naturally aligns with the philosophy of continual learning (CL), motivating further exploration of injecting CL into the unification process. Extensive experiments conducted on two baselines and four benchmarks demonstrate the significance of UniBench300 and the superiority of CL in supporting a stable unification process. Moreover, while conducting dedicated analyses, the performance degradation is found to be negatively correlated with network capacity. Additionally, modality discrepancies contribute to varying degradation levels across tasks (RGBT > RGBD > RGBE in MMVOT), offering valuable insights for future multi-modal vision research. Source codes and the proposed benchmark is available at \textit{https://github.com/Zhangyong-Tang/UniBench300}.

comment: ACMMM 2025

☆ Geospatial Diffusion for Land Cover Imperviousness Change Forecasting

Debvrat Varshney, Vibhas Vats, Bhartendu Pandey, Christa Brelsford, Philipe Dias

Land cover, both present and future, has a significant effect on several important Earth system processes. For example, impervious surfaces heat up and speed up surface water runoff and reduce groundwater infiltration, with concomitant effects on regional hydrology and flood risk. While regional Earth System models have increasing skill at forecasting hydrologic and atmospheric processes at high resolution in future climate scenarios, our ability to forecast land-use and land-cover change (LULC), a critical input to risk and consequences assessment for these scenarios, has lagged behind. In this paper, we propose a new paradigm exploiting Generative AI (GenAI) for land cover change forecasting by framing LULC forecasting as a data synthesis problem conditioned on historical and auxiliary data-sources. We discuss desirable properties of generative models that fundament our research premise, and demonstrate the feasibility of our methodology through experiments on imperviousness forecasting using historical data covering the entire conterminous United States. Specifically, we train a diffusion model for decadal forecasting of imperviousness and compare its performance to a baseline that assumes no change at all. Evaluation across 12 metropolitan areas for a year held-out during training indicate that for average resolutions $\geq 0.7\times0.7km^2$ our model yields MAE lower than such a baseline. This finding corroborates that such a generative model can capture spatiotemporal patterns from historical data that are significant for projecting future change. Finally, we discuss future research to incorporate auxiliary information on physical properties about the Earth, as well as supporting simulation of different scenarios by means of driver variables.

☆ SemPT: Semantic Prompt Tuning for Vision-Language Models

Xiao Shi, Yangjun Ou, Zhenzhong Chen

Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language Models (VLMs) pre-trained on large amounts of image-text pairs offer a promising solution. However, existing prompt tuning methods rely on sparse category labels or disparate LLM-generated descriptions, which fragment knowledge representation and hinder transferability. To address this limitation, we introduce Semantic Prompt Tuning (SemPT), a novel framework that tackles the generalization challenge by leveraging shared attribute-level knowledge across categories. Specifically, SemPT adopts a two-step prompting strategy to guide LLM in extracting shared visual attributes and generating attribute-level descriptions, capturing transferable semantic cues beyond labels while ensuring coherent structure. Then, visually guided weighting is applied to the embeddings of attribute-level descriptions to reduce noise from irrelevant attributes and enhance the text embeddings. Additionally, image embeddings are jointly aligned with both label and attribute-enhanced text embeddings, balancing discrimination for seen categories and transferability to unseen ones. Considering the availability of category exposure, our inference dynamically selects between standard label embeddings for seen categories and attribute-enhanced embeddings for unseen ones to ensure effective adaptation. Extensive experiments on 15 benchmark datasets demonstrate that SemPT achieves state-of-the-art performance across various settings, including base-to-novel generalization, cross-dataset transfer, cross-domain transfer, and few-shot learning.

☆ Lameness detection in dairy cows using pose estimation and bidirectional LSTMs

Helena Russello, Rik van der Tol, Eldert J. van Henten, Gert Kootstra

This study presents a lameness detection approach that combines pose estimation and Bidirectional Long-Short-Term Memory (BLSTM) neural networks. Combining pose-estimation and BLSTMs classifier offers the following advantages: markerless pose-estimation, elimination of manual feature engineering by learning temporal motion features from the keypoint trajectories, and working with short sequences and small training datasets. Motion sequences of nine keypoints (located on the cows' hooves, head and back) were extracted from videos of walking cows with the T-LEAP pose estimation model. The trajectories of the keypoints were then used as an input to a BLSTM classifier that was trained to perform binary lameness classification. Our method significantly outperformed an established method that relied on manually-designed locomotion features: our best architecture achieved a classification accuracy of 85%, against 80% accuracy for the feature-based approach. Furthermore, we showed that our BLSTM classifier could detect lameness with as little as one second of video data.

☆ Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

Ryan Ramos, Vladan Stojnić, Giorgos Kordopatis-Zilos, Yuta Nakashima, Giorgos Tolias, Noa Garcia

Prior work has analyzed the robustness of visual encoders to image transformations and corruptions, particularly in cases where such alterations are not seen during training. When this occurs, they introduce a form of distribution shift at test time, often leading to performance degradation. The primary focus has been on severe corruptions that, when applied aggressively, distort useful signals necessary for accurate semantic predictions. We take a different perspective by analyzing parameters of the image acquisition process and transformations that may be subtle or even imperceptible to the human eye. We find that such parameters are systematically encoded in the learned visual representations and can be easily recovered. More strikingly, their presence can have a profound impact, either positively or negatively, on semantic predictions. This effect depends on whether there is a strong correlation or anti-correlation between semantic labels and these acquisition-based or processing-based labels. Our code and data are available at: https://github.com/ryan-caesar-ramos/visual-encoder-traces

comment: 8 main pages, supplementary attached, ICCV 2025 highlight

☆ ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation

Hosam Elgendy, Ahmed Sharshar, Ahmed Aboeitta, Mohsen Guizani

Understanding environmental changes from aerial imagery is vital for climate resilience, urban planning, and ecosystem monitoring. Yet, current vision language models (VLMs) overlook causal signals from environmental sensors, rely on single-source captions prone to stylistic bias, and lack interactive scenario-based reasoning. We present ChatENV, the first interactive VLM that jointly reasons over satellite image pairs and real-world sensor data. Our framework: (i) creates a 177k-image dataset forming 152k temporal pairs across 62 land-use classes in 197 countries with rich sensor metadata (e.g., temperature, PM10, CO); (ii) annotates data using GPT- 4o and Gemini 2.0 for stylistic and semantic diversity; and (iii) fine-tunes Qwen-2.5-VL using efficient Low-Rank Adaptation (LoRA) adapters for chat purposes. ChatENV achieves strong performance in temporal and "what-if" reasoning (e.g., BERT-F1 0.903) and rivals or outperforms state-of-the-art temporal models, while supporting interactive scenario-based analysis. This positions ChatENV as a powerful tool for grounded, sensor-aware environmental monitoring.

comment: 11 pages, 5 figures, 7 tables

☆ Increasing the Utility of Synthetic Images through Chamfer Guidance

Nicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari Hemmat, Melissa Hall, Jakob Verbeek, Adriana Romero-Soriano, Michal Drozdzal

Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress in generation quality has come at the expense of generation diversity, limiting the utility of these models as a source of synthetic training data. Although guidance-based approaches have been introduced to improve the utility of generated data by focusing on quality or diversity, the (implicit or explicit) utility functions oftentimes disregard the potential distribution shift between synthetic and real data. In this work, we introduce Chamfer Guidance: a training-free guidance approach which leverages a handful of real exemplar images to characterize the quality and diversity of synthetic data. We show that by leveraging the proposed Chamfer Guidance, we can boost the diversity of the generations w.r.t. a dataset of real images while maintaining or improving the generation quality on ImageNet-1k and standard geo-diversity benchmarks. Our approach achieves state-of-the-art few-shot performance with as little as 2 exemplar real images, obtaining 96.4\% in terms of precision, and 86.4\% in terms of distributional coverage, which increase to 97.5\% and 92.7\%, respectively, when using 32 real images. We showcase the benefits of the Chamfer Guidance generation by training downstream image classifiers on synthetic data, achieving accuracy boost of up to 15\% for in-distribution over the baselines, and up to 16\% in out-of-distribution. Furthermore, our approach does not require using the unconditional model, and thus obtains a 31\% reduction in FLOPs w.r.t. classifier-free-guidance-based approaches at sampling time.

☆ FIND-Net -- Fourier-Integrated Network with Dictionary Kernels for Metal Artifact Reduction

Farid Tasharofi, Fuxin Fan, Melika Qahqaie, Mareike Thies, Andreas Maier

Metal artifacts, caused by high-density metallic implants in computed tomography (CT) imaging, severely degrade image quality, complicating diagnosis and treatment planning. While existing deep learning algorithms have achieved notable success in Metal Artifact Reduction (MAR), they often struggle to suppress artifacts while preserving structural details. To address this challenge, we propose FIND-Net (Fourier-Integrated Network with Dictionary Kernels), a novel MAR framework that integrates frequency and spatial domain processing to achieve superior artifact suppression and structural preservation. FIND-Net incorporates Fast Fourier Convolution (FFC) layers and trainable Gaussian filtering, treating MAR as a hybrid task operating in both spatial and frequency domains. This approach enhances global contextual understanding and frequency selectivity, effectively reducing artifacts while maintaining anatomical structures. Experiments on synthetic datasets show that FIND-Net achieves statistically significant improvements over state-of-the-art MAR methods, with a 3.07% MAE reduction, 0.18% SSIM increase, and 0.90% PSNR improvement, confirming robustness across varying artifact complexities. Furthermore, evaluations on real-world clinical CT scans confirm FIND-Net's ability to minimize modifications to clean anatomical regions while effectively suppressing metal-induced distortions. These findings highlight FIND-Net's potential for advancing MAR performance, offering superior structural preservation and improved clinical applicability. Code is available at https://github.com/Farid-Tasharofi/FIND-Net

comment: Accepted at MICCAI 2025. This is the submitted version prior to peer review. The final Version of Record will appear in the MICCAI 2025 proceedings (Springer LNCS)

☆ Fourier-Guided Attention Upsampling for Image Super-Resolution

Daejune Choi, Youchan No, Jinhyung Lee, Duksu Kim

We propose Frequency-Guided Attention (FGA), a lightweight upsampling module for single image super-resolution. Conventional upsamplers, such as Sub-Pixel Convolution, are efficient but frequently fail to reconstruct high-frequency details and introduce aliasing artifacts. FGA addresses these issues by integrating (1) a Fourier feature-based Multi-Layer Perceptron (MLP) for positional frequency encoding, (2) a cross-resolution Correlation Attention Layer for adaptive spatial alignment, and (3) a frequency-domain L1 loss for spectral fidelity supervision. Adding merely 0.3M parameters, FGA consistently enhances performance across five diverse super-resolution backbones in both lightweight and full-capacity scenarios. Experimental results demonstrate average PSNR gains of 0.12~0.14 dB and improved frequency-domain consistency by up to 29%, particularly evident on texture-rich datasets. Visual and spectral evaluations confirm FGA's effectiveness in reducing aliasing and preserving fine details, establishing it as a practical, scalable alternative to traditional upsampling methods.

comment: 15 pages, 7 figures, under submission to a journal

☆ DIVA-VQA: Detecting Inter-frame Variations in UGC Video Quality

Xinyi Wang, Angeliki Katsenou, David Bull

The rapid growth of user-generated (video) content (UGC) has driven increased demand for research on no-reference (NR) perceptual video quality assessment (VQA). NR-VQA is a key component for large-scale video quality monitoring in social media and streaming applications where a pristine reference is not available. This paper proposes a novel NR-VQA model based on spatio-temporal fragmentation driven by inter-frame variations. By leveraging these inter-frame differences, the model progressively analyses quality-sensitive regions at multiple levels: frames, patches, and fragmented frames. It integrates frames, fragmented residuals, and fragmented frames aligned with residuals to effectively capture global and local information. The model extracts both 2D and 3D features in order to characterize these spatio-temporal variations. Experiments conducted on five UGC datasets and against state-of-the-art models ranked our proposed method among the top 2 in terms of average rank correlation (DIVA-VQA-L: 0.898 and DIVA-VQA-B: 0.886). The improved performance is offered at a low runtime complexity, with DIVA-VQA-B ranked top and DIVA-VQA-L third on average compared to the fastest existing NR-VQA method. Code and models are publicly available at: https://github.com/xinyiW915/DIVA-VQA.

comment: 6 pages, 1 figure. Accepted for presentation at the 2025 IEEE International Conference on Image Processing (ICIP)

☆ Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving

Yuxin Cao, Yedi Zhang, Wentao He, Yifan Liao, Yan Xiao, Chang Li, Zhiyong Huang, Jin Song Dong

Learning-based autonomous driving systems remain critically vulnerable to adversarial patches, posing serious safety and security risks in their real-world deployment. Black-box attacks, notable for their high attack success rate without model knowledge, are especially concerning, with their transferability extensively studied to reduce computational costs compared to query-based attacks. Previous transferability-based black-box attacks typically adopt mean Average Precision (mAP) as the evaluation metric and design training loss accordingly. However, due to the presence of multiple detected bounding boxes and the relatively lenient Intersection over Union (IoU) thresholds, the attack effectiveness of these approaches is often overestimated, resulting in reduced success rates in practical attacking scenarios. Furthermore, patches trained on low-resolution data often fail to maintain effectiveness on high-resolution images, limiting their transferability to autonomous driving datasets. To fill this gap, we propose P$^3$A, a Powerful and Practical Patch Attack framework for 2D object detection in autonomous driving, specifically optimized for high-resolution datasets. First, we introduce a novel metric, Practical Attack Success Rate (PASR), to more accurately quantify attack effectiveness with greater relevance for pedestrian safety. Second, we present a tailored Localization-Confidence Suppression Loss (LCSL) to improve attack transferability under PASR. Finally, to maintain the transferability for high-resolution datasets, we further incorporate the Probabilistic Scale-Preserving Padding (PSPP) into the patch attack pipeline as a data preprocessing step. Extensive experiments show that P$^3$A outperforms state-of-the-art attacks on unseen models and unseen high-resolution datasets, both under the proposed practical IoU-based evaluation metric and the previous mAP-based metrics.

comment: 13 pages, 4 figures

☆ On Spectral Properties of Gradient-based Explanation Methods

Amir Mehrpanah, Erik Englesson, Hossein Azizpour

Understanding the behavior of deep networks is crucial to increase our confidence in their results. Despite an extensive body of work for explaining their predictions, researchers have faced reliability issues, which can be attributed to insufficient formalism. In our research, we adopt novel probabilistic and spectral perspectives to formally analyze explanation methods. Our study reveals a pervasive spectral bias stemming from the use of gradient, and sheds light on some common design choices that have been discovered experimentally, in particular, the use of squared gradient and input perturbation. We further characterize how the choice of perturbation hyperparameters in explanation methods, such as SmoothGrad, can lead to inconsistent explanations and introduce two remedies based on our proposed formalism: (i) a mechanism to determine a standard perturbation scale, and (ii) an aggregation method which we call SpectralLens. Finally, we substantiate our theoretical results through quantitative evaluations.

comment: 36 pages, 16 figures, published in European Conference on Computer Vision 2024

☆ EvTurb: Event Camera Guided Turbulence Removal

Yixing Liu, Minggui Teng, Yifei Xia, Peiqi Duan, Boxin Shi

Atmospheric turbulence degrades image quality by introducing blur and geometric tilt distortions, posing significant challenges to downstream computer vision tasks. Existing single-image and multi-frame methods struggle with the highly ill-posed nature of this problem due to the compositional complexity of turbulence-induced distortions. To address this, we propose EvTurb, an event guided turbulence removal framework that leverages high-speed event streams to decouple blur and tilt effects. EvTurb decouples blur and tilt effects by modeling event-based turbulence formation, specifically through a novel two-step event-guided network: event integrals are first employed to reduce blur in the coarse outputs. This is followed by employing a variance map, derived from raw event streams, to eliminate the tilt distortion for the refined outputs. Additionally, we present TurbEvent, the first real-captured dataset featuring diverse turbulence scenarios. Experimental results demonstrate that EvTurb surpasses state-of-the-art methods while maintaining computational efficiency.

☆ HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

Zheng Qin, Ruobing Zheng, Yabing Wang, Tianqi Li, Yi Yuan, Jingdong Chen, Le Wang

While Multimodal Large Language Models (MLLMs) show immense promise for achieving truly human-like interactions, progress is hindered by the lack of fine-grained evaluation frameworks for human-centered scenarios, encompassing both the understanding of complex human intentions and the provision of empathetic, context-aware responses. Here we introduce HumanSense, a comprehensive benchmark designed to evaluate the human-centered perception and interaction capabilities of MLLMs, with a particular focus on deep understanding of extended multimodal contexts and the formulation of rational feedback. Our evaluation reveals that leading MLLMs still have considerable room for improvement, particularly for advanced interaction-oriented tasks. Supplementing visual input with audio and text information yields substantial improvements, and Omni-modal models show advantages on these tasks. Furthermore, we argue that appropriate feedback stems from a contextual analysis of the interlocutor's needs and emotions, with reasoning ability serving as the key to unlocking it. Accordingly, we employ a multi-stage, modality-progressive reinforcement learning to enhance the reasoning abilities of an Omni model, achieving substantial gains on evaluation results. Additionally, we observe that successful reasoning processes exhibit highly consistent thought patterns. By designing corresponding prompts, we also enhance the performance of non-reasoning models in a training-free manner. Project page: \textcolor{brightpink}https://digital-avatar.github.io/ai/HumanSense/

☆ Towards Agentic AI for Multimodal-Guided Video Object Segmentation

Tuyen Tran, Thao Minh Le, Truyen Tran

Referring-based Video Object Segmentation is a multimodal problem that requires producing fine-grained segmentation results guided by external cues. Traditional approaches to this task typically involve training specialized models, which come with high computational complexity and manual annotation effort. Recent advances in vision-language foundation models open a promising direction toward training-free approaches. Several studies have explored leveraging these general-purpose models for fine-grained segmentation, achieving performance comparable to that of fully supervised, task-specific models. However, existing methods rely on fixed pipelines that lack the flexibility needed to adapt to the dynamic nature of the task. To address this limitation, we propose Multi-Modal Agent, a novel agentic system designed to solve this task in a more flexible and adaptive manner. Specifically, our method leverages the reasoning capabilities of large language models (LLMs) to generate dynamic workflows tailored to each input. This adaptive procedure iteratively interacts with a set of specialized tools designed for low-level tasks across different modalities to identify the target object described by the multimodal cues. Our agentic approach demonstrates clear improvements over prior methods on two multimodal-conditioned VOS tasks: RVOS and Ref-AVS.

☆ Adapting SAM via Cross-Entropy Masking for Class Imbalance in Remote Sensing Change Detection

Humza Naveed, Xina Zeng, Mitch Bryson, Nagita Mehrseresht

Foundational models have achieved significant success in diverse domains of computer vision. They learn general representations that are easily transferable to tasks not seen during training. One such foundational model is Segment anything model (SAM), which can accurately segment objects in images. We propose adapting the SAM encoder via fine-tuning for remote sensing change detection (RSCD) along with spatial-temporal feature enhancement (STFE) and multi-scale decoder fusion (MSDF) to detect changes robustly at multiple scales. Additionally, we propose a novel cross-entropy masking (CEM) loss to handle high class imbalance in change detection datasets. Our method outperforms state-of-the-art (SOTA) methods on four change detection datasets, Levir-CD, WHU-CD, CLCD, and S2Looking. We achieved 2.5% F1-score improvement on a large complex S2Looking dataset. The code is available at: https://github.com/humza909/SAM-CEM-CD

comment: work in progress

☆ SpaRC-AD: A Baseline for Radar-Camera Fusion in End-to-End Autonomous Driving

Philipp Wolters, Johannes Gilg, Torben Teepe, Gerhard Rigoll

End-to-end autonomous driving systems promise stronger performance through unified optimization of perception, motion forecasting, and planning. However, vision-based approaches face fundamental limitations in adverse weather conditions, partial occlusions, and precise velocity estimation - critical challenges in safety-sensitive scenarios where accurate motion understanding and long-horizon trajectory prediction are essential for collision avoidance. To address these limitations, we propose SpaRC-AD, a query-based end-to-end camera-radar fusion framework for planning-oriented autonomous driving. Through sparse 3D feature alignment, and doppler-based velocity estimation, we achieve strong 3D scene representations for refinement of agent anchors, map polylines and motion modelling. Our method achieves strong improvements over the state-of-the-art vision-only baselines across multiple autonomous driving tasks, including 3D detection (+4.8% mAP), multi-object tracking (+8.3% AMOTA), online mapping (+1.8% mAP), motion prediction (-4.0% mADE), and trajectory planning (-0.1m L2 and -9% TPC). We achieve both spatial coherence and temporal consistency on multiple challenging benchmarks, including real-world open-loop nuScenes, long-horizon T-nuScenes, and closed-loop simulator Bench2Drive. We show the effectiveness of radar-based fusion in safety-critical scenarios where accurate motion understanding and long-horizon trajectory prediction are essential for collision avoidance. The source code of all experiments is available at https://phi-wol.github.io/sparcad/

comment: 8 pages, 4 figures, 5 tables

☆ HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis

Shiyu Liu, Kui Jiang, Xianming Liu, Hongxun Yao, Xiaocheng Feng

Audio-driven talking head video generation enhances user engagement in human-computer interaction. However, current methods frequently produce videos with motion blur and lip jitter, primarily due to their reliance on implicit modeling of audio-facial motion correlations--an approach lacking explicit articulatory priors (i.e., anatomical guidance for speech-related facial movements). To overcome this limitation, we propose HM-Talker, a novel framework for generating high-fidelity, temporally coherent talking heads. HM-Talker leverages a hybrid motion representation combining both implicit and explicit motion cues. Explicit cues use Action Units (AUs), anatomically defined facial muscle movements, alongside implicit features to minimize phoneme-viseme misalignment. Specifically, our Cross-Modal Disentanglement Module (CMDM) extracts complementary implicit/explicit motion features while predicting AUs directly from audio input aligned to visual cues. To mitigate identity-dependent biases in explicit features and enhance cross-subject generalization, we introduce the Hybrid Motion Modeling Module (HMMM). This module dynamically merges randomly paired implicit/explicit features, enforcing identity-agnostic learning. Together, these components enable robust lip synchronization across diverse identities, advancing personalized talking head synthesis. Extensive experiments demonstrate HM-Talker's superiority over state-of-the-art methods in visual quality and lip-sync accuracy.

☆ PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks

Xinhao Wang, Zhiwei Lin, Zhongyu Xia, Yongtao Wang

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes substantial GPU memory requirements and extended training time due to weight fine-tuning.In this paper, we propose PTQAT, a novel general hybrid quantization algorithm for the efficient deployment of 3D perception networks. To address the speed accuracy trade-off between PTQ and QAT, our method selects critical layers for QAT fine-tuning and performs PTQ on the remaining layers. Contrary to intuition, fine-tuning the layers with smaller output discrepancies before and after quantization, rather than those with larger discrepancies, actually leads to greater improvements in the model's quantization accuracy. This means we better compensate for quantization errors during their propagation, rather than addressing them at the point where they occur. The proposed PTQAT achieves similar performance to QAT with more efficiency by freezing nearly 50% of quantifiable layers. Additionally, PTQAT is a universal quantization method that supports various quantization bit widths (4 bits) as well as different model architectures, including CNNs and Transformers. The experimental results on nuScenes across diverse 3D perception tasks, including object detection, semantic segmentation, and occupancy prediction, show that our method consistently outperforms QAT-only baselines. Notably, it achieves 0.2%-0.9% NDS and 0.3%-1.0% mAP gains in object detection, 0.3%-2.0% mIoU gains in semantic segmentation and occupancy prediction while fine-tuning fewer weights.

comment: 8 pages, Accepted by ICCVW 2025

☆ Retrieval-Augmented Prompt for OOD Detection

Ruisong Han, Zongbo Han, Jiahao Zhang, Mingyue Cheng, Changqing Zhang

Out-of-Distribution (OOD) detection is crucial for the reliable deployment of machine learning models in-the-wild, enabling accurate identification of test samples that differ from the training data distribution. Existing methods rely on auxiliary outlier samples or in-distribution (ID) data to generate outlier information for training, but due to limited outliers and their mismatch with real test OOD samples, they often fail to provide sufficient semantic supervision, leading to suboptimal performance. To address this, we propose a novel OOD detection method called Retrieval-Augmented Prompt (RAP). RAP augments a pre-trained vision-language model's prompts by retrieving external knowledge, offering enhanced semantic supervision for OOD detection. During training, RAP retrieves descriptive words for outliers based on joint similarity with external textual knowledge and uses them to augment the model's OOD prompts. During testing, RAP dynamically updates OOD prompts in real-time based on the encountered OOD samples, enabling the model to rapidly adapt to the test environment. Our extensive experiments demonstrate that RAP achieves state-of-the-art performance on large-scale OOD detection benchmarks. For example, in 1-shot OOD detection on the ImageNet-1k dataset, RAP reduces the average FPR95 by 7.05% and improves the AUROC by 1.71% compared to previous methods. Additionally, comprehensive ablation studies validate the effectiveness of each module and the underlying motivations of our approach.

☆ AR Surgical Navigation With Surface Tracing: Comparing In-SitVisualization with Tool-Tracking Guidance for Neurosurgical Applications

Marc J. Fischer, Jeffrey Potts, Gabriel Urreola, Dax Jones, Paolo Palmisciano, E. Bradley Strong, Branden Cord, Andrew D. Hernandez, Julia D. Sharma, E. Brandon Strong

Augmented Reality (AR) surgical navigation systems are emerging as the next generation of intraoperative surgical guidance, promising to overcome limitations of traditional navigation systems. However, known issues with AR depth perception due to vergence-accommodation conflict and occlusion handling limitations of the currently commercially available display technology present acute challenges in surgical settings where precision is paramount. This study presents a novel methodology for utilizing AR guidance to register anatomical targets and provide real-time instrument navigation using placement of simulated external ventricular drain catheters on a phantom model as the clinical scenario. The system registers target positions to the patient through a novel surface tracing method and uses real-time infrared tool tracking to aid in catheter placement, relying only on the onboard sensors of the Microsoft HoloLens 2. A group of intended users performed the procedure of simulated insertions under two AR guidance conditions: static in-situ visualization, where planned trajectories are overlaid directly onto the patient anatomy, and real-time tool-tracking guidance, where live feedback of the catheter's pose is provided relative to the plan. Following the insertion tests, computed tomography scans of the phantom models were acquired, allowing for evaluation of insertion accuracy, target deviation, angular error, and depth precision. System Usability Scale surveys assessed user experience and cognitive workload. Tool-tracking guidance improved performance metrics across all accuracy measures and was preferred by users in subjective evaluations. A free copy of this paper and all supplemental materials are available at https://bit.ly/45l89Hq.

comment: 10pages, 3 figures, will be published at ISMAR 2025 (accepted)

☆ PSScreen: Partially Supervised Multiple Retinal Disease Screening

Boyi Zheng, Qing Liu

comment: Accepted at BMVC 2025 (Oral)

☆ GCRPNet: Graph-Enhanced Contextual and Regional Perception Network For Salient Object Detection in Optical Remote Sensing Images

Mengyu Ren, Yutong Li, Hua Li, Runmin Cong, Sam Kwong

Salient object detection (SOD) in optical remote sensing images (ORSIs) faces numerous challenges, including significant variations in target scales and low contrast between targets and the background. Existing methods based on vision transformers (ViTs) and convolutional neural networks (CNNs) architectures aim to leverage both global and local features, but the difficulty in effectively integrating these heterogeneous features limits their overall performance. To overcome these limitations, we propose a graph-enhanced contextual and regional perception network (GCRPNet), which builds upon the Mamba architecture to simultaneously capture long-range dependencies and enhance regional feature representation. Specifically, we employ the visual state space (VSS) encoder to extract multi-scale features. To further achieve deep guidance and enhancement of these features, we first design a difference-similarity guided hierarchical graph attention module (DS-HGAM). This module strengthens cross-layer interaction capabilities between features of different scales while enhancing the model's structural perception,allowing it to distinguish between foreground and background more effectively. Then, we design the LEVSS block as the decoder of GCRPNet. This module integrates our proposed adaptive scanning strategy and multi-granularity collaborative attention enhancement module (MCAEM). It performs adaptive patch scanning on feature maps processed via multi-scale convolutions, thereby capturing rich local region information and enhancing Mamba's local modeling capability. Extensive experimental results demonstrate that the proposed model achieves state-of-the-art performance, validating its effectiveness and superiority.

☆ Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset

Ziye Deng, Ruihan He, Jiaxiang Liu, Yuan Wang, Zijie Meng, Songtao Jiang, Yong Xie, Zuozhu Liu

Medical image grounding aims to align natural language phrases with specific regions in medical images, serving as a foundational task for intelligent diagnosis, visual question answering (VQA), and automated report generation (MRG). However, existing research is constrained by limited modality coverage, coarse-grained annotations, and the absence of a unified, generalizable grounding framework. To address these challenges, we construct a large-scale medical grounding dataset Med-GLIP-5M comprising over 5.3 million region-level annotations across seven imaging modalities, covering diverse anatomical structures and pathological findings. The dataset supports both segmentation and grounding tasks with hierarchical region labels, ranging from organ-level boundaries to fine-grained lesions. Based on this foundation, we propose Med-GLIP, a modality-aware grounding framework trained on Med-GLIP-5M. Rather than relying on explicitly designed expert modules, Med-GLIP implicitly acquires hierarchical semantic understanding from diverse training data -- enabling it to recognize multi-granularity structures, such as distinguishing lungs from pneumonia lesions. Extensive experiments demonstrate that Med-GLIP consistently outperforms state-of-the-art baselines across multiple grounding benchmarks. Furthermore, integrating its spatial outputs into downstream tasks, including medical VQA and report generation, leads to substantial performance gains. Our dataset will be released soon.

☆ Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies

Ayushman Sarkar, Mohd Yamani Idna Idris, Zhenyu Yu

Visual reasoning is critical for a wide range of computer vision tasks that go beyond surface-level object detection and classification. Despite notable advances in relational, symbolic, temporal, causal, and commonsense reasoning, existing surveys often address these directions in isolation, lacking a unified analysis and comparison across reasoning types, methodologies, and evaluation protocols. This survey aims to address this gap by categorizing visual reasoning into five major types (relational, symbolic, temporal, causal, and commonsense) and systematically examining their implementation through architectures such as graph-based models, memory networks, attention mechanisms, and neuro-symbolic systems. We review evaluation protocols designed to assess functional correctness, structural consistency, and causal validity, and critically analyze their limitations in terms of generalizability, reproducibility, and explanatory power. Beyond evaluation, we identify key open challenges in visual reasoning, including scalability to complex scenes, deeper integration of symbolic and neural paradigms, the lack of comprehensive benchmark datasets, and reasoning under weak supervision. Finally, we outline a forward-looking research agenda for next-generation vision systems, emphasizing that bridging perception and reasoning is essential for building transparent, trustworthy, and cross-domain adaptive AI systems, particularly in critical domains such as autonomous driving and medical diagnostics.

☆ EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba

Quang Nguyen, Nhat Le, Baoru Huang, Minh Nhat Vu, Chengcheng Tang, Van Nguyen, Ngan Le, Thieu Vo, Anh Nguyen

Estimating human dance motion is a challenging task with various industrial applications. Recently, many efforts have focused on predicting human dance motion using either egocentric video or music as input. However, the task of jointly estimating human motion from both egocentric video and music remains largely unexplored. In this paper, we aim to develop a new method that predicts human dance motion from both egocentric video and music. In practice, the egocentric view often obscures much of the body, making accurate full-pose estimation challenging. Additionally, incorporating music requires the generated head and body movements to align well with both visual and musical inputs. We first introduce EgoAIST++, a new large-scale dataset that combines both egocentric views and music with more than 36 hours of dancing motion. Drawing on the success of diffusion models and Mamba on modeling sequences, we develop an EgoMusic Motion Network with a core Skeleton Mamba that explicitly captures the skeleton structure of the human body. We illustrate that our approach is theoretically supportive. Intensive experiments show that our method clearly outperforms state-of-the-art approaches and generalizes effectively to real-world data.

comment: Accepted at The 2025 IEEE/CVF International Conference on Computer Vision (ICCV 2025)

☆ A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection

Yangjie Xiao, Ke Zhang, Jiacun Wang, Xin Sheng, Yurong Guo, Meijuan Chen, Zehua Ren, Zhaoye Zheng, Zhenbing Zhao

Bolt defect detection is critical to ensure the safety of transmission lines. However, the scarcity of defect images and imbalanced data distributions significantly limit detection performance. To address this problem, we propose a segmentationdriven bolt defect editing method (SBDE) to augment the dataset. First, a bolt attribute segmentation model (Bolt-SAM) is proposed, which enhances the segmentation of complex bolt attributes through the CLAHE-FFT Adapter (CFA) and Multipart- Aware Mask Decoder (MAMD), generating high-quality masks for subsequent editing tasks. Second, a mask optimization module (MOD) is designed and integrated with the image inpainting model (LaMa) to construct the bolt defect attribute editing model (MOD-LaMa), which converts normal bolts into defective ones through attribute editing. Finally, an editing recovery augmentation (ERA) strategy is proposed to recover and put the edited defect bolts back into the original inspection scenes and expand the defect detection dataset. We constructed multiple bolt datasets and conducted extensive experiments. Experimental results demonstrate that the bolt defect images generated by SBDE significantly outperform state-of-the-art image editing models, and effectively improve the performance of bolt defect detection, which fully verifies the effectiveness and application potential of the proposed method. The code of the project is available at https://github.com/Jay-xyj/SBDE.

☆ Multi-Sample Anti-Aliasing and Constrained Optimization for 3D Gaussian Splatting

Zheng Zhou, Jia-Chen Zhang, Yu-Jie Xiong, Chun-Ming Xia

Recent advances in 3D Gaussian splatting have significantly improved real-time novel view synthesis, yet insufficient geometric constraints during scene optimization often result in blurred reconstructions of fine-grained details, particularly in regions with high-frequency textures and sharp discontinuities. To address this, we propose a comprehensive optimization framework integrating multisample anti-aliasing (MSAA) with dual geometric constraints. Our system computes pixel colors through adaptive blending of quadruple subsamples, effectively reducing aliasing artifacts in high-frequency components. The framework introduces two constraints: (a) an adaptive weighting strategy that prioritizes under-reconstructed regions through dynamic gradient analysis, and (b) gradient differential constraints enforcing geometric regularization at object boundaries. This targeted optimization enables the model to allocate computational resources preferentially to critical regions requiring refinement while maintaining global consistency. Extensive experimental evaluations across multiple benchmarks demonstrate that our method achieves state-of-the-art performance in detail preservation, particularly in preserving high-frequency textures and sharp discontinuities, while maintaining real-time rendering efficiency. Quantitative metrics and perceptual studies confirm statistically significant improvements over baseline approaches in both structural similarity (SSIM) and perceptual quality (LPIPS).

☆ TweezeEdit: Consistent and Efficient Image Editing with Path Regularization

Jianda Mao, Kaibo Wang, Yang Xiang, Kani Chen

Large-scale pre-trained diffusion models empower users to edit images through text guidance. However, existing methods often over-align with target prompts while inadequately preserving source image semantics. Such approaches generate target images explicitly or implicitly from the inversion noise of the source images, termed the inversion anchors. We identify this strategy as suboptimal for semantic preservation and inefficient due to elongated editing paths. We propose TweezeEdit, a tuning- and inversion-free framework for consistent and efficient image editing. Our method addresses these limitations by regularizing the entire denoising path rather than relying solely on the inversion anchors, ensuring source semantic retention and shortening editing paths. Guided by gradient-driven regularization, we efficiently inject target prompt semantics along a direct path using a consistency model. Extensive experiments demonstrate TweezeEdit's superior performance in semantic preservation and target alignment, outperforming existing methods. Remarkably, it requires only 12 steps (1.6 seconds per edit), underscoring its potential for real-time applications.

☆ On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations

Amir Mehrpanah, Matteo Gamba, Kevin Smith, Hossein Azizpour

ReLU networks, while prevalent for visual data, have sharp transitions, sometimes relying on individual pixels for predictions, making vanilla gradient-based explanations noisy and difficult to interpret. Existing methods, such as GradCAM, smooth these explanations by producing surrogate models at the cost of faithfulness. We introduce a unifying spectral framework to systematically analyze and quantify smoothness, faithfulness, and their trade-off in explanations. Using this framework, we quantify and regularize the contribution of ReLU networks to high-frequency information, providing a principled approach to identifying this trade-off. Our analysis characterizes how surrogate-based smoothing distorts explanations, leading to an ``explanation gap'' that we formally define and measure for different post-hoc methods. Finally, we validate our theoretical findings across different design choices, datasets, and ablations.

comment: 23 pages, 14 figures, to be published in International Conference on Computer Vision 2025

☆ STAMP: Multi-pattern Attention-aware Multiple Instance Learning for STAS Diagnosis in Multi-center Histopathology Images AAAI2026

Liangrui Pan, xiaoyu Li, Guang Zhu, Guanting Li, Ruixin Wang, Jiadi Luo, Yaning Yang, Liang qingchun, Shaoliang Peng

Spread through air spaces (STAS) constitutes a novel invasive pattern in lung adenocarcinoma (LUAD), associated with tumor recurrence and diminished survival rates. However, large-scale STAS diagnosis in LUAD remains a labor-intensive endeavor, compounded by the propensity for oversight and misdiagnosis due to its distinctive pathological characteristics and morphological features. Consequently, there is a pressing clinical imperative to leverage deep learning models for STAS diagnosis. This study initially assembled histopathological images from STAS patients at the Second Xiangya Hospital and the Third Xiangya Hospital of Central South University, alongside the TCGA-LUAD cohort. Three senior pathologists conducted cross-verification annotations to construct the STAS-SXY, STAS-TXY, and STAS-TCGA datasets. We then propose a multi-pattern attention-aware multiple instance learning framework, named STAMP, to analyze and diagnose the presence of STAS across multi-center histopathology images. Specifically, the dual-branch architecture guides the model to learn STAS-associated pathological features from distinct semantic spaces. Transformer-based instance encoding and a multi-pattern attention aggregation modules dynamically selects regions closely associated with STAS pathology, suppressing irrelevant noise and enhancing the discriminative power of global representations. Moreover, a similarity regularization constraint prevents feature redundancy across branches, thereby improving overall diagnostic accuracy. Extensive experiments demonstrated that STAMP achieved competitive diagnostic results on STAS-SXY, STAS-TXY and STAS-TCGA, with AUCs of 0.8058, 0.8017, and 0.7928, respectively, surpassing the clinical level.

comment: Submit to AAAI2026

☆ Enhanced Sparse Point Cloud Data Processing for Privacy-aware Human Action Recognition

Maimunatu Tunau, Vincent Gbouna Zakka, Zhuangzhuang Dai

Human Action Recognition (HAR) plays a crucial role in healthcare, fitness tracking, and ambient assisted living technologies. While traditional vision based HAR systems are effective, they pose privacy concerns. mmWave radar sensors offer a privacy preserving alternative but present challenges due to the sparse and noisy nature of their point cloud data. In the literature, three primary data processing methods: Density-Based Spatial Clustering of Applications with Noise (DBSCAN), the Hungarian Algorithm, and Kalman Filtering have been widely used to improve the quality and continuity of radar data. However, a comprehensive evaluation of these methods, both individually and in combination, remains lacking. This paper addresses that gap by conducting a detailed performance analysis of the three methods using the MiliPoint dataset. We evaluate each method individually, all possible pairwise combinations, and the combination of all three, assessing both recognition accuracy and computational cost. Furthermore, we propose targeted enhancements to the individual methods aimed at improving accuracy. Our results provide crucial insights into the strengths and trade-offs of each method and their integrations, guiding future work on mmWave based HAR systems

☆ SingleStrip: learning skull-stripping from a single labeled example

Bella Specktor-Fadida, Malte Hoffmann

Deep learning segmentation relies heavily on labeled data, but manual labeling is laborious and time-consuming, especially for volumetric images such as brain magnetic resonance imaging (MRI). While recent domain-randomization techniques alleviate the dependency on labeled data by synthesizing diverse training images from label maps, they offer limited anatomical variability when very few label maps are available. Semi-supervised self-training addresses label scarcity by iteratively incorporating model predictions into the training set, enabling networks to learn from unlabeled data. In this work, we combine domain randomization with self-training to train three-dimensional skull-stripping networks using as little as a single labeled example. First, we automatically bin voxel intensities, yielding labels we use to synthesize images for training an initial skull-stripping model. Second, we train a convolutional autoencoder (AE) on the labeled example and use its reconstruction error to assess the quality of brain masks predicted for unlabeled data. Third, we select the top-ranking pseudo-labels to fine-tune the network, achieving skull-stripping performance on out-of-distribution data that approaches models trained with more labeled images. We compare AE-based ranking to consistency-based ranking under test-time augmentation, finding that the AE approach yields a stronger correlation with segmentation accuracy. Our results highlight the potential of combining domain randomization and AE-based quality control to enable effective semi-supervised segmentation from extremely limited labeled data. This strategy may ease the labeling burden that slows progress in studies involving new anatomical structures or emerging imaging techniques.

comment: Accepted as an oral presentation to the MICCAI 2025 Data Engineering in Medical Imaging (DEMI) workshop

☆ Multi-Label Plant Species Prediction with Metadata-Enhanced Multi-Head Vision Transformers

Hanna Herasimchyk, Robin Labryga, Tomislav Prusina

We present a multi-head vision transformer approach for multi-label plant species prediction in vegetation plot images, addressing the PlantCLEF 2025 challenge. The task involves training models on single-species plant images while testing on multi-species quadrat images, creating a drastic domain shift. Our methodology leverages a pre-trained DINOv2 Vision Transformer Base (ViT-B/14) backbone with multiple classification heads for species, genus, and family prediction, utilizing taxonomic hierarchies. Key contributions include multi-scale tiling to capture plants at different scales, dynamic threshold optimization based on mean prediction length, and ensemble strategies through bagging and Hydra model architectures. The approach incorporates various inference techniques including image cropping to remove non-plant artifacts, top-n filtering for prediction constraints, and logit thresholding strategies. Experiments were conducted on approximately 1.4 million training images covering 7,806 plant species. Results demonstrate strong performance, making our submission 3rd best on the private leaderboard. Our code is available at https://github.com/geranium12/plant-clef-2025/tree/v1.0.0.

comment: Accepted for publication at: LifeCLEF Lab at CLEF 2025 Working Notes, 2025, Madrid, Spain

☆ Trajectory-aware Shifted State Space Models for Online Video Super-Resolution

Qiang Zhu, Xiandong Meng, Yuxian Jiang, Fan Zhang, David Bull, Shuyuan Zhu, Bing Zeng

Online video super-resolution (VSR) is an important technique for many real-world video processing applications, which aims to restore the current high-resolution video frame based on temporally previous frames. Most of the existing online VSR methods solely employ one neighboring previous frame to achieve temporal alignment, which limits long-range temporal modeling of videos. Recently, state space models (SSMs) have been proposed with linear computational complexity and a global receptive field, which significantly improve computational efficiency and performance. In this context, this paper presents a novel online VSR method based on Trajectory-aware Shifted SSMs (TS-Mamba), leveraging both long-term trajectory modeling and low-complexity Mamba to achieve efficient spatio-temporal information aggregation. Specifically, TS-Mamba first constructs the trajectories within a video to select the most similar tokens from the previous frames. Then, a Trajectory-aware Shifted Mamba Aggregation (TSMA) module consisting of proposed shifted SSMs blocks is employed to aggregate the selected tokens. The shifted SSMs blocks are designed based on Hilbert scannings and corresponding shift operations to compensate for scanning losses and strengthen the spatial continuity of Mamba. Additionally, we propose a trajectory-aware loss function to supervise the trajectory generation, ensuring the accuracy of token selection when training our model. Extensive experiments on three widely used VSR test datasets demonstrate that compared with six online VSR benchmark models, our TS-Mamba achieves state-of-the-art performance in most cases and over 22.7\% complexity reduction (in MACs). The source code for TS-Mamba will be available at https://github.com.

☆ From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images

Pablo Hernández-Cámara, Jesus Malo, Valero Laparra

A number of scientists suggested that human visual perception may emerge from image statistics, shaping efficient neural representations in early vision. In this work, a bio-inspired architecture that can accommodate several known facts in the retina-V1 cortex, the PerceptNet, has been end-to-end optimized for different tasks related to image reconstruction: autoencoding, denoising, deblurring, and sparsity regularization. Our results show that the encoder stage (V1-like layer) consistently exhibits the highest correlation with human perceptual judgments on image distortion despite not using perceptual information in the initialization or training. This alignment exhibits an optimum for moderate noise, blur and sparsity. These findings suggest that the visual system may be tuned to remove those particular levels of distortion with that level of sparsity and that biologically inspired models can learn perceptual metrics without human supervision.

☆ SkeySpot: Automating Service Key Detection for Digital Electrical Layout Plans in the Construction Industry

Dhruv Dosi, Rohit Meena, Param Rajpura, Yogesh Kumar Meena

Legacy floor plans, often preserved only as scanned documents, remain essential resources for architecture, urban planning, and facility management in the construction industry. However, the lack of machine-readable floor plans render large-scale interpretation both time-consuming and error-prone. Automated symbol spotting offers a scalable solution by enabling the identification of service key symbols directly from floor plans, supporting workflows such as cost estimation, infrastructure maintenance, and regulatory compliance. This work introduces a labelled Digitised Electrical Layout Plans (DELP) dataset comprising 45 scanned electrical layout plans annotated with 2,450 instances across 34 distinct service key classes. A systematic evaluation framework is proposed using pretrained object detection models for DELP dataset. Among the models benchmarked, YOLOv8 achieves the highest performance with a mean Average Precision (mAP) of 82.5\%. Using YOLOv8, we develop SkeySpot, a lightweight, open-source toolkit for real-time detection, classification, and quantification of electrical symbols. SkeySpot produces structured, standardised outputs that can be scaled up for interoperable building information workflows, ultimately enabling compatibility across downstream applications and regulatory platforms. By lowering dependency on proprietary CAD systems and reducing manual annotation effort, this approach makes the digitisation of electrical layouts more accessible to small and medium-sized enterprises (SMEs) in the construction industry, while supporting broader goals of standardisation, interoperability, and sustainability in the built environment.

comment: 6 pages, preprint accepted in IEEE SMC 2025

☆ DOD-SA: Infrared-Visible Decoupled Object Detection with Single-Modality Annotations

Hang Jin, Chenqiang Gao, Junjie Guo, Fangcen Liu, Kanghui Tian, Qinyao Chang

Infrared-visible object detection has shown great potential in real-world applications, enabling robust all-day perception by leveraging the complementary information of infrared and visible images. However, existing methods typically require dual-modality annotations to output detection results for both modalities during prediction, which incurs high annotation costs. To address this challenge, we propose a novel infrared-visible Decoupled Object Detection framework with Single-modality Annotations, called DOD-SA. The architecture of DOD-SA is built upon a Single- and Dual-Modality Collaborative Teacher-Student Network (CoSD-TSNet), which consists of a single-modality branch (SM-Branch) and a dual-modality decoupled branch (DMD-Branch). The teacher model generates pseudo-labels for the unlabeled modality, simultaneously supporting the training of the student model. The collaborative design enables cross-modality knowledge transfer from the labeled modality to the unlabeled modality, and facilitates effective SM-to-DMD branch supervision. To further improve the decoupling ability of the model and the pseudo-label quality, we introduce a Progressive and Self-Tuning Training Strategy (PaST) that trains the model in three stages: (1) pretraining SM-Branch, (2) guiding the learning of DMD-Branch by SM-Branch, and (3) refining DMD-Branch. In addition, we design a Pseudo Label Assigner (PLA) to align and pair labels across modalities, explicitly addressing modality misalignment during training. Extensive experiments on the DroneVehicle dataset demonstrate that our method outperforms state-of-the-art (SOTA).

comment: 9 pages, 5 figures

☆ We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

Runqi Qiao, Qiuna Tan, Peiqing Yang, Yanzi Wang, Xiaowan Wang, Enhui Wan, Sitong Zhou, Guanting Dong, Yuchen Zeng, Yida Xu, Jie Wang, Chong Sun, Chen Li, Honggang Zhang

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to comprehensively enhance the mathematical reasoning abilities of MLLMs. The key contributions of We-Math 2.0 are fourfold: (1) MathBook Knowledge System: We construct a five-level hierarchical system encompassing 491 knowledge points and 1,819 fundamental principles. (2) MathBook-Standard & Pro: We develop MathBook-Standard, a dataset that ensures broad conceptual coverage and flexibility through dual expansion. Additionally, we define a three-dimensional difficulty space and generate 7 progressive variants per problem to build MathBook-Pro, a challenging dataset for robust training. (3) MathBook-RL: We propose a two-stage RL framework comprising: (i) Cold-Start Fine-tuning, which aligns the model with knowledge-oriented chain-of-thought reasoning; and (ii) Progressive Alignment RL, leveraging average-reward learning and dynamic data scheduling to achieve progressive alignment across difficulty levels. (4) MathBookEval: We introduce a comprehensive benchmark covering all 491 knowledge points with diverse reasoning step distributions. Experimental results show that MathBook-RL performs competitively with existing baselines on four widely-used benchmarks and achieves strong results on MathBookEval, suggesting promising generalization in mathematical reasoning.

comment: Working in progress

☆ CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation

Baichen Liu, Qi Lyu, Xudong Wang, Jiahua Dong, Lianqing Liu, Zhi Han

Continual video instance segmentation demands both the plasticity to absorb new object categories and the stability to retain previously learned ones, all while preserving temporal consistency across frames. In this work, we introduce Contrastive Residual Injection and Semantic Prompting (CRISP), an earlier attempt tailored to address the instance-wise, category-wise, and task-wise confusion in continual video instance segmentation. For instance-wise learning, we model instance tracking and construct instance correlation loss, which emphasizes the correlation with the prior query space while strengthening the specificity of the current task query. For category-wise learning, we build an adaptive residual semantic prompt (ARSP) learning framework, which constructs a learnable semantic residual prompt pool generated by category text and uses an adjustive query-prompt matching mechanism to build a mapping relationship between the query of the current task and the semantic residual prompt. Meanwhile, a semantic consistency loss based on the contrastive learning is introduced to maintain semantic coherence between object queries and residual prompts during incremental training. For task-wise learning, to ensure the correlation at the inter-task level within the query space, we introduce a concise yet powerful initialization strategy for incremental prompts. Extensive experiments on YouTube-VIS-2019 and YouTube-VIS-2021 datasets demonstrate that CRISP significantly outperforms existing continual segmentation methods in the long-term continual video instance segmentation task, avoiding catastrophic forgetting and effectively improving segmentation and classification performance. The code is available at https://github.com/01upup10/CRISP.

☆ MM-Food-100K: A 100,000-Sample Multimodal Food Intelligence Dataset with Verifiable Provenance

Yi Dong, Yusuke Muraoka, Scott Shi, Yi Zhang

We present MM-Food-100K, a public 100,000-sample multimodal food intelligence dataset with verifiable provenance. It is a curated approximately 10% open subset of an original 1.2 million, quality-accepted corpus of food images annotated for a wide range of information (such as dish name, region of creation). The corpus was collected over six weeks from over 87,000 contributors using the Codatta contribution model, which combines community sourcing with configurable AI-assisted quality checks; each submission is linked to a wallet address in a secure off-chain ledger for traceability, with a full on-chain protocol on the roadmap. We describe the schema, pipeline, and QA, and validate utility by fine-tuning large vision-language models (ChatGPT 5, ChatGPT OSS, Qwen-Max) on image-based nutrition prediction. Fine-tuning yields consistent gains over out-of-box baselines across standard metrics; we report results primarily on the MM-Food-100K subset. We release MM-Food-100K for publicly free access and retain approximately 90% for potential commercial access with revenue sharing to contributors.

comment: 10 pages, 5 figures, 6 tables. The dataset is available at https://huggingface.co/datasets/Codatta/MM-Food-100K

☆ STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes

Keishi Ishihara, Kento Sasaki, Tsubasa Takahashi, Daiki Shiono, Yu Yamaguchi

Vision-Language Models (VLMs) have been applied to autonomous driving to support decision-making in complex real-world scenarios. However, their training on static, web-sourced image-text pairs fundamentally limits the precise spatiotemporal reasoning required to understand and predict dynamic traffic scenes. We address this critical gap with STRIDE-QA, a large-scale visual question answering (VQA) dataset for physically grounded reasoning from an ego-centric perspective. Constructed from 100 hours of multi-sensor driving data in Tokyo, capturing diverse and challenging conditions, STRIDE-QA is the largest VQA dataset for spatiotemporal reasoning in urban driving, offering 16 million QA pairs over 285K frames. Grounded by dense, automatically generated annotations including 3D bounding boxes, segmentation masks, and multi-object tracks, the dataset uniquely supports both object-centric and ego-centric reasoning through three novel QA tasks that require spatial localization and temporal prediction. Our benchmarks demonstrate that existing VLMs struggle significantly, achieving near-zero scores on prediction consistency. In contrast, VLMs fine-tuned on STRIDE-QA exhibit dramatic performance gains, achieving 55% success in spatial localization and 28% consistency in future motion prediction, compared to near-zero scores from general-purpose VLMs. Therefore, STRIDE-QA establishes a comprehensive foundation for developing more reliable VLMs for safety-critical autonomous systems.

comment: Project Page: https://turingmotors.github.io/stride-qa/

☆ NanoControl: A Lightweight Framework for Precise and Efficient Control in Diffusion Transformer

Shanyuan Liu, Jian Zhu, Junda Lu, Yue Gong, Liuzhuozheng Li, Bo Cheng, Yuhang Ma, Liebucha Wu, Xiaoyu Wu, Dawei Leng, Yuhui Yin

Diffusion Transformers (DiTs) have demonstrated exceptional capabilities in text-to-image synthesis. However, in the domain of controllable text-to-image generation using DiTs, most existing methods still rely on the ControlNet paradigm originally designed for UNet-based diffusion models. This paradigm introduces significant parameter overhead and increased computational costs. To address these challenges, we propose the Nano Control Diffusion Transformer (NanoControl), which employs Flux as the backbone network. Our model achieves state-of-the-art controllable text-to-image generation performance while incurring only a 0.024\% increase in parameter count and a 0.029\% increase in GFLOPs, thus enabling highly efficient controllable generation. Specifically, rather than duplicating the DiT backbone for control, we design a LoRA-style (low-rank adaptation) control module that directly learns control signals from raw conditioning inputs. Furthermore, we introduce a KV-Context Augmentation mechanism that integrates condition-specific key-value information into the backbone in a simple yet highly effective manner, facilitating deep fusion of conditional features. Extensive benchmark experiments demonstrate that NanoControl significantly reduces computational overhead compared to conventional control approaches, while maintaining superior generation quality and achieving improved controllability.

☆ CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model

Zhuoyuan Yu, Yuxing Long, Zihan Yang, Chengyan Zeng, Hongwei Fan, Jiyao Zhang, Hao Dong

Existing vision-and-language navigation models often deviate from the correct trajectory when executing instructions. However, these models lack effective error correction capability, hindering their recovery from errors. To address this challenge, we propose Self-correction Flywheel, a novel post-training paradigm. Instead of considering the model's error trajectories on the training set as a drawback, our paradigm emphasizes their significance as a valuable data source. We have developed a method to identify deviations in these error trajectories and devised innovative techniques to automatically generate self-correction data for perception and action. These self-correction data serve as fuel to power the model's continued training. The brilliance of our paradigm is revealed when we re-evaluate the model on the training set, uncovering new error trajectories. At this time, the self-correction flywheel begins to spin. Through multiple flywheel iterations, we progressively enhance our monocular RGB-based VLA navigation model CorrectNav. Experiments on R2R-CE and RxR-CE benchmarks show CorrectNav achieves new state-of-the-art success rates of 65.1% and 69.3%, surpassing prior best VLA navigation models by 8.2% and 16.4%. Real robot tests in various indoor and outdoor environments demonstrate \method's superior capability of error correction, dynamic obstacle avoidance, and long instruction following.

☆ SC-Lane: Slope-aware and Consistent Road Height Estimation Framework for 3D Lane Detection

Chaesong Park, Eunbin Seo, Jihyeon Hwang, Jongwoo Lim

In this paper, we introduce SC-Lane, a novel slope-aware and temporally consistent heightmap estimation framework for 3D lane detection. Unlike previous approaches that rely on fixed slope anchors, SC-Lane adaptively determines the fusion of slope-specific height features, improving robustness to diverse road geometries. To achieve this, we propose a Slope-Aware Adaptive Feature module that dynamically predicts the appropriate weights from image cues for integrating multi-slope representations into a unified heightmap. Additionally, a Height Consistency Module enforces temporal coherence, ensuring stable and accurate height estimation across consecutive frames, which is crucial for real-world driving scenarios. To evaluate the effectiveness of SC-Lane, we employ three standardized metrics-Mean Absolute Error(MAE), Root Mean Squared Error (RMSE), and threshold-based accuracy-which, although common in surface and depth estimation, have been underutilized for road height assessment. Using the LiDAR-derived heightmap dataset introduced in prior work [20], we benchmark our method under these metrics, thereby establishing a rigorous standard for future comparisons. Extensive experiments on the OpenLane benchmark demonstrate that SC-Lane significantly improves both height estimation and 3D lane detection, achieving state-of-the-art performance with an F-score of 64.3%, outperforming existing methods by a notable margin. For detailed results and a demonstration video, please refer to our project page:https://parkchaesong.github.io/sclane/

comment: 10 pages, 4 figures, 5 tables

☆ Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models

Eunseo Koh, Seunghoo Hong, Tae-Young Kim, Simon S. Woo, Jae-Pil Heo

Text-to-Image (T2I) diffusion models have made significant progress in generating diverse high-quality images from textual prompts. However, these models still face challenges in suppressing content that is strongly entangled with specific words. For example, when generating an image of ``Charlie Chaplin", a ``mustache" consistently appears even if explicitly instructed not to include it, as the concept of ``mustache" is strongly entangled with ``Charlie Chaplin". To address this issue, we propose a novel approach to directly suppress such entangled content within the text embedding space of diffusion models. Our method introduces a delta vector that modifies the text embedding to weaken the influence of undesired content in the generated image, and we further demonstrate that this delta vector can be easily obtained through a zero-shot approach. Furthermore, we propose a Selective Suppression with Delta Vector (SSDV) method to adapt delta vector into the cross-attention mechanism, enabling more effective suppression of unwanted content in regions where it would otherwise be generated. Additionally, we enabled more precise suppression in personalized T2I models by optimizing delta vector, which previous baselines were unable to achieve. Extensive experimental results demonstrate that our approach significantly outperforms existing methods, both in terms of quantitative and qualitative metrics.

☆ PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection

Haibin Sun, Xinghui Song

Driver distraction detection is essential for improving traffic safety and reducing road accidents. However, existing models often suffer from degraded generalization when deployed in real-world scenarios. This limitation primarily arises from the few-shot learning challenge caused by the high cost of data annotation in practical environments, as well as the substantial domain shift between training datasets and target deployment conditions. To address these issues, we propose a Pose-driven Quality-controlled Data Augmentation Framework (PQ-DAF) that leverages a vision-language model for sample filtering to cost-effectively expand training data and enhance cross-domain robustness. Specifically, we employ a Progressive Conditional Diffusion Model (PCDMs) to accurately capture key driver pose features and synthesize diverse training examples. A sample quality assessment module, built upon the CogVLM vision-language model, is then introduced to filter out low-quality synthetic samples based on a confidence threshold, ensuring the reliability of the augmented dataset. Extensive experiments demonstrate that PQ-DAF substantially improves performance in few-shot driver distraction detection, achieving significant gains in model generalization under data-scarce conditions.

comment: 11 pages, 6 figures

☆ Unlocking Robust Semantic Segmentation Performance via Label-only Elastic Deformations against Implicit Label Noise

Yechan Kim, Dongho Yoon, Younkwan Lee, Unse Fatima, Hong Kook Kim, Songjae Lee, Sanga Park, Jeong Ho Park, Seonjong Kang, Moongu Jeon

While previous studies on image segmentation focus on handling severe (or explicit) label noise, real-world datasets also exhibit subtle (or implicit) label imperfections. These arise from inherent challenges, such as ambiguous object boundaries and annotator variability. Although not explicitly present, such mild and latent noise can still impair model performance. Typical data augmentation methods, which apply identical transformations to the image and its label, risk amplifying these subtle imperfections and limiting the model's generalization capacity. In this paper, we introduce NSegment+, a novel augmentation framework that decouples image and label transformations to address such realistic noise for semantic segmentation. By introducing controlled elastic deformations only to segmentation labels while preserving the original images, our method encourages models to focus on learning robust representations of object structures despite minor label inconsistencies. Extensive experiments demonstrate that NSegment+ consistently improves performance, achieving mIoU gains of up to +2.29, +2.38, +1.75, and +3.39 in average on Vaihingen, LoveDA, Cityscapes, and PASCAL VOC, respectively-even without bells and whistles, highlighting the importance of addressing implicit label noise. These gains can be further amplified when combined with other training tricks, including CutMix and Label Smoothing.

☆ Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion Models

Hyundo Lee, Suhyung Choi, Byoung-Tak Zhang, Inwoo Hwang

Image generation models trained on large datasets can synthesize high-quality images but often produce spatially inconsistent and distorted images due to limited information about the underlying structures and spatial layouts. In this work, we leverage intrinsic scene properties (e.g., depth, segmentation maps) that provide rich information about the underlying scene, unlike prior approaches that solely rely on image-text pairs or use intrinsics as conditional inputs. Our approach aims to co-generate both images and their corresponding intrinsics, enabling the model to implicitly capture the underlying scene structure and generate more spatially consistent and realistic images. Specifically, we first extract rich intrinsic scene properties from a large image dataset with pre-trained estimators, eliminating the need for additional scene information or explicit 3D representations. We then aggregate various intrinsic scene properties into a single latent variable using an autoencoder. Building upon pre-trained large-scale Latent Diffusion Models (LDMs), our method simultaneously denoises the image and intrinsic domains by carefully sharing mutual information so that the image and intrinsic reflect each other without degrading image quality. Experimental results demonstrate that our method corrects spatial inconsistencies and produces a more natural layout of scenes while maintaining the fidelity and textual alignment of the base model (e.g., Stable Diffusion).

☆ Contrast Sensitivity Function of Multimodal Vision-Language Models

Pablo Hernández-Cámara, Alexandra Gomez-Villa, Jose Manuel Jaén-Lorites, Jorge Vila-Tomás, Jesus Malo, Valero Laparra

Assessing the alignment of multimodal vision-language models~(VLMs) with human perception is essential to understand how they perceive low-level visual features. A key characteristic of human vision is the contrast sensitivity function (CSF), which describes sensitivity to spatial frequency at low-contrasts. Here, we introduce a novel behavioral psychophysics-inspired method to estimate the CSF of chat-based VLMs by directly prompting them to judge pattern visibility at different contrasts for each frequency. This methodology is closer to the real experiments in psychophysics than the previously reported. Using band-pass filtered noise images and a diverse set of prompts, we assess model responses across multiple architectures. We find that while some models approximate human-like CSF shape or magnitude, none fully replicate both. Notably, prompt phrasing has a large effect on the responses, raising concerns about prompt stability. Our results provide a new framework for probing visual sensitivity in multimodal models and reveal key gaps between their visual representations and human perception.

☆ UWB-PostureGuard: A Privacy-Preserving RF Sensing System for Continuous Ergonomic Sitting Posture Monitoring

Haotang Li, Zhenyu Qi, Sen He, Kebin Peng, Sheng Tan, Yili Ren, Tomas Cerny, Jiyue Zhao, Zi Wang

Improper sitting posture during prolonged computer use has become a significant public health concern. Traditional posture monitoring solutions face substantial barriers, including privacy concerns with camera-based systems and user discomfort with wearable sensors. This paper presents UWB-PostureGuard, a privacy-preserving ultra-wideband (UWB) sensing system that advances mobile technologies for preventive health management through continuous, contactless monitoring of ergonomic sitting posture. Our system leverages commercial UWB devices, utilizing comprehensive feature engineering to extract multiple ergonomic sitting posture features. We develop PoseGBDT to effectively capture temporal dependencies in posture patterns, addressing limitations of traditional frame-wise classification approaches. Extensive real-world evaluation across 10 participants and 19 distinct postures demonstrates exceptional performance, achieving 99.11% accuracy while maintaining robustness against environmental variables such as clothing thickness, additional devices, and furniture configurations. Our system provides a scalable, privacy-preserving mobile health solution on existing platforms for proactive ergonomic management, improving quality of life at low costs.

☆ HierOctFusion: Multi-scale Octree-based 3D Shape Generation via Part-Whole-Hierarchy Message Passing

Xinjie Gao, Bi'an Du, Wei Hu

3D content generation remains a fundamental yet challenging task due to the inherent structural complexity of 3D data. While recent octree-based diffusion models offer a promising balance between efficiency and quality through hierarchical generation, they often overlook two key insights: 1) existing methods typically model 3D objects as holistic entities, ignoring their semantic part hierarchies and limiting generalization; and 2) holistic high-resolution modeling is computationally expensive, whereas real-world objects are inherently sparse and hierarchical, making them well-suited for layered generation. Motivated by these observations, we propose HierOctFusion, a part-aware multi-scale octree diffusion model that enhances hierarchical feature interaction for generating fine-grained and sparse object structures. Furthermore, we introduce a cross-attention conditioning mechanism that injects part-level information into the generation process, enabling semantic features to propagate effectively across hierarchical levels from parts to the whole. Additionally, we construct a 3D dataset with part category annotations using a pre-trained segmentation model to facilitate training and evaluation. Experiments demonstrate that HierOctFusion achieves superior shape quality and efficiency compared to prior methods.

☆ LD-LAudio-V1: Video-to-Long-Form-Audio Generation Extension with Dual Lightweight Adapters

Haomin Zhang, Kristin Qi, Shuxin Yang, Zihao Chen, Chaofan Ding, Xinhan Di

comment: Gen4AVC@ICCV: 1st Workshop on Generative AI for Audio-Visual Content Creation

☆ Data-Driven Abdominal Phenotypes of Type 2 Diabetes in Lean, Overweight, and Obese Cohorts

Lucas W. Remedios, Chloe Choe, Trent M. Schwartz, Dingjie Su, Gaurav Rudravaram, Chenyu Gao, Aravind R. Krishnan, Adam M. Saunders, Michael E. Kim, Shunxing Bao, Alvin C. Powers, Bennett A. Landman, John Virostko

Purpose: Although elevated BMI is a well-known risk factor for type 2 diabetes, the disease's presence in some lean adults and absence in others with obesity suggests that detailed body composition may uncover abdominal phenotypes of type 2 diabetes. With AI, we can now extract detailed measurements of size, shape, and fat content from abdominal structures in 3D clinical imaging at scale. This creates an opportunity to empirically define body composition signatures linked to type 2 diabetes risk and protection using large-scale clinical data. Approach: To uncover BMI-specific diabetic abdominal patterns from clinical CT, we applied our design four times: once on the full cohort (n = 1,728) and once on lean (n = 497), overweight (n = 611), and obese (n = 620) subgroups separately. Briefly, our experimental design transforms abdominal scans into collections of explainable measurements through segmentation, classifies type 2 diabetes through a cross-validated random forest, measures how features contribute to model-estimated risk or protection through SHAP analysis, groups scans by shared model decision patterns (clustering from SHAP) and links back to anatomical differences (classification). Results: The random-forests achieved mean AUCs of 0.72-0.74. There were shared type 2 diabetes signatures in each group; fatty skeletal muscle, older age, greater visceral and subcutaneous fat, and a smaller or fat-laden pancreas. Univariate logistic regression confirmed the direction of 14-18 of the top 20 predictors within each subgroup (p < 0.05). Conclusions: Our findings suggest that abdominal drivers of type 2 diabetes may be consistent across weight classes.

☆ Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset ACM MM 25

Wentao Mo, Qingchao Chen, Yuxin Peng, Siyuan Huang, Yang Liu

The advancement of 3D vision-language (3D VL) learning is hindered by several limitations in existing 3D VL datasets: they rarely necessitate reasoning beyond a close range of objects in single viewpoint, and annotations often link instructions to single objects, missing richer contextual alignments between multiple objects. This significantly curtails the development of models capable of deep, multi-view 3D scene understanding over distant objects. To address these challenges, we introduce MV-ScanQA, a novel 3D question answering dataset where 68% of questions explicitly require integrating information from multiple views (compared to less than 7% in existing datasets), thereby rigorously testing multi-view compositional reasoning. To facilitate the training of models for such demanding scenarios, we present TripAlign dataset, a large-scale and low-cost 2D-3D-language pre-training corpus containing 1M <2D view, set of 3D objects, text> triplets that explicitly aligns groups of contextually related objects with text, providing richer, view-grounded multi-object multimodal alignment signals than previous single-object annotations. We further develop LEGO, a baseline method for the multi-view reasoning challenge in MV-ScanQA, transferring knowledge from pre-trained 2D LVLMs to 3D domain with TripAlign. Empirically, LEGO pre-trained on TripAlign achieves state-of-the-art performance not only on the proposed MV-ScanQA, but also on existing benchmarks for 3D dense captioning and question answering. Datasets and code are available at https://matthewdm0816.github.io/tripalign-mvscanqa.

comment: Accepeted to ACM MM 25

☆ GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning

Kelin Yu, Sheng Zhang, Harshit Soora, Furong Huang, Heng Huang, Pratap Tokekar, Ruohan Gao

Recent advances have shown that video generation models can enhance robot learning by deriving effective robot actions through inverse dynamics. However, these methods heavily depend on the quality of generated data and struggle with fine-grained manipulation due to the lack of environment feedback. While video-based reinforcement learning improves policy robustness, it remains constrained by the uncertainty of video generation and the challenges of collecting large-scale robot datasets for training diffusion models. To address these limitations, we propose GenFlowRL, which derives shaped rewards from generated flow trained from diverse cross-embodiment datasets. This enables learning generalizable and robust policies from diverse demonstrations using low-dimensional, object-centric features. Experiments on 10 manipulation tasks, both in simulation and real-world cross-embodiment evaluations, demonstrate that GenFlowRL effectively leverages manipulation features extracted from generated object-centric flow, consistently achieving superior performance across diverse and challenging scenarios. Our Project Page: https://colinyu1.github.io/genflowrl

comment: Published at ICCV 2025

♻ ☆ MedVLThinker: Simple Baselines for Multimodal Medical Reasoning

Xiaoke Huang, Juncheng Wu, Hui Liu, Xianfeng Tang, Yuyin Zhou

Large Reasoning Models (LRMs) have introduced a new paradigm in AI by enabling models to ``think before responding" via chain-of-thought reasoning. However, the absence of open and reproducible recipes for building reasoning-centric medical LMMs hinders community-wide research, analysis, and comparison. In this paper, we present MedVLThinker, a suite of simple yet strong baselines. Our fully open recipe consists of: (1) systematic data curation for both text-only and image-text medical data, filtered according to varying levels of reasoning difficulty, and (2) two training paradigms: Supervised Fine-Tuning (SFT) on distilled reasoning traces and Reinforcement Learning with Verifiable Rewards (RLVR) based on final answer correctness. Across extensive experiments on the Qwen2.5-VL model family (3B, 7B) and six medical QA benchmarks, we find that RLVR consistently and significantly outperforms SFT. Additionally, under the RLVR framework, a key, counter-intuitive finding is that training on our curated text-only reasoning data provides a more substantial performance boost than training on multimodal image-text data. Our best open 7B model, trained using the RLVR recipe on text-only data, establishes a new state-of-the-art on existing public VQA benchmarks, surpassing all previous open-source medical LMMs. Furthermore, scaling our model to 32B achieves performance on par with the proprietary GPT-4o. We release all curated data, models, and code to provide the community with a strong, open foundation for future research in multimodal medical reasoning.

comment: Project page: https://ucsc-vlaa.github.io/MedVLThinker/ ; Code: https://github.com/UCSC-VLAA/MedVLThinker ; Model and Data: https://huggingface.co/collections/UCSC-VLAA/medvlthinker-688f52224fb7ff7d965d581d

♻ ☆ Robotic Ultrasound-Guided Femoral Artery Reconstruction of Anatomically-Representative Phantoms

Lidia Al-Zogbi, Deepak Raina, Vinciya Pandian, Thorsten Fleiter, Axel Krieger

Femoral artery access is essential for numerous clinical procedures, including diagnostic angiography, therapeutic catheterization, and emergency interventions. Despite its critical role, successful vascular access remains challenging due to anatomical variability, overlying adipose tissue, and the need for precise ultrasound (US) guidance. Needle placement errors can result in severe complications, thereby limiting the procedure to highly skilled clinicians operating in controlled hospital environments. While robotic systems have shown promise in addressing these challenges through autonomous scanning and vessel reconstruction, clinical translation remains limited due to reliance on simplified phantom models that fail to capture human anatomical complexity. In this work, we present a method for autonomous robotic US scanning of bifurcated femoral arteries, and validate it on five vascular phantoms created from real patient computed tomography (CT) data. Additionally, we introduce a video-based deep learning US segmentation network tailored for vascular imaging, enabling improved 3D arterial reconstruction. The proposed network achieves a Dice score of 89.21% and an Intersection over Union of 80.54% on a new vascular dataset. The reconstructed artery centerline is evaluated against ground truth CT data, showing an average L2 error of 0.91+/-0.70 mm, with an average Hausdorff distance of 4.36+/-1.11mm. This study is the first to validate an autonomous robotic system for US scanning of the femoral artery on a diverse set of patient-specific phantoms, introducing a more advanced framework for evaluating robotic performance in vascular imaging and intervention.

♻ ☆ TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuning

Junzhe Xu, Yuyang Yin, Xi Chen

This paper introduces TBAC-UniImage, a novel unified model for multimodal understanding and generation. We achieve this by deeply integrating a pre-trained Diffusion Model, acting as a generative ladder, with a Multimodal Large Language Model (MLLM). Previous diffusion-based unified models face two primary limitations. One approach uses only the MLLM's final hidden state as the generative condition. This creates a shallow connection, as the generator is isolated from the rich, hierarchical representations within the MLLM's intermediate layers. The other approach, pretraining a unified generative architecture from scratch, is computationally expensive and prohibitive for many researchers. To overcome these issues, our work explores a new paradigm. Instead of relying on a single output, we use representations from multiple, diverse layers of the MLLM as generative conditions for the diffusion model. This method treats the pre-trained generator as a ladder, receiving guidance from various depths of the MLLM's understanding process. Consequently, TBAC-UniImage achieves a much deeper and more fine-grained unification of understanding and generation.

♻ ☆ MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Dataset

Jianxiong Gao, Yanwei Fu, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng

Reconstructing 3D visuals from functional Magnetic Resonance Imaging (fMRI) data, introduced as Recon3DMind, is of significant interest to both cognitive neuroscience and computer vision. To advance this task, we present the fMRI-3D dataset, which includes data from 15 participants and showcases a total of 4,768 3D objects. The dataset consists of two components: fMRI-Shape, previously introduced and available at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Shape, and fMRI-Objaverse, proposed in this paper and available at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Objaverse. fMRI-Objaverse includes data from 5 subjects, 4 of whom are also part of the core set in fMRI-Shape. Each subject views 3,142 3D objects across 117 categories, all accompanied by text captions. This significantly enhances the diversity and potential applications of the dataset. Moreover, we propose MinD-3D++, a novel framework for decoding textured 3D visual information from fMRI signals. The framework evaluates the feasibility of not only reconstructing 3D objects from the human mind but also generating, for the first time, 3D textured meshes with detailed textures from fMRI data. We establish new benchmarks by designing metrics at the semantic, structural, and textured levels to evaluate model performance. Furthermore, we assess the model's effectiveness in out-of-distribution settings and analyze the attribution of the proposed 3D pari fMRI dataset in visual regions of interest (ROIs) in fMRI signals. Our experiments demonstrate that MinD-3D++ not only reconstructs 3D objects with high semantic and spatial accuracy but also provides deeper insights into how the human brain processes 3D visual information. Project page: https://jianxgao.github.io/MinD-3D.

comment: Accepted to TPAMI 2025

♻ ☆ GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo

Vibhas K. Vats, Sripad Joshi, David J. Crandall, Md. Alimoor Reza, Soon-heung Jung

Traditional multi-view stereo (MVS) methods rely heavily on photometric and geometric consistency constraints, but newer machine learning-based MVS methods check geometric consistency across multiple source views only as a post-processing step. In this paper, we present a novel approach that explicitly encourages geometric consistency of reference view depth maps across multiple source views at different scales during learning (see Fig. 1). We find that adding this geometric consistency loss significantly accelerates learning by explicitly penalizing geometrically inconsistent pixels, reducing the training iteration requirements to nearly half that of other MVS methods. Our extensive experiments show that our approach achieves a new state-of-the-art on the DTU and BlendedMVS datasets, and competitive results on the Tanks and Temples benchmark. To the best of our knowledge, GC-MVSNet is the first attempt to enforce multi-view, multi-scale geometric consistency during learning.

comment: Accepted in WACV 2024 Link: https://openaccess.thecvf.com/content/WACV2024/html/Vats_GC-MVSNet_Multi-View_Multi-Scale_Geometrically-Consistent_Multi-View_Stereo_WACV_2024_paper.html

♻ ☆ OpenCUA: Open Foundations for Computer-Use Agents

Xinyuan Wang, Bowen Wang, Dunjie Lu, Junlin Yang, Tianbao Xie, Junli Wang, Jiaqi Deng, Xiaole Guo, Yiheng Xu, Chen Henry Wu, Zhennan Shen, Zhuokai Li, Ryan Li, Xiaochuan Li, Junda Chen, Boyuan Zheng, Peihang Li, Fangyu Lei, Ruisheng Cao, Yeqiao Fu, Dongchan Shin, Martin Shin, Jiarui Hu, Yuyan Wang, Jixuan Chen, Yuxiao Ye, Danyang Zhang, Dikang Du, Hao Hu, Huarong Chen, Zaida Zhou, Haotian Yao, Ziwei Chen, Qizheng Gu, Yipu Wang, Heng Wang, Diyi Yang, Victor Zhong, Flood Sung, Y. Charles, Zhilin Yang, Tao Yu

Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain closed. As these agents will increasingly mediate digital interactions and execute consequential decisions on our behalf, the research community needs access to open CUA frameworks to study their capabilities, limitations, and risks. To bridge this gap, we propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models. Our framework consists of: (1) an annotation infrastructure that seamlessly captures human computer-use demonstrations; (2) AgentNet, the first large-scale computer-use task dataset spanning 3 operating systems and 200+ applications and websites; (3) a scalable pipeline that transforms demonstrations into state-action pairs with reflective long Chain-of-Thought reasoning that sustain robust performance gains as data scales. Our end-to-end agent models demonstrate strong performance across CUA benchmarks. In particular, OpenCUA-32B achieves an average success rate of 34.8% on OSWorld-Verified, establishing a new state-of-the-art (SOTA) among open-source models and surpassing OpenAI CUA (GPT-4o). Further analysis confirms that our approach generalizes well across domains and benefits significantly from increased test-time computation. We release our annotation tool, datasets, code, and models to build open foundations for further CUA research.

comment: Updata author list, modify first page format, correct typos

♻ ☆ Quantum-Brain: Quantum-Inspired Neural Network Approach to Vision-Brain Understanding

Hoang-Quan Nguyen, Xuan-Bac Nguyen, Hugh Churchill, Arabinda Kumar Choudhary, Pawan Sinha, Samee U. Khan, Khoa Luu

Vision-brain understanding aims to extract semantic information about brain signals from human perceptions. Existing deep learning methods for vision-brain understanding are usually introduced in a traditional learning paradigm missing the ability to learn the connectivities between brain regions. Meanwhile, the quantum computing theory offers a new paradigm for designing deep learning models. Motivated by the connectivities in the brain signals and the entanglement properties in quantum computing, we propose a novel Quantum-Brain approach, a quantum-inspired neural network, to tackle the vision-brain understanding problem. To compute the connectivity between areas in brain signals, we introduce a new Quantum-Inspired Voxel-Controlling module to learn the impact of a brain voxel on others represented in the Hilbert space. To effectively learn connectivity, a novel Phase-Shifting module is presented to calibrate the value of the brain signals. Finally, we introduce a new Measurement-like Projection module to present the connectivity information from the Hilbert space into the feature space. The proposed approach can learn to find the connectivities between fMRI voxels and enhance the semantic information obtained from human perceptions. Our experimental results on the Natural Scene Dataset benchmarks illustrate the effectiveness of the proposed method with Top-1 accuracies of 95.1% and 95.6% on image and brain retrieval tasks and an Inception score of 95.3% on fMRI-to-image reconstruction task. Our proposed quantum-inspired network brings a potential paradigm to solving the vision-brain problems via the quantum computing theory.

♻ ☆ Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images

Solène Debuysère, Nicolas Trouvé, Nathan Letheule, Olivier Lévêque, Elise Colin

We present a framework for adapting a large pretrained latent diffusion model to high-resolution Synthetic Aperture Radar (SAR) image generation. The approach enables controllable synthesis and the creation of rare or out-of-distribution scenes beyond the training set. Rather than training a task-specific small model from scratch, we adapt an open-source text-to-image foundation model to the SAR modality, using its semantic prior to align prompts with SAR imaging physics (side-looking geometry, slant-range projection, and coherent speckle with heavy-tailed statistics). Using a 100k-image SAR dataset, we compare full fine-tuning and parameter-efficient Low-Rank Adaptation (LoRA) across the UNet diffusion backbone, the Variational Autoencoder (VAE), and the text encoders. Evaluation combines (i) statistical distances to real SAR amplitude distributions, (ii) textural similarity via Gray-Level Co-occurrence Matrix (GLCM) descriptors, and (iii) semantic alignment using a SAR-specialized CLIP model. Our results show that a hybrid strategy-full UNet tuning with LoRA on the text encoders and a learned token embedding-best preserves SAR geometry and texture while maintaining prompt fidelity. The framework supports text-based control and multimodal conditioning (e.g., segmentation maps, TerraSAR-X, or optical guidance), opening new paths for large-scale SAR scene data augmentation and unseen scenario simulation in Earth observation.

♻ ☆ From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts

Yuji Wang, Moran Li, Xiaobin Hu, Ran Yi, Jiangning Zhang, Chengming Xu, Weijian Cao, Yabiao Wang, Chengjie Wang, Lizhuang Ma

Current video generation models struggle with identity preservation under large facial angles, primarily facing two challenges: the difficulty in exploring an effective mechanism to integrate identity features into DiT structure, and the lack of targeted coverage of large facial angles in existing open-source video datasets. To address these, we present two key innovations. First, we introduce a Mixture of Facial Experts (MoFE) that dynamically combines complementary cues from three specialized experts, each designed to capture distinct but mutually reinforcing aspects of facial attributes. The identity expert captures cross-pose identity-sensitive features, the semantic expert extracts high-level visual semantxics, and the detail expert preserves pixel-level features (e.g., skin texture, color gradients). Furthermore, to mitigate dataset limitations, we have tailored a data processing pipeline centered on two key aspects: Face Constraints and Identity Consistency. Face Constraints ensure facial angle diversity and a high proportion of facial regions, while Identity Consistency preserves coherent person-specific features across temporal sequences, collectively addressing the scarcity of large facial angles and identity-stable training data in existing datasets. Leveraging this pipeline, we have curated and refined a Large Face Angles (LFA) Dataset from existing open-source human video datasets, comprising 460K video clips with annotated facial angles. Experimental results on the LFA benchmark demonstrate that our method, empowered by the LFA dataset, significantly outperforms prior SOTA methods in face similarity, face FID, and CLIP semantic alignment. The code and dataset will be made publicly available at https://github.com/rain152/LFA-Video-Generation.

♻ ☆ UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

Yuping Wang, Xiangyu Huang, Xiaokang Sun, Mingxuan Yan, Shuo Xing, Zhengzhong Tu, Jiachen Li

We introduce UniOcc, a comprehensive, unified benchmark and toolkit for occupancy forecasting (i.e., predicting future occupancies based on historical information) and occupancy prediction (i.e., predicting current-frame occupancy from camera images. UniOcc unifies the data from multiple real-world datasets (i.e., nuScenes, Waymo) and high-fidelity driving simulators (i.e., CARLA, OpenCOOD), providing 2D/3D occupancy labels and annotating innovative per-voxel flows. Unlike existing studies that rely on suboptimal pseudo labels for evaluation, UniOcc incorporates novel evaluation metrics that do not depend on ground-truth labels, enabling robust assessment on additional aspects of occupancy quality. Through extensive experiments on state-of-the-art models, we demonstrate that large-scale, diverse training data and explicit flow information significantly enhance occupancy prediction and forecasting performance. Our data and code are available at https://uniocc.github.io/.

comment: IEEE/CVF International Conference on Computer Vision (ICCV 2025); Project website: https://uniocc.github.io/

♻ ☆ Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition ACM MM 2025

Jihao Gu, Kun Li, Fei Wang, Yanyan Wei, Zhiliang Wu, Hehe Fan, Meng Wang

Micro-Actions (MAs) are an important form of non-verbal communication in social interactions, with potential applications in human emotional analysis. However, existing methods in Micro-Action Recognition often overlook the inherent subtle changes in MAs, which limits the accuracy of distinguishing MAs with subtle changes. To address this issue, we present a novel Motion-guided Modulation Network (MMN) that implicitly captures and modulates subtle motion cues to enhance spatial-temporal representation learning. Specifically, we introduce a Motion-guided Skeletal Modulation module (MSM) to inject motion cues at the skeletal level, acting as a control signal to guide spatial representation modeling. In parallel, we design a Motion-guided Temporal Modulation module (MTM) to incorporate motion information at the frame level, facilitating the modeling of holistic motion patterns in micro-actions. Finally, we propose a motion consistency learning strategy to aggregate the motion cues from multi-scale features for micro-action classification. Experimental results on the Micro-Action 52 and iMiGUE datasets demonstrate that MMN achieves state-of-the-art performance in skeleton-based micro-action recognition, underscoring the importance of explicitly modeling subtle motion cues. The code will be available at https://github.com/momiji-bit/MMN.

comment: Accepted by ACM MM 2025

♻ ☆ Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation ACM MM2025

Chao Yin, Hao Li, Kequan Yang, Jide Li, Pinpin Zhu, Xiaoqiang Li

While promptable segmentation (\textit{e.g.}, SAM) has shown promise for various segmentation tasks, it still requires manual visual prompts for each object to be segmented. In contrast, task-generic promptable segmentation aims to reduce the need for such detailed prompts by employing only a task-generic prompt to guide segmentation across all test samples. However, when applied to Camouflaged Object Segmentation (COS), current methods still face two critical issues: 1) \textit{\textbf{semantic ambiguity in getting instance-specific text prompts}}, which arises from insufficient discriminative cues in holistic captions, leading to foreground-background confusion; 2) \textit{\textbf{semantic discrepancy combined with spatial separation in getting instance-specific visual prompts}}, which results from global background sampling far from object boundaries with low feature correlation, causing SAM to segment irrelevant regions. To address the issues above, we propose \textbf{RDVP-MSD}, a novel training-free test-time adaptation framework that synergizes \textbf{R}egion-constrained \textbf{D}ual-stream \textbf{V}isual \textbf{P}rompting (RDVP) via \textbf{M}ultimodal \textbf{S}tepwise \textbf{D}ecomposition Chain of Thought (MSD-CoT). MSD-CoT progressively disentangles image captions to eliminate semantic ambiguity, while RDVP injects spatial constraints into visual prompting and independently samples visual prompts for foreground and background points, effectively mitigating semantic discrepancy and spatial separation. Without requiring any training or supervision, RDVP-MSD achieves a state-of-the-art segmentation result on multiple COS benchmarks and delivers a faster inference speed than previous methods, demonstrating significantly improved accuracy and efficiency. The codes will be available at \href{https://github.com/ycyinchao/RDVP-MSD}{https://github.com/ycyinchao/RDVP-MSD}

comment: accepted by ACM MM2025

♻ ☆ IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection

Yanhui Li, Yunkang Cao, Chengliang Liu, Yuan Xiong, Xinghui Dong, Chao Huang

Industrial anomaly detection is a critical component of modern manufacturing, yet the scarcity of defective samples restricts traditional detection methods to scenario-specific applications. Although Vision-Language Models (VLMs) demonstrate significant advantages in generalization capabilities, their performance in industrial anomaly detection remains limited. To address this challenge, we propose IAD-R1, a universal post-training framework applicable to VLMs of different architectures and parameter scales, which substantially enhances their anomaly detection capabilities. IAD-R1 employs a two-stage training strategy: the Perception Activation Supervised Fine-Tuning (PA-SFT) stage utilizes a meticulously constructed high-quality Chain-of-Thought dataset (Expert-AD) for training, enhancing anomaly perception capabilities and establishing reasoning-to-answer correlations; the Structured Control Group Relative Policy Optimization (SC-GRPO) stage employs carefully designed reward functions to achieve a capability leap from "Anomaly Perception" to "Anomaly Interpretation". Experimental results demonstrate that IAD-R1 achieves significant improvements across 7 VLMs, the largest improvement was on the DAGM dataset, with average accuracy 43.3% higher than the 0.5B baseline. Notably, the 0.5B parameter model trained with IAD-R1 surpasses commercial models including GPT-4.1 and Claude-Sonnet-4 in zero-shot settings, demonstrating the effectiveness and superiority of IAD-R1. The dataset, code, and all model weights will be publicly available at https://github.com/Yanhui-Lee/IAD-R1.

♻ ☆ Preacher: Paper-to-Video Agentic System

Jingwei Liu, Ling Yang, Hao Luo, Fan Wang, Hongyan Li, Mengdi Wang

♻ ☆ Deblurring in the Wild: A Real-World Dataset from Smartphone High-Speed Videos

Mahdi Mohd Hossain Noki, Syed Mumtahin Mahmud, Prothito Shovon Majumder, Abdul Mohaimen Al Radi, Sudipto Das Sukanto, Afia Lubaina, Md. Mosaddek Khan

We introduce the largest real-world image deblurring dataset constructed from smartphone slow-motion videos. Using 240 frames captured over one second, we simulate realistic long-exposure blur by averaging frames to produce blurry images, while using the temporally centered frame as the sharp reference. Our dataset contains over 42,000 high-resolution blur-sharp image pairs, making it approximately 10 times larger than widely used datasets, with 8 times the amount of different scenes, including indoor and outdoor environments, with varying object and camera motions. We benchmark multiple state-of-the-art (SOTA) deblurring models on our dataset and observe significant performance degradation, highlighting the complexity and diversity of our benchmark. Our dataset serves as a challenging new benchmark to facilitate robust and generalizable deblurring models.

comment: 8 pages (without references), 3 figures. Dataset https://huggingface.co/datasets/masterda/SloMoBlur

♻ ☆ GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

♻ ☆ Reinforcement Learning in Vision: A Survey

Weijia Wu, Chen Gao, Joya Chen, Kevin Qinghong Lin, Qingwei Meng, Yiming Zhang, Yuke Qiu, Hong Zhou, Mike Zheng Shou

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and up-to-date synthesis of the field. We first formalize visual RL problems and trace the evolution of policy-optimization strategies from RLHF to verifiable reward paradigms, and from Proximal Policy Optimization to Group Relative Policy Optimization. We then organize more than 200 representative works into four thematic pillars: multi-modal large language models, visual generation, unified model frameworks, and vision-language-action models. For each pillar we examine algorithmic design, reward engineering, benchmark progress, and we distill trends such as curriculum-driven training, preference-aligned diffusion, and unified reward modeling. Finally, we review evaluation protocols spanning set-level fidelity, sample-level preference, and state-level stability, and we identify open challenges that include sample efficiency, generalization, and safe deployment. Our goal is to provide researchers and practitioners with a coherent map of the rapidly expanding landscape of visual RL and to highlight promising directions for future inquiry. Resources are available at: https://github.com/weijiawu/Awesome-Visual-Reinforcement-Learning.

comment: 22 pages

♻ ☆ Iterative Volume Fusion for Asymmetric Stereo Matching

Yuanting Gao, Linghao Shen

Stereo matching is vital in 3D computer vision, with most algorithms assuming symmetric visual properties between binocular visions. However, the rise of asymmetric multi-camera systems (e.g., tele-wide cameras) challenges this assumption and complicates stereo matching. Visual asymmetry disrupts stereo matching by affecting the crucial cost volume computation. To address this, we explore the matching cost distribution of two established cost volume construction methods in asymmetric stereo. We find that each cost volume experiences distinct information distortion, indicating that both should be comprehensively utilized to solve the issue. Based on this, we propose the two-phase Iterative Volume Fusion network for Asymmetric Stereo matching (IVF-AStereo). Initially, the aggregated concatenation volume refines the correlation volume. Subsequently, both volumes are fused to enhance fine details. Our method excels in asymmetric scenarios and shows robust performance against significant visual asymmetry. Extensive comparative experiments on benchmark datasets, along with ablation studies, confirm the effectiveness of our approach in asymmetric stereo with resolution and color degradation.

comment: Accepted to ICRA 2025

♻ ☆ DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction

Ben Kaye, Tomas Jakab, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi

The choice of data representation is a key factor in the success of deep learning in geometric tasks. For instance, DUSt3R recently introduced the concept of viewpoint-invariant point maps, generalizing depth prediction and showing that all key problems in the 3D reconstruction of static scenes can be reduced to predicting such point maps. In this paper, we develop an analogous concept for a very different problem: the reconstruction of the 3D shape and pose of deformable objects. To this end, we introduce Dual Point Maps (DualPM), where a pair of point maps is extracted from the same image-one associating pixels to their 3D locations on the object and the other to a canonical version of the object in its rest pose. We also extend point maps to amodal reconstruction to recover the complete shape of the object, even through self-occlusions. We show that 3D reconstruction and 3D pose estimation can be reduced to the prediction of DualPMs. Empirically, we demonstrate that this representation is a suitable target for deep networks to predict. Specifically, we focus on modeling quadrupeds, showing that DualPMs can be trained purely on synthetic 3D data, consisting of one or two models per category, while generalizing effectively to real images. With this approach, we achieve significant improvements over previous methods for the 3D analysis and reconstruction of such objects.

comment: First two authors contributed equally. CVPR 2025 highlight. Project page: https://dualpm.github.io

♻ ☆ Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method

Masoumeh Sharafi, Soufiane Belharbi, Houssem Ben Salem, Ali Etemad, Alessandro Lameiras Koerich, Marco Pedersoli, Simon Bacon, Eric Granger

Facial expression recognition (FER) models are employed in many video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, deep FER models often struggle with subtle expressions and high inter-subject variability, limiting their performance in real-world applications. To improve their performance, source-free domain adaptation (SFDA) methods have been proposed to personalize a pretrained source model using only unlabeled target domain data, thereby avoiding data privacy, storage, and transmission constraints. This paper addresses a challenging scenario where source data is unavailable for adaptation, and only unlabeled target data consisting solely of neutral expressions is available. SFDA methods are not typically designed to adapt using target data from only a single class. Further, using models to generate facial images with non-neutral expressions can be unstable and computationally intensive. In this paper, personalized feature translation (PFT) is proposed for SFDA. Unlike current image translation methods for SFDA, our lightweight method operates in the latent space. We first pre-train the translator on the source domain data to transform the subject-specific style features from one source subject into another. Expression information is preserved by optimizing a combination of expression consistency and style-aware objectives. Then, the translator is adapted on neutral target data, without using source data or image synthesis. By translating in the latent space, PFT avoids the complexity and noise of face expression generation, producing discriminative embeddings optimized for classification. Using PFT eliminates the need for image synthesis, reduces computational overhead (using a lightweight translator), and only adapts part of the model, making the method efficient compared to image-based translation.

♻ ☆ VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

Runjia Li, Philip Torr, Andrea Vedaldi, Tomas Jakab

We propose a novel memory module for building video generators capable of interactively exploring environments. Previous approaches have achieved similar results either by out-painting 2D views of a scene while incrementally reconstructing its 3D geometry-which quickly accumulates errors-or by using video generators with a short context window, which struggle to maintain scene coherence over the long term. To address these limitations, we introduce Surfel-Indexed View Memory (VMem), a memory module that remembers past views by indexing them geometrically based on the 3D surface elements (surfels) they have observed. VMem enables efficient retrieval of the most relevant past views when generating new ones. By focusing only on these relevant views, our method produces consistent explorations of imagined environments at a fraction of the computational cost required to use all past views as context. We evaluate our approach on challenging long-term scene synthesis benchmarks and demonstrate superior performance compared to existing methods in maintaining scene coherence and camera control.

comment: ICCV 2025 highlight. Project page: https://v-mem.github.io

♻ ☆ Evaluation of Cultural Competence of Vision-Language Models

Srishti Yadav, Lauren Tilton, Maria Antoniak, Taylor Arnold, Jiaang Li, Siddhesh Milind Pawar, Antonia Karamolegkou, Stella Frank, Zhaochong An, Negar Rostamzadeh, Daniel Hershcovich, Serge Belongie, Ekaterina Shutova

Modern vision-language models (VLMs) often fail at cultural competency evaluations and benchmarks. Given the diversity of applications built upon VLMs, there is renewed interest in understanding how they encode cultural nuances. While individual aspects of this problem have been studied, we still lack a comprehensive framework for systematically identifying and annotating the nuanced cultural dimensions present in images for VLMs. This position paper argues that foundational methodologies from visual culture studies (cultural studies, semiotics, and visual studies) are necessary for cultural analysis of images. Building upon this review, we propose a set of five frameworks, corresponding to cultural dimensions, that must be considered for a more complete analysis of the cultural competencies of VLMs.

♻ ☆ Vision Transformers in Precision Agriculture: A Comprehensive Survey

Saber Mehdipour, Seyed Abolghasem Mirroshandel, Seyed Amirhossein Tabatabaei

Detecting plant diseases is a crucial aspect of modern agriculture, as it plays a key role in maintaining crop health and increasing overall yield. Traditional approaches, though still valuable, often rely on manual inspection or conventional machine learning techniques, both of which face limitations in scalability and accuracy. Recently, Vision Transformers (ViTs) have emerged as a promising alternative, offering advantages such as improved handling of long-range dependencies and better scalability for visual tasks. This review explores the application of ViTs in precision agriculture, covering a range of tasks. We begin by introducing the foundational architecture of ViTs and discussing their transition from Natural Language Processing (NLP) to Computer Vision. The discussion includes the concept of inductive bias in traditional models like Convolutional Neural Networks (CNNs), and how ViTs mitigate these biases. We provide a comprehensive review of recent literature, focusing on key methodologies, datasets, and performance metrics. This study also includes a comparative analysis of CNNs and ViTs, along with a review of hybrid models and performance enhancements. Technical challenges such as data requirements, computational demands, and model interpretability are addressed, along with potential solutions. Finally, we outline future research directions and technological advancements that could further support the integration of ViTs in real-world agricultural settings. Our goal with this study is to offer practitioners and researchers a deeper understanding of how ViTs are poised to transform smart and precision agriculture.

♻ ☆ Unifying Self-Supervised Clustering and Energy-Based Models

Emanuele Sansone, Robin Manhaeve

Self-supervised learning excels at learning representations from large amounts of data. At the same time, generative models offer the complementary property of learning information about the underlying data generation process. In this study, we aim at establishing a principled connection between these two paradigms and highlight the benefits of their complementarity. In particular, we perform an analysis of self-supervised learning objectives, elucidating the underlying probabilistic graphical models and presenting a standardized methodology for their derivation from first principles. The analysis suggests a natural means of integrating self-supervised learning with likelihood-based generative models. We instantiate this concept within the realm of cluster-based self-supervised learning and energy models, introducing a lower bound proven to reliably penalize the most important failure modes and unlocking full unification. Our theoretical findings are substantiated through experiments on synthetic and real-world data, including SVHN, CIFAR10, and CIFAR100, demonstrating that our objective function allows to jointly train a backbone network in a discriminative and generative fashion, consequently outperforming existing self-supervised learning strategies in terms of clustering, generation and out-of-distribution detection performance by a wide margin. We also demonstrate that the solution can be integrated into a neuro-symbolic framework to tackle a simple yet non-trivial instantiation of the symbol grounding problem. The code is publicly available at https://github.com/emsansone/GEDI.

comment: Changes from previous version: change introductions and added acknowledgments. Integral version of workshop paper arXiv:2309.15420. Improved GEDI version (from two stages to single stage training) arxiv:2212.13425 - ACCEPTED TO TMLR 2025

♻ ☆ TD3Net: A temporal densely connected multi-dilated convolutional network for lipreading

Byung Hoon Lee, Wooseok Shin, Sung Won Han

The word-level lipreading approach typically employs a two-stage framework with separate frontend and backend architectures to model dynamic lip movements. Each component has been extensively studied, and in the backend architecture, temporal convolutional networks (TCNs) have been widely adopted in state-of-the-art methods. Recently, dense skip connections have been introduced in TCNs to mitigate the limited density of the receptive field, thereby improving the modeling of complex temporal representations. However, their performance remains constrained owing to potential information loss regarding the continuous nature of lip movements, caused by blind spots in the receptive field. To address this limitation, we propose TD3Net, a temporal densely connected multi-dilated convolutional network that combines dense skip connections and multi-dilated temporal convolutions as the backend architecture. TD3Net covers a wide and dense receptive field without blind spots by applying different dilation factors to skip-connected features. Experimental results on a word-level lipreading task using two large publicly available datasets, Lip Reading in the Wild (LRW) and LRW-1000, indicate that the proposed method achieves performance comparable to state-of-the-art methods. It achieved higher accuracy with fewer parameters and lower floating-point operations compared to existing TCN-based backend architectures. Moreover, visualization results suggest that our approach effectively utilizes diverse temporal features while preserving temporal continuity, presenting notable advantages in lipreading systems. The code is available at our GitHub repository (https://github.com/Leebh-kor/TD3Net).

comment: Accepted for publication in Journal of Visual Communication and Image Representation. DOI: https://doi.org/10.1016/j.jvcir.2025.104540

♻ ☆ Video-based automatic lameness detection of dairy cows using pose estimation and multiple locomotion traits

Helena Russello, Rik van der Tol, Menno Holzhauer, Eldert J. van Henten, Gert Kootstra

This study presents an automated lameness detection system that uses deep-learning image processing techniques to extract multiple locomotion traits associated with lameness. Using the T-LEAP pose estimation model, the motion of nine keypoints was extracted from videos of walking cows. The videos were recorded outdoors, with varying illumination conditions, and T-LEAP extracted 99.6% of correct keypoints. The trajectories of the keypoints were then used to compute six locomotion traits: back posture measurement, head bobbing, tracking distance, stride length, stance duration, and swing duration. The three most important traits were back posture measurement, head bobbing, and tracking distance. For the ground truth, we showed that a thoughtful merging of the scores of the observers could improve intra-observer reliability and agreement. We showed that including multiple locomotion traits improves the classification accuracy from 76.6% with only one trait to 79.9% with the three most important traits and to 80.1% with all six locomotion traits.

♻ ☆ INSIGHT: Explainable Weakly-Supervised Medical Image Analysis

Wenbo Zhang, Junyu Chen, Christopher Kanan

Due to their large sizes, volumetric scans and whole-slide pathology images (WSIs) are often processed by extracting embeddings from local regions and then an aggregator makes predictions from this set. However, current methods require post-hoc visualization techniques (e.g., Grad-CAM) and often fail to localize small yet clinically crucial details. To address these limitations, we introduce INSIGHT, a novel weakly-supervised aggregator that integrates heatmap generation as an inductive bias. Starting from pre-trained feature maps, INSIGHT employs a detection module with small convolutional kernels to capture fine details and a context module with a broader receptive field to suppress local false positives. The resulting internal heatmap highlights diagnostically relevant regions. On CT and WSI benchmarks, INSIGHT achieves state-of-the-art classification results and high weakly-labeled semantic segmentation performance. Project website and code are available at: https://zhangdylan83.github.io/ewsmia/

comment: Accepted at MLHC 2025 (Machine Learning for Healthcare)

♻ ☆ NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning

Zhixi Cai, Fucai Ke, Simindokht Jahangard, Maria Garcia de la Banda, Reza Haffari, Peter J. Stuckey, Hamid Rezatofighi

Visual Grounding (VG) tasks, such as referring expression detection and segmentation tasks are important for linking visual entities to context, especially in complex reasoning tasks that require detailed query interpretation. This paper explores VG beyond basic perception, highlighting challenges for methods that require reasoning like human cognition. Recent advances in large language methods (LLMs) and Vision-Language methods (VLMs) have improved abilities for visual comprehension, contextual understanding, and reasoning. These methods are mainly split into end-to-end and compositional methods, with the latter offering more flexibility. Compositional approaches that integrate LLMs and foundation models show promising performance but still struggle with complex reasoning with language-based logical representations. To address these limitations, we propose NAVER, a compositional visual grounding method that integrates explicit probabilistic logic reasoning within a finite-state automaton, equipped with a self-correcting mechanism. This design improves robustness and interpretability in inference through explicit logic reasoning. Our results show that NAVER achieves SoTA performance comparing to recent end-to-end and compositional baselines. The code is available at https://github.com/ControlNet/NAVER .

comment: ICCV 2025

♻ ☆ A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks

Hang Su, Yunlong Feng, Daniel Gehrig, Panfeng Jiang, Ling Gao, Xavier Lagorce, Laurent Kneip

Structure and continuous motion estimation from point correspondences is a fundamental problem in computer vision that has been powered by well-known algorithms such as the familiar 5-point or 8-point algorithm. However, despite their acclaim, these algorithms are limited to processing point correspondences originating from a pair of views each one representing an instantaneous capture of the scene. Yet, in the case of rolling shutter cameras, or more recently, event cameras, this synchronization breaks down. In this work, we present a unified approach for structure and linear motion estimation from 2D point correspondences with arbitrary timestamps, from an arbitrary set of views. By formulating the problem in terms of first-order dynamics and leveraging a constant velocity motion model, we derive a novel, linear point incidence relation allowing for the efficient recovery of both linear velocity and 3D points with predictable degeneracies and solution multiplicities. Owing to its general formulation, it can handle correspondences from a wide range of sensing modalities such as global shutter, rolling shutter, and event cameras, and can even combine correspondences from different collocated sensors. We validate the effectiveness of our solver on both simulated and real-world data, where we show consistent improvement across all modalities when compared to recent approaches. We believe our work opens the door to efficient structure and motion estimation from asynchronous data. Code can be found at https://github.com/suhang99/AsyncTrack-Motion-Solver.

♻ ☆ Debiasing Multimodal Large Language Models via Penalization of Language Priors

YiFan Zhang, Yang Shi, Weichen Yu, Qingsong Wen, Xue Wang, Wenjing Yang, Zhang Zhang, Liang Wang, Rong Jin

In the realms of computer vision and natural language processing, Multimodal Large Language Models (MLLMs) have become indispensable tools, proficient in generating textual responses based on visual inputs. Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image. Empirical experiments underscore the persistence of this bias, as MLLMs often provide confident answers even in the absence of relevant images or given incongruent visual inputs. To rectify these biases and redirect the model's focus toward visual information, we propose two simple, training-free strategies. First, for tasks such as classification or multi-choice question answering, we introduce a "Post-Hoc Debias" method using an affine calibration step to adjust the output distribution. This approach ensures uniform answer scores when the image is absent, acting as an effective regularization technique to alleviate the influence of LLM priors. For more intricate open-ended generation tasks, we extend this method to "Visual Debias Decoding", which mitigates bias by contrasting token log-probabilities conditioned on a correct image versus a meaningless one. Additionally, our investigation sheds light on the instability of MLLMs across various decoding configurations. Through systematic exploration of different settings, we achieve significant performance improvements--surpassing previously reported results--and raise concerns about the fairness of current evaluation practices. Comprehensive experiments substantiate the effectiveness of our proposed strategies in mitigating biases. These strategies not only prove beneficial in minimizing hallucinations but also contribute to the generation of more helpful and precise illustrations.

comment: 10 pages, 12 figures

♻ ☆ CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting

Lei Tian, Xiaomin Li, Liqian Ma, Hao Yin, Zirui Zheng, Hefei Huang, Taiqing Li, Huchuan Lu, Xu Jia

Recent advances in 3D reconstruction techniques and vision-language models have fueled significant progress in 3D semantic understanding, a capability critical to robotics, autonomous driving, and virtual/augmented reality. However, methods that rely on 2D priors are prone to a critical challenge: cross-view semantic inconsistencies induced by occlusion, image blur, and view-dependent variations. These inconsistencies, when propagated via projection supervision, deteriorate the quality of 3D Gaussian semantic fields and introduce artifacts in the rendered outputs. To mitigate this limitation, we propose CCL-LGS, a novel framework that enforces view-consistent semantic supervision by integrating multi-view semantic cues. Specifically, our approach first employs a zero-shot tracker to align a set of SAM-generated 2D masks and reliably identify their corresponding categories. Next, we utilize CLIP to extract robust semantic encodings across views. Finally, our Contrastive Codebook Learning (CCL) module distills discriminative semantic features by enforcing intra-class compactness and inter-class distinctiveness. In contrast to previous methods that directly apply CLIP to imperfect masks, our framework explicitly resolves semantic conflicts while preserving category discriminability. Extensive experiments demonstrate that CCL-LGS outperforms previous state-of-the-art methods. Our project page is available at https://epsilontl.github.io/CCL-LGS/.

comment: ICCV 2025

♻ ☆ Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection

Ayush K. Rai, Kyle Min, Tarun Krishna, Feiyan Hu, Alan F. Smeaton, Noel E. O'Connor

Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in such approaches lies in selecting an appropriate masking strategy. Previous studies have explored predefined masking techniques, including random and tube-based masking, as well as approaches that leverage key motion priors, optical flow and semantic cues from externally pre-trained models. In this work, we introduce a novel and generalizable Trajectory-Aware Adaptive Token Sampler (TATS), which models the motion dynamics of tokens and can be seamlessly integrated into the masked autoencoder (MAE) framework to select motion-centric tokens in videos. Additionally, we propose a unified training strategy that enables joint optimization of both MAE and TATS from scratch using Proximal Policy Optimization (PPO). We show that our model allows for aggressive masking without compromising performance on the downstream task of action recognition while also ensuring that the pre-training remains memory efficient. Extensive experiments of the proposed approach across four benchmarks, including Something-Something v2, Kinetics-400, UCF101, and HMDB51, demonstrate the effectiveness, transferability, generalization, and efficiency of our work compared to other state-of-the-art methods.

comment: Accepted in ICCVW 2025 - Long Multi-Scene Video Foundations Workshop

♻ ☆ Improved GUI Grounding via Iterative Narrowing

Anthony Nguyen

Graphical User Interface (GUI) grounding plays a crucial role in enhancing the capabilities of Vision-Language Model (VLM) agents. While general VLMs, such as GPT-4V, demonstrate strong performance across various tasks, their proficiency in GUI grounding remains suboptimal. Recent studies have focused on fine-tuning these models specifically for zero-shot GUI grounding, yielding significant improvements over baseline performance. We introduce a visual prompting framework that employs an iterative narrowing mechanism to further improve the performance of both general and fine-tuned models in GUI grounding. For evaluation, we tested our method on a comprehensive benchmark comprising various UI platforms and provided the code to reproduce our results.

comment: Code available at https://github.com/ant-8/GUI-Grounding-via-Iterative-Narrowing

♻ ☆ SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs

Bei Yan, Zhiyuan Chen, Yuecong Min, Jie Zhang, Jiahao Wang, Xiaozhen Wang, Shiguang Shan

Despite rapid advances, Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge, which correspond to faithfulness and factuality hallucinations, respectively. Prior studies primarily evaluate faithfulness hallucination at a rather coarse level (e.g., object-level) and lack fine-grained analysis. Additionally, existing benchmarks often rely on costly manual curation or reused public datasets, raising concerns about scalability and data leakage. To address these limitations, we propose an automated data construction pipeline that produces scalable, controllable, and diverse evaluation data. We also design a hierarchical hallucination induction framework with input perturbations to simulate realistic noisy scenarios. Integrating these designs, we construct SHALE, a Scalable HALlucination Evaluation benchmark designed to assess both faithfulness and factuality hallucinations via a fine-grained hallucination categorization scheme. SHALE comprises over 30K image-instruction pairs spanning 12 representative visual perception aspects for faithfulness and 6 knowledge domains for factuality, considering both clean and noisy scenarios. Extensive experiments on over 20 mainstream LVLMs reveal significant factuality hallucinations and high sensitivity to semantic perturbations.

♻ ☆ Tuning-Free Online Robust Principal Component Analysis through Implicit Regularization

Lakshmi Jayalal, Gokularam Muthukrishnan, Sheetal Kalyani

The performance of the standard Online Robust Principal Component Analysis (OR-PCA) technique depends on the optimum tuning of the explicit regularizers and this tuning is dataset sensitive. We aim to remove the dependency on these tuning parameters by using implicit regularization. We propose to use the implicit regularization effect of various modified gradient descents to make OR-PCA tuning free. Our method incorporates three different versions of modified gradient descent that separately but naturally encourage sparsity and low-rank structures in the data. The proposed method performs comparable or better than the tuned OR-PCA for both simulated and real-world datasets. Tuning-free ORPCA makes it more scalable for large datasets since we do not require dataset-dependent parameter tuning.

♻ ☆ Unifying Locality of KANs and Feature Drift Compensation Projection for Data-free Replay based Continual Face Forgery Detection

Tianshuo Zhang, Siran Peng, Li Gao, Haoyuan Zhang, Xiangyu Zhu, Zhen Lei

The rapid advancements in face forgery techniques necessitate that detectors continuously adapt to new forgery methods, thus situating face forgery detection within a continual learning paradigm. However, when detectors learn new forgery types, their performance on previous types often degrades rapidly, a phenomenon known as catastrophic forgetting. Kolmogorov-Arnold Networks (KANs) utilize locally plastic splines as their activation functions, enabling them to learn new tasks by modifying only local regions of the functions while leaving other areas unaffected. Therefore, they are naturally suitable for addressing catastrophic forgetting. However, KANs have two significant limitations: 1) the splines are ineffective for modeling high-dimensional images, while alternative activation functions that are suitable for images lack the essential property of locality; 2) in continual learning, when features from different domains overlap, the mapping of different domains to distinct curve regions always collapses due to repeated modifications of the same regions. In this paper, we propose a KAN-based Continual Face Forgery Detection (KAN-CFD) framework, which includes a Domain-Group KAN Detector (DG-KD) and a data-free replay Feature Separation strategy via KAN Drift Compensation Projection (FS-KDCP). DG-KD enables KANs to fit high-dimensional image inputs while preserving locality and local plasticity. FS-KDCP avoids the overlap of the KAN input spaces without using data from prior tasks. Experimental results demonstrate that the proposed method achieves superior performance while notably reducing forgetting.

♻ ☆ SIFThinker: Spatially-Aware Image Focus for Visual Reasoning

Zhangquan Chen, Ruihui Zhao, Chuwei Luo, Mingze Sun, Xinlei Yu, Yangyang Kang, Ruqi Huang

Current multimodal large language models (MLLMs) still face significant challenges in complex visual tasks (e.g., spatial understanding, fine-grained perception). Prior methods have tried to incorporate visual reasoning, however, they fail to leverage attention correction with spatial cues to iteratively refine their focus on prompt-relevant regions. In this paper, we introduce SIFThinker, a spatially-aware "think-with-images" framework that mimics human visual perception. Specifically, SIFThinker enables attention correcting and image region focusing by interleaving depth-enhanced bounding boxes and natural language. Our contributions are twofold: First, we introduce a reverse-expansion-forward-inference strategy that facilitates the generation of interleaved image-text chains of thought for process-level supervision, which in turn leads to the construction of the SIF-50K dataset. Besides, we propose GRPO-SIF, a reinforced training paradigm that integrates depth-informed visual grounding into a unified reasoning pipeline, teaching the model to dynamically correct and focus on prompt-relevant regions. Extensive experiments demonstrate that SIFThinker outperforms state-of-the-art methods in spatial understanding and fine-grained visual perception, while maintaining strong general capabilities, highlighting the effectiveness of our method. Code: https://github.com/zhangquanchen/SIFThinker.

comment: 15 pages, 13 figures

♻ ☆ Exploring the Application of Visual Question Answering (VQA) for Classroom Activity Monitoring

Sinh Trong Vu, Hieu Trung Pham, Dung Manh Nguyen, Hieu Minh Hoang, Nhu Hoang Le, Thu Ha Pham, Tai Tan Mai

Classroom behavior monitoring is a critical aspect of educational research, with significant implications for student engagement and learning outcomes. Recent advancements in Visual Question Answering (VQA) models offer promising tools for automatically analyzing complex classroom interactions from video recordings. In this paper, we investigate the applicability of several state-of-the-art open-source VQA models, including LLaMA2, LLaMA3, QWEN3, and NVILA, in the context of classroom behavior analysis. To facilitate rigorous evaluation, we introduce our BAV-Classroom-VQA dataset derived from real-world classroom video recordings at the Banking Academy of Vietnam. We present the methodology for data collection, annotation, and benchmark the performance of the selected VQA models on this dataset. Our initial experimental results demonstrate that all four models achieve promising performance levels in answering behavior-related visual questions, showcasing their potential in future classroom analytics and intervention systems.

♻ ☆ Yan: Foundational Interactive Video Generation

Deheng Ye, Fangyun Zhou, Jiacheng Lv, Jianqi Ma, Jun Zhang, Junyan Lv, Junyou Li, Minwen Deng, Mingyu Yang, Qiang Fu, Wei Yang, Wenkai Lv, Yangbin Yu, Yewen Wang, Yonghang Guan, Zhihao Hu, Zhongbin Fang, Zhongqian Sun

We present Yan, a foundational framework for interactive video generation, covering the entire pipeline from simulation and generation to editing. Specifically, Yan comprises three core modules. AAA-level Simulation: We design a highly-compressed, low-latency 3D-VAE coupled with a KV-cache-based shift-window denoising inference process, achieving real-time 1080P/60FPS interactive simulation. Multi-Modal Generation: We introduce a hierarchical autoregressive caption method that injects game-specific knowledge into open-domain multi-modal video diffusion models (VDMs), then transforming the VDM into a frame-wise, action-controllable, real-time infinite interactive video generator. Notably, when the textual and visual prompts are sourced from different domains, the model demonstrates strong generalization, allowing it to blend and compose the style and mechanics across domains flexibly according to user prompts. Multi-Granularity Editing: We propose a hybrid model that explicitly disentangles interactive mechanics simulation from visual rendering, enabling multi-granularity video content editing during interaction through text. Collectively, Yan offers an integration of these modules, pushing interactive video generation beyond isolated capabilities toward a comprehensive AI-driven interactive creation paradigm, paving the way for the next generation of creative tools, media, and entertainment. The project page is: https://greatx3.github.io/Yan/.

♻ ☆ Bootstrapping, Autonomous Testing, and Initialization System for Si/SiGe Multi-quantum Dot Devices

Tyler J. Kovach, Daniel Schug, M. A. Wolfe, E. R. MacQuarrie, Patrick J. Walsh, Owen M. Eskandari, Jared Benson, Mark Friesen, M. A. Eriksson, Justyna P. Zwolak

Semiconductor quantum dot (QD) devices have become central to advancements in spin-based quantum computing. However, the increasing complexity of modern QD devices makes calibration and control -- particularly at elevated temperatures -- a bottleneck to progress, highlighting the need for robust and scalable autonomous solutions. A major hurdle arises from trapped charges within the oxide layers, which induce random offset voltage shifts on gate electrodes, with a standard deviation of approximately 83~\si{\milli\volt} of variation within state-of-the-art present-day devices. Efficient characterization and tuning of large arrays of QD qubits depend on choices of automated protocols. Here, we introduce a physically intuitive framework for a bootstrapping, autonomous testing, and initialization system (BATIS) designed to streamline QD device evaluation and calibration. BATIS navigates high-dimensional gate voltage spaces, automating essential steps such as leakage testing, formation of all current channels, and gate characterization in the presence of trapped charges. For forming the current channels, BATIS follows a non-standard approach that requires a single set of measurements regardless of the number of channels. Demonstrated at $1.3$~\si{\kelvin} on a quad-QD Si/Si$_x$Ge$_{1-x}$ device, BATIS eliminates the need for deep cryogenic environments during initial device diagnostics, significantly enhancing scalability and reducing setup times. By requiring only minimal prior knowledge of the device architecture, BATIS represents a platform-agnostic solution, adaptable to various QD systems, which bridges a critical gap in QD autotuning.

comment: 16 pages, 6 figures, 3 pages of supplemental material

♻ ☆ OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM

Jinhong Wang, Shuo Tong, Jian liu, Dongqi Tang, Weiqiang Wang, Wentong Li, Hongxia Xu, Danny Chen, Jintai Chen, Jian Wu

Despite the remarkable progress of multimodal large language models (MLLMs), they continue to face challenges in achieving competitive performance on ordinal regression (OR; a.k.a. ordinal classification). To address this issue, this paper presents OrderChain, a novel and general prompting paradigm that improves the ordinal understanding ability of MLLMs by specificity and commonality modeling. Specifically, our OrderChain consists of a set of task-aware prompts to facilitate the specificity modeling of diverse OR tasks and a new range optimization Chain-of-Thought (RO-CoT), which learns a commonality way of thinking about OR tasks by uniformly decomposing them into multiple small-range optimization subtasks. Further, we propose a category recursive division (CRD) method to generate instruction candidate category prompts to support RO-CoT automatic optimization. Comprehensive experiments show that LLaVA model with our OrderChain improves baseline LLaVA significantly on diverse OR datasets, e.g., from 47.5\% to 93.2\% accuracy on the Adience dataset for age estimation, and from 30.0\% to 85.7\% accuracy on the Diabetic Retinopathy dataset. Notably, LLaVA with our OrderChain also remarkably outperforms state-of-the-art methods by 27% on accuracy and 0.24 on MAE on the Adience dataset. To our best knowledge, our OrderChain is the first work that augments MLLMs for OR tasks, and the effectiveness is witnessed across a spectrum of OR datasets. Project Page: https://order-chain.github.io/.

comment: Accepted by ICCV 2025

♻ ☆ M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation

Kui Jiang, Shiyu Liu, Junjun Jiang, Hongxun Yao, Xiaopeng Fan

Audio-driven talking head generation holds significant potential for film production. While existing 3D methods have advanced motion modeling and content synthesis, they often produce rendering artifacts, such as motion blur, temporal jitter, and local penetration, due to limitations in representing stable, fine-grained motion fields. Through systematic analysis, we reformulate talking head generation into a unified framework comprising three steps: video preprocessing, motion representation, and rendering reconstruction. This framework underpins our proposed M2DAO-Talker, which addresses current limitations via multi-granular motion decoupling and alternating optimization. Specifically, we devise a novel 2D portrait preprocessing pipeline to extract frame-wise deformation control conditions (motion region segmentation masks, and camera parameters) to facilitate motion representation. To ameliorate motion modeling, we elaborate a multi-granular motion decoupling strategy, which independently models non-rigid (oral and facial) and rigid (head) motions for improved reconstruction accuracy. Meanwhile, a motion consistency constraint is developed to ensure head-torso kinematic consistency, thereby mitigating penetration artifacts caused by motion aliasing. In addition, an alternating optimization strategy is designed to iteratively refine facial and oral motion parameters, enabling more realistic video generation. Experiments across multiple datasets show that M2DAO-Talker achieves state-of-the-art performance, with the 2.43 dB PSNR improvement in generation quality and 0.64 gain in user-evaluated video realness versus TalkingGaussian while with 150 FPS inference speed. Our project homepage is https://m2dao-talker.github.io/M2DAO-Talk.github.io.

♻ ☆ TikZero: Zero-Shot Text-Guided Graphics Program Synthesis

Jonas Belouadi, Eddy Ilg, Margret Keuper, Hideki Tanaka, Masao Utiyama, Raj Dabre, Steffen Eger, Simone Paolo Ponzetto

Automatically synthesizing figures from text captions is a compelling capability. However, achieving high geometric precision and editability requires representing figures as graphics programs in languages like TikZ, and aligned training data (i.e., graphics programs with captions) remains scarce. Meanwhile, large amounts of unaligned graphics programs and captioned raster images are more readily available. We reconcile these disparate data sources by presenting TikZero, which decouples graphics program generation from text understanding by using image representations as an intermediary bridge. It enables independent training on graphics programs and captioned images and allows for zero-shot text-guided graphics program synthesis during inference. We show that our method substantially outperforms baselines that can only operate with caption-aligned graphics programs. Furthermore, when leveraging caption-aligned graphics programs as a complementary training signal, TikZero matches or exceeds the performance of much larger models, including commercial systems like GPT-4o. Our code, datasets, and select models are publicly available.

comment: Accepted at ICCV 2025 (highlight); Project page: https://github.com/potamides/DeTikZify

♻ ☆ A Lightweight Transformer with Phase-Only Cross-Attention for Illumination-Invariant Biometric Authentication

Arun K. Sharma, Shubhobrata Bhattacharya, Motahar Reza, Bishakh Bhattacharya

Traditional biometric systems have encountered significant setbacks due to various unavoidable factors, for example, wearing of face masks in face recognition-based biometrics and hygiene concerns in fingerprint-based biometrics. This paper proposes a novel lightweight vision transformer with phase-only cross-attention (POC-ViT) using dual biometric traits of forehead and periocular portions of the face, capable of performing well even with face masks and without any physical touch, offering a promising alternative to traditional methods. The POC-ViT framework is designed to handle two biometric traits and to capture inter-dependencies in terms of relative structural patterns. Each channel consists of a Cross-Attention using phase-only correlation (POC) that captures both their individual and correlated structural patterns. The computation of cross-attention using POC extracts the phase correlation in the spatial features. Therefore, it is robust against variations in resolution and intensity, as well as illumination changes in the input images. The lightweight model is suitable for edge device deployment. The performance of the proposed framework was successfully demonstrated using the Forehead Subcutaneous Vein Pattern and Periocular Biometric Pattern (FSVP-PBP) database, having 350 subjects. The POC-ViT framework outperformed state-of-the-art methods with an outstanding classification accuracy of $98.8\%$ with the dual biometric traits.

comment: Submitted to IEEE

♻ ☆ Semantic-aware DropSplat: Adaptive Pruning of Redundant Gaussians for 3D Aerial-View Segmentation

Xu Tang, Junan Jia, Yijing Wang, Jingjing Ma, Xiangrong Zhang

In the task of 3D Aerial-view Scene Semantic Segmentation (3D-AVS-SS), traditional methods struggle to address semantic ambiguity caused by scale variations and structural occlusions in aerial images. This limits their segmentation accuracy and consistency. To tackle these challenges, we propose a novel 3D-AVS-SS approach named SAD-Splat. Our method introduces a Gaussian point drop module, which integrates semantic confidence estimation with a learnable sparsity mechanism based on the Hard Concrete distribution. This module effectively eliminates redundant and semantically ambiguous Gaussian points, enhancing both segmentation performance and representation compactness. Furthermore, SAD-Splat incorporates a high-confidence pseudo-label generation pipeline. It leverages 2D foundation models to enhance supervision when ground-truth labels are limited, thereby further improving segmentation accuracy. To advance research in this domain, we introduce a challenging benchmark dataset: 3D Aerial Semantic (3D-AS), which encompasses diverse real-world aerial scenes with sparse annotations. Experimental results demonstrate that SAD-Splat achieves an excellent balance between segmentation accuracy and representation compactness. It offers an efficient and scalable solution for 3D aerial scene understanding.

comment: 9 pages, 4 figures

♻ ☆ Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation

Yuxuan Wang, Xuanyu Yi, Haohan Weng, Qingshan Xu, Xiaokang Wei, Xianghui Yang, Chunchao Guo, Long Chen, Hanwang Zhang

Triangle meshes are fundamental to 3D applications, enabling efficient modification and rasterization while maintaining compatibility with standard rendering pipelines. However, current automatic mesh generation methods typically rely on intermediate representations that lack the continuous surface quality inherent to meshes. Converting these representations into meshes produces dense, suboptimal outputs. Although recent autoregressive approaches demonstrate promise in directly modeling mesh vertices and faces, they are constrained by the limitation in face count, scalability, and structural fidelity. To address these challenges, we propose Nautilus, a locality-aware autoencoder for artist-like mesh generation that leverages the local properties of manifold meshes to achieve structural fidelity and efficient representation. Our approach introduces a novel tokenization algorithm that preserves face proximity relationships and compresses sequence length through locally shared vertices and edges, enabling the generation of meshes with an unprecedented scale of up to 5,000 faces. Furthermore, we develop a Dual-stream Point Conditioner that provides multi-scale geometric guidance, ensuring global consistency and local structural fidelity by capturing fine-grained geometric features. Extensive experiments demonstrate that Nautilus significantly outperforms state-of-the-art methods in both fidelity and scalability. The project page is at https://nautilusmeshgen.github.io.

comment: accepted to ICCV 2025

♻ ☆ A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality

Rongqian Chen, Allison Andreyev, Yanming Xiu, Mahdi Imani, Bin Li, Maria Gorlatova, Gang Tan, Tian Lan

Augmented Reality (AR) enriches perception by overlaying virtual elements on the physical world. Due to its growing popularity, cognitive attacks that alter AR content to manipulate users' semantic perception have received increasing attention. Existing detection methods often focus on visual changes, which are restricted to pixel- or image-level processing and lack semantic reasoning capabilities, or they rely on pre-trained vision-language models (VLMs), which function as black-box approaches with limited interpretability. In this paper, we present CADAR, a novel neurosymbolic approach for cognitive attack detection in AR. It fuses multimodal vision-language inputs using neural VLMs to obtain a symbolic perception-graph representation, incorporating prior knowledge, salience weighting, and temporal correlations. The model then enables particle-filter based statistical reasoning -- a sequential Monte Carlo method -- to detect cognitive attacks. Thus, CADAR inherits the adaptability of pre-trained VLM and the interpretability and reasoning rigor of particle filtering. Experiments on an extended AR cognitive attack dataset show accuracy improvements of up to 10.7% over strong baselines on challenging AR attack scenarios, underscoring the promise of neurosymbolic methods for effective and interpretable cognitive attack detection.

♻ ☆ MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding

Chang Liu, Ye Pan, Chenyang Ding, Susanto Rahardja, Xiaokang Yang

Audio-driven emotional 3D facial animation aims to generate synchronized lip movements and vivid facial expressions. However, most existing approaches focus on static and predefined emotion labels, limiting their diversity and naturalness. To address these challenges, we propose MEDTalk, a novel framework for fine-grained and dynamic emotional talking head generation. Our approach first disentangles content and emotion embedding spaces from motion sequences using a carefully designed cross-reconstruction process, enabling independent control over lip movements and facial expressions. Beyond conventional audio-driven lip synchronization, we integrate audio and speech text, predicting frame-wise intensity variations and dynamically adjusting static emotion features to generate realistic emotional expressions. Furthermore, to enhance control and personalization, we incorporate multimodal inputs-including text descriptions and reference expression images-to guide the generation of user-specified facial expressions. With MetaHuman as the priority, our generated results can be conveniently integrated into the industrial production pipeline. The code is available at: https://github.com/SJTU-Lucy/MEDTalk.

♻ ☆ MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching

Peng Xu, Zhiyu Xiang, Jingyun Fu, Tianyu Pu, Hanzhi Zhong, Eryun Liu

Despite the significant advances in domain generalized stereo matching, existing methods still exhibit domain-specific preferences when transferring from synthetic to real domains, hindering their practical applications in complex and diverse scenarios. The probability distributions predicted by the stereo network naturally encode rich similarity and uncertainty information. Inspired by this observation, we propose to extract these two types of dark knowledge from the pre-trained network to model intuitive multi-modal ground-truth distributions for both edge and non-edge regions. To mitigate the inherent domain preferences of a single network, we adopt network ensemble and further distinguish between objective and biased knowledge in the Laplace parameter space. Finally, the objective knowledge and the original disparity labels are jointly modeled as a mixture of Laplacians to provide fine-grained supervision for the stereo network training. Extensive experiments demonstrate that: (1) Our method is generic and effectively improves the generalization of existing networks. (2) PCWNet with our method achieves the state-of-the-art generalization performance on both KITTI 2015 and 2012 datasets. (3) Our method outperforms existing methods in comprehensive ranking across four popular real-world datasets.

♻ ☆ MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning

Quang-Trung Truong, Yuk-Kwan Wong, Vo Hoang Kim Tuyen Dang, Rinaldi Gotama, Duc Thanh Nguyen, Sai-Kit Yeung

Marine videos present significant challenges for video understanding due to the dynamics of marine objects and the surrounding environment, camera motion, and the complexity of underwater scenes. Existing video captioning datasets, typically focused on generic or human-centric domains, often fail to generalize to the complexities of the marine environment and gain insights about marine life. To address these limitations, we propose a two-stage marine object-oriented video captioning pipeline. We introduce a comprehensive video understanding benchmark that leverages the triplets of video, text, and segmentation masks to facilitate visual grounding and captioning, leading to improved marine video understanding and analysis, and marine video generation. Additionally, we highlight the effectiveness of video splitting in order to detect salient object transitions in scene changes, which significantly enrich the semantics of captioning content. Our dataset and code have been released at https://msc.hkustvgd.com.

comment: Published at ACMMM2025 (Dataset track)

♻ ☆ SOI is the Root of All Evil: Quantifying and Breaking Similar Object Interference in Single Object Tracking

Yipei Wang, Shiyu Hu, Shukun Jia, Panxi Xu, Hongfei Ma, Yiping Ma, Jing Zhang, Xiaobo Lu, Xin Zhao

In this paper, we present the first systematic investigation and quantification of Similar Object Interference (SOI), a long-overlooked yet critical bottleneck in Single Object Tracking (SOT). Through controlled Online Interference Masking (OIM) experiments, we quantitatively demonstrate that eliminating interference sources leads to substantial performance improvements (AUC gains up to 4.35) across all SOTA trackers, directly validating SOI as a primary constraint for robust tracking and highlighting the feasibility of external cognitive guidance. Building upon these insights, we adopt natural language as a practical form of external guidance, and construct SOIBench-the first semantic cognitive guidance benchmark specifically targeting SOI challenges. It automatically mines SOI frames through multi-tracker collective judgment and introduces a multi-level annotation protocol to generate precise semantic guidance texts. Systematic evaluation on SOIBench reveals a striking finding: existing vision-language tracking (VLT) methods fail to effectively exploit semantic cognitive guidance, achieving only marginal improvements or even performance degradation (AUC changes of -0.26 to +0.71). In contrast, we propose a novel paradigm employing large-scale vision-language models (VLM) as external cognitive engines that can be seamlessly integrated into arbitrary RGB trackers. This approach demonstrates substantial improvements under semantic cognitive guidance (AUC gains up to 0.93), representing a significant advancement over existing VLT methods. We hope SOIBench will serve as a standardized evaluation platform to advance semantic cognitive tracking research and contribute new insights to the tracking research community.

♻ ☆ Visual SLAMMOT Considering Multiple Motion Models

Peilin Tian, Hao Li

Simultaneous Localization and Mapping (SLAM) and Multi-Object Tracking (MOT) are pivotal tasks in the realm of autonomous driving, attracting considerable research attention. While SLAM endeavors to generate real-time maps and determine the vehicle's pose in unfamiliar settings, MOT focuses on the real-time identification and tracking of multiple dynamic objects. Despite their importance, the prevalent approach treats SLAM and MOT as independent modules within an autonomous vehicle system, leading to inherent limitations. Classical SLAM methodologies often rely on a static environment assumption, suitable for indoor rather than dynamic outdoor scenarios. Conversely, conventional MOT techniques typically rely on the vehicle's known state, constraining the accuracy of object state estimations based on this prior. To address these challenges, previous efforts introduced the unified SLAMMOT paradigm, yet primarily focused on simplistic motion patterns. In our team's previous work IMM-SLAMMOT\cite{IMM-SLAMMOT}, we present a novel methodology incorporating consideration of multiple motion models into SLAMMOT i.e. tightly coupled SLAM and MOT, demonstrating its efficacy in LiDAR-based systems. This paper studies feasibility and advantages of instantiating this methodology as visual SLAMMOT, bridging the gap between LiDAR and vision-based sensing mechanisms. Specifically, we propose a solution of visual SLAMMOT considering multiple motion models and validate the inherent advantages of IMM-SLAMMOT in the visual domain.

♻ ☆ Scaling Open-Vocabulary Action Detection

Zhen Hao Sia, Yogesh Singh Rawat

In this work, we focus on scaling open-vocabulary action detection. Existing approaches for action detection are predominantly limited to closed-set scenarios and rely on complex, parameter-heavy architectures. Extending these models to the open-vocabulary setting poses two key challenges: (1) the lack of large-scale datasets with many action classes for robust training, and (2) parameter-heavy adaptations to a pretrained vision-language contrastive model to convert it for detection, risking overfitting the additional non-pretrained parameters to base action classes. Firstly, we introduce an encoder-only multimodal model for video action detection, reducing the reliance on parameter-heavy additions for video action detection. Secondly, we introduce a simple weakly supervised training strategy to exploit an existing closed-set action detection dataset for pretraining. Finally, we depart from the ill-posed base-to-novel benchmark used by prior works in open-vocabulary action detection and devise a new benchmark to evaluate on existing closed-set action detection datasets without ever using them for training, showing novel results to serve as baselines for future work. Our code is available at https://siatheindochinese.github.io/sia_act_page/ .

♻ ☆ EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement

Wenjie Cai, Qingguo Meng, Zhenyu Wang, Xingbo Dong, Zhe Jin

Capturing high-quality visual content under low-light conditions remains a challenging problem due to severe noise and underexposure, which degrade the performance of downstream applications. Traditional frame-based low-light image enhancement methods often amplify noise or fail to preserve structural details. Event cameras, offering high dynamic range and microsecond temporal resolution by asynchronously capturing brightness changes, emerge as a promising complement for low-light imaging. However, existing fusion methods fail to fully exploit this synergy, either by forcing modalities into a shared representation too early or by losing vital low-level correlations through isolated processing. To address these challenges, we propose EvRWKV, a novel framework that enables continuous cross-modal interaction through dual-domain processing. Our approach incorporates a Cross-RWKV module, leveraging the Receptance Weighted Key Value (RWKV) architecture for fine-grained temporal and cross-modal fusion, and an Event Image Spectral Fusion Enhancer (EISFE) module, which jointly performs adaptive frequency-domain noise suppression and spatial-domain deformable convolution alignment. This continuous interaction maintains feature consistency from low-level textures to high-level semantics. Extensive qualitative and quantitative evaluations on real-world low-light datasets (SDE, SDSD, RELED) demonstrate that EvRWKV achieves state-of-the-art performance, effectively enhancing image quality by suppressing noise, restoring structural details, and improving visual clarity in challenging low-light conditions.

♻ ☆ BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models

Yu Pan, Jiahao Chen, Lin Wang, Bingrong Dai, Yi Du

In recent years, Diffusion models have achieved remarkable progress in the field of image generation. However, recent studies have shown that diffusion models are susceptible to backdoor attacks, in which attackers can manipulate the output by injecting covert triggers such as specific visual patterns or textual phrases into the training dataset. Fortunately, with the continuous advancement of defense techniques, defenders have become increasingly capable of identifying and mitigating most backdoor attacks using visual inspection and neural network-based detection methods. However, in this paper, we identify a novel type of backdoor threat that is more lightweight and covert than existing approaches, which we name BadBlocks, requires only about 30 of the computational resources and 20 GPU time typically needed by previous backdoor attacks, yet it successfully injects backdoors and evades the most advanced defense frameworks. BadBlocks enables attackers to selectively contaminate specific blocks within the UNet architecture of diffusion models while maintaining normal functionality in the remaining components. Experimental results demonstrate that BadBlocks achieves a high attack success rate and low perceptual quality loss , even under extremely constrained computational resources and GPU time. Moreover, BadBlocks is able to bypass existing defense frameworks, especially the attention-based backdoor detection method, highlighting it as a novel and noteworthy threat. Ablation studies further demonstrate that effective backdoor injection does not require fine-tuning the entire network and highlight the pivotal role of certain neural network layers in backdoor mapping. Overall, BadBlocks significantly reduces the barrier to conducting backdoor attacks in all aspects. It enables attackers to inject backdoors into large-scale diffusion models even using consumer-grade GPUs.

♻ ☆ Common Data Properties Limit Object-Attribute Binding in CLIP

Bijay Gurung, David T. Hoffmann, Thomas Brox

Contrastive vision-language models like CLIP are used for a large variety of applications, such as zero-shot classification or as vision encoder for multi-modal models. Despite their popularity, their representations show major limitations. For instance, CLIP models learn bag-of-words representations and, as a consequence, fail to distinguish whether an image is of ``a yellow submarine and a blue bus'' or ``a blue submarine and a yellow bus''. Previous attempts to fix this issue added hard negatives during training or modified the architecture, but failed to resolve the problem in its entirety. We suspect that the missing insights to solve the binding problem for CLIP are hidden in arguably the most important part of learning algorithms: the data. In this work, we fill this gap by rigorously identifying the influence of data properties on CLIP's ability to learn binding using a synthetic dataset. We find that common properties of natural data such as low attribute density, incomplete captions, and the saliency bias, a tendency of human captioners to describe the object that is ``most salient'' to them, have a detrimental effect on binding performance. In contrast to common belief, we find that neither scaling the batch size, i.e., implicitly adding more hard negatives, nor explicitly creating hard negatives enables CLIP to learn reliable binding. Only when the data expresses our identified data properties does CLIP learn almost perfect binding.

comment: accepted at GCPR 2025

♻ ☆ Hierarchical Cross-modal Prompt Learning for Vision-Language Models

Hao Zheng, Shunzhi Yang, Zhuoxin He, Jinfeng Yang, Zhenhua Huang

Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preserving their generalization capabilities remains challenging. Although prompt learning methods have shown promise, they suffer from two fundamental bottlenecks that limit generalization: (a) modality isolation, and (b) hierarchical semantic decay. To address these limitations, we propose HiCroPL, a Hierarchical Cross-modal Prompt Learning framework that establishes bidirectional knowledge flow between text and vision modalities, enabling them to refine their semantics mutually. HiCroPL routes knowledge flows by leveraging the complementary strengths of text and vision. In early layers, text prompts inject relatively clear semantics into visual prompts through a hierarchical knowledge mapper, enhancing the representation of low-level visual semantics. In later layers, visual prompts encoding specific task-relevant objects flow back to refine text prompts, enabling deeper alignment. Crucially, our hierarchical knowledge mapper allows representations at multi-scales to be fused, ensuring that deeper representations retain transferable shallow semantics thereby enhancing generalization. We further introduce a lightweight layer-specific knowledge proxy to enable efficient cross-modal interactions. Extensive evaluations across four tasks demonstrate HiCroPL's superior performance, achieving state-of-the-art results on 11 benchmarks with significant improvements. Code is available at: https://github.com/zzeoZheng/HiCroPL.

comment: Accepted by ICCV2025

♻ ☆ ViFusionTST: Deep Fusion of Time-Series Image Representations from Load Signals for Early Bed-Exit Prediction

Hao Liu, Yu Hu, Rakiba Rayhana, Ling Bai, Zheng Liu

Bed-related falls remain a major source of injury in hospitals and long-term care facilities, yet many commercial alarms trigger only after a patient has already left the bed. We show that early bed-exit intent can be predicted using only one low-cost load cell mounted under a bed leg. The resulting load signals are first converted into a compact set of complementary images: an RGB line plot that preserves raw waveforms and three texture maps-recurrence plot, Markov transition field, and Gramian angular field-that expose higher-order dynamics. We introduce ViFusionTST, a dual-stream Swin Transformer that processes the line plot and texture maps in parallel and fuses them through cross-attention to learn data-driven modality weights. To provide a realistic benchmark, we collected six months of continuous data from 95 beds in a long-term-care facility. On this real-world dataset ViFusionTST reaches an accuracy of 0.885 and an F1 score of 0.794, surpassing recent 1D and 2D time-series baselines across F1, recall, accuracy, and AUPRC. The results demonstrate that image-based fusion of load-sensor signals for time series classification is a practical and effective solution for real-time, privacy-preserving fall prevention.

♻ ☆ Wild2Avatar: Rendering Humans Behind Occlusions

Tiange Xiang, Adam Sun, Scott Delp, Kazuki Kozuka, Li Fei-Fei, Ehsan Adeli

Rendering the visual appearance of moving humans from occluded monocular videos is a challenging task. Most existing research renders 3D humans under ideal conditions, requiring a clear and unobstructed scene. Those methods cannot be used to render humans in real-world scenes where obstacles may block the camera's view and lead to partial occlusions. In this work, we present Wild2Avatar, a neural rendering approach catered for occluded in-the-wild monocular videos. We propose occlusion-aware scene parameterization for decoupling the scene into three parts - occlusion, human, and background. Additionally, extensive objective functions are designed to help enforce the decoupling of the human from both the occlusion and the background and to ensure the completeness of the human model. We verify the effectiveness of our approach with experiments on in-the-wild videos.

comment: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Webpage: https://cs.stanford.edu/~xtiange/projects/wild2avatar/

♻ ☆ An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models

Binxu Wang, Cengiz Pehlevan

We develop an analytical framework for understanding how the generated distribution evolves during diffusion model training. Leveraging a Gaussian-equivalence principle, we solve the full-batch gradient-flow dynamics of linear and convolutional denoisers and integrate the resulting probability-flow ODE, yielding analytic expressions for the generated distribution. The theory exposes a universal inverse-variance spectral law: the time for an eigen- or Fourier mode to match its target variance scales as $\tau\propto\lambda^{-1}$, so high-variance (coarse) structure is mastered orders of magnitude sooner than low-variance (fine) detail. Extending the analysis to deep linear networks and circulant full-width convolutions shows that weight sharing merely multiplies learning rates accelerating but not eliminating the bias whereas local convolution introduces a qualitatively different bias. Experiments on Gaussian and natural-image datasets confirm the spectral law persists in deep MLP-based UNet. Convolutional U-Nets, however, display rapid near-simultaneous emergence of many modes, implicating local convolution in reshaping learning dynamics. These results underscore how data covariance governs the order and speed with which diffusion models learn, and they call for deeper investigation of the unique inductive biases introduced by local convolution.

comment: 91 pages, 23 figures. Preprint

♻ ☆ Part Segmentation of Human Meshes via Multi-View Human Parsing

James Dickens, Kamyar Hamad

Recent advances in point cloud deep learning have led to models that achieve high per-part labeling accuracy on large-scale point clouds, using only the raw geometry of unordered point sets. In parallel, the field of human parsing focuses on predicting body part and clothing/accessory labels from images. This work aims to bridge these two domains by enabling per-vertex semantic segmentation of large-scale human meshes. To achieve this, a pseudo-ground truth labeling pipeline is developed for the Thuman2.1 dataset: meshes are first aligned to a canonical pose, segmented from multiple viewpoints, and the resulting point-level labels are then backprojected onto the original mesh to produce per-point pseudo ground truth annotations. Subsequently, a novel, memory-efficient sampling strategy is introduced, a windowed iterative farthest point sampling (FPS) with space-filling curve-based serialization to effectively downsample the point clouds. This is followed by a purely geometric segmentation using PointTransformer, enabling semantic parsing of human meshes without relying on texture information. Experimental results confirm the effectiveness and accuracy of the proposed approach. Project code and pre-processed data is available at https://github.com/JamesMcCullochDickens/Human3DParsing/tree/master.

2025-08-13

Sound 20

☆ A Comparative Analysis on ASR System Combination for Attention, CTC, Factored Hybrid, and Transducer Models

Noureldin Bayoumi, Robin Schmitt, Tina Raissi, Albert Zeyer, Ralf Schlüter, Hermann Ney

Combination approaches for speech recognition (ASR) systems cover structured sentence-level or word-based merging techniques as well as combination of model scores during beam search. In this work, we compare model combination across popular ASR architectures. Our method leverages the complementary strengths of different models in exploring diverse portions of the search space. We rescore a joint hypothesis list of two model candidates. We then identify the best hypothesis through log-linear combination of these sequence-level scores. While model combination during first-pass recognition may yield improved performance, it introduces variability due to differing decoding methods, making direct comparison more challenging. Our two-pass method ensures consistent comparisons across all system combination results presented in this study. We evaluate model pair candidates with varying architectures and label topologies and units. Experimental results are provided for the Librispeech 960h task.

comment: Accepted for presentation at IEEE Speech Communication; 16th ITG Conference

☆ Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions

Tina Raissi, Nick Rossenbach, Ralf Schlüter

We analyze automatic speech recognition (ASR) modeling choices under domain mismatch, comparing classic modular and novel sequence-to-sequence (seq2seq) architectures. Across the different ASR architectures, we examine a spectrum of modeling choices, including label units, context length, and topology. To isolate language domain effects from acoustic variation, we synthesize target domain audio using a text-to-speech system trained on LibriSpeech. We incorporate target domain n-gram and neural language models for domain adaptation without retraining the acoustic model. To our knowledge, this is the first controlled comparison of optimized ASR systems across state-of-the-art architectures under domain shift, offering insights into their generalization. The results show that, under domain shift, rather than the decoder architecture choice or the distinction between classic modular and novel seq2seq models, it is specific modeling choices that influence performance.

comment: Accepted for presentation at IEEE ASRU 2025

☆ BeatFM: Improving Beat Tracking with Pre-trained Music Foundation Model

Ganghui Ru, Jieying Wang, Jiahao Zhao, Yulun Wu, Yi Yu, Nannan Jiang, Wei Wang, Wei Li

Beat tracking is a widely researched topic in music information retrieval. However, current beat tracking methods face challenges due to the scarcity of labeled data, which limits their ability to generalize across diverse musical styles and accurately capture complex rhythmic structures. To overcome these challenges, we propose a novel beat tracking paradigm BeatFM, which introduces a pre-trained music foundation model and leverages its rich semantic knowledge to improve beat tracking performance. Pre-training on diverse music datasets endows music foundation models with a robust understanding of music, thereby effectively addressing these challenges. To further adapt it for beat tracking, we design a plug-and-play multi-dimensional semantic aggregation module, which is composed of three parallel sub-modules, each focusing on semantic aggregation in the temporal, frequency, and channel domains, respectively. Extensive experiments demonstrate that our method achieves state-of-the-art performance in beat and downbeat tracking across multiple benchmark datasets.

comment: This paper has been accepted by ICME2025

☆ HingeNet: A Harmonic-Aware Fine-Tuning Approach for Beat Tracking

Ganghui Ru, Jieying Wang, Jiahao Zhao, Yulun Wu, Yi Yu, Nannan Jiang, Wei Wang, Wei Li

Fine-tuning pre-trained foundation models has made significant progress in music information retrieval. However, applying these models to beat tracking tasks remains unexplored as the limited annotated data renders conventional fine-tuning methods ineffective. To address this challenge, we propose HingeNet, a novel and general parameter-efficient fine-tuning method specifically designed for beat tracking tasks. HingeNet is a lightweight and separable network, visually resembling a hinge, designed to tightly interface with pre-trained foundation models by using their intermediate feature representations as input. This unique architecture grants HingeNet broad generalizability, enabling effective integration with various pre-trained foundation models. Furthermore, considering the significance of harmonics in beat tracking, we introduce harmonic-aware mechanism during the fine-tuning process to better capture and emphasize the harmonic structures in musical signals. Experiments on benchmark datasets demonstrate that HingeNet achieves state-of-the-art performance in beat and downbeat tracking

comment: This paper has been accepted by ICME2025

☆ MetaGuardian: Enhancing Voice Assistant Security through Advanced Acoustic Metamaterials

Zhiyuan Ning, Zheng Wang, Zhanyong Tang

We present MetaGuardian, a voice assistant (VA) protection system based on acoustic metamaterials. MetaGuardian can be directly integrated into the enclosures of various smart devices, effectively defending against inaudible, adversarial and laser attacks without relying on additional software support or altering the underlying hardware, ensuring usability. To achieve this, MetaGuardian leverages the mutual impedance effects between metamaterial units to extend the signal filtering range to 16-40 kHz to effectively block wide-band inaudible attacks. Additionally, it adopts a carefully designed coiled space structure to precisely interfere with adversarial attacks while ensuring the normal functioning of VAs. Furthermore, MetaGuardian offers a universal structural design, allowing itself to be flexibly adapted to various smart devices, striking a balance between portability and protection effectiveness. In controled evaluation environments, MetaGuardian achieves a high defense success rate against various attack types, including adversarial, inaudible and laser attacks.

☆ $\text{M}^3\text{PDB}$: A Multimodal, Multi-Label, Multilingual Prompt Database for Speech Generation

Boyu Zhu, Cheng Gong, Muyang Wu, Ruihao Jing, Fan Liu, Xiaolei Zhang, Chi Zhang, Xuelong Li

Recent advancements in zero-shot speech generation have enabled models to synthesize speech that mimics speaker identity and speaking style from speech prompts. However, these models' effectiveness is significantly limited in real-world scenarios where high-quality speech prompts are absent, incomplete, or out of domain. This issue arises primarily from a significant quality mismatch between the speech data utilized for model training and the input prompt speech during inference. To address this, we introduce $\text{M}^3\text{PDB}$, the first large-scale, multi-modal, multi-label, and multilingual prompt database designed for robust prompt selection in speech generation. Our dataset construction leverages a novel multi-modal, multi-agent annotation framework, enabling precise and hierarchical labeling across diverse modalities. Furthermore, we propose a lightweight yet effective prompt selection strategy tailored for real-time, resource-constrained inference settings. Experimental results demonstrate that our proposed database and selection strategy effectively support various challenging speech generation scenarios. We hope our work can inspire the community to shift focus from improving performance on standard benchmarks to addressing more realistic and diverse application scenarios in speech generation. Code and dataset are available at: https://github.com/hizening/M3PDB.

☆ OSUM-EChat: Enhancing End-to-End Empathetic Spoken Chatbot via Understanding-Driven Spoken Dialogue

Xuelong Geng, Qijie Shao, Hongfei Xue, Shuiyuan Wang, Hanke Xie, Zhao Guo, Yi Zhao, Guojian Li, Wenjie Tian, Chengyou Wang, Zhixian Zhao, Kangxiang Xia, Ziyu Zhang, Zhennan Lin, Tianlun Zuo, Mingchen Shao, Yuang Cao, Guobin Ma, Longhao Li, Yuhang Dai, Dehui Gao, Dake Guo, Lei Xie

Empathy is crucial in enabling natural interactions within spoken dialogue systems, allowing machines to recognize and respond appropriately to paralinguistic cues such as age, gender, and emotion. Recent advancements in end-to-end speech language models, which unify speech understanding and generation, provide promising solutions. However, several challenges persist, including an over-reliance on large-scale dialogue datasets, insufficient extraction of paralinguistic cues vital for conveying empathy, and the lack of empathy-specific datasets and evaluation frameworks. To address these issues, we introduce OSUM-EChat, an open-source, end-to-end spoken dialogue system designed to enhance empathetic interactions, particularly in resource-limited settings. OSUM-EChat introduces two key innovations: (1) a three-stage understanding-driven spoken dialogue training strategy that extends the capabilities of a large speech understanding model to spoken dialogue tasks, and (2) a linguistic-paralinguistic dual thinking mechanism that integrates paralinguistic understanding through a chain of thought with dialogue generation, enabling the system to produce more empathetic responses. This approach reduces reliance on large-scale dialogue datasets while maintaining high-quality empathetic interactions. Additionally, we introduce the EChat-200K dataset, a rich corpus of empathetic speech-to-speech dialogues, and the EChat-eval benchmark, a comprehensive framework for evaluating the empathetic capabilities of dialogue systems. Experimental results demonstrate that OSUM-EChat outperforms end-to-end spoken dialogue models regarding empathetic responsiveness, validating its effectiveness.

☆ Leveraging Zipformer Model for Effective Language Identification in Code-Switched Child-Directed Speech

Lavanya Shankar, Leibny Paola Garcia Perera

Code-switching and language identification in child-directed scenarios present significant challenges, particularly in bilingual environments. This paper addresses this challenge by using Zipformer to handle the nuances of speech, which contains two imbalanced languages, Mandarin and English, in an utterance. This work demonstrates that the internal layers of the Zipformer effectively encode the language characteristics, which can be leveraged in language identification. We present the selection methodology of the inner layers to extract the embeddings and make a comparison with different back-ends. Our analysis shows that Zipformer is robust across these backends. Our approach effectively handles imbalanced data, achieving a Balanced Accuracy (BAC) of 81.89%, a 15.47% improvement over the language identification baseline. These findings highlight the potential of the transformer encoder architecture model in real scenarios.

☆ No Free Lunch from Audio Pretraining in Bioacoustics: A Benchmark Study of Embeddings

Chenggang Chen, Zhiyu Yang

Bioacoustics, the study of animal sounds, offers a non-invasive method to monitor ecosystems. Extracting embeddings from audio-pretrained deep learning (DL) models without fine-tuning has become popular for obtaining bioacoustic features for tasks. However, a recent benchmark study reveals that while fine-tuned audio-pretrained VGG and transformer models achieve state-of-the-art performance in some tasks, they fail in others. This study benchmarks 11 DL models on the same tasks by reducing their learned embeddings' dimensionality and evaluating them through clustering. We found that audio-pretrained DL models 1) without fine-tuning even underperform fine-tuned AlexNet, 2) both with and without fine-tuning fail to separate the background from labeled sounds, but ResNet does, and 3) outperform other models when fewer background sounds are included during fine-tuning. This study underscores the necessity of fine-tuning audio-pretrained models and checking the embeddings after fine-tuning. Our codes are available: https://github.com/NeuroscienceAI/Audio\_Embeddings

☆ Perturbed Public Voices (P$^{2}$V): A Dataset for Robust Audio Deepfake Detection

Chongyang Gao, Marco Postiglione, Isabel Gortner, Sarit Kraus, V. S. Subrahmanian

Current audio deepfake detectors cannot be trusted. While they excel on controlled benchmarks, they fail when tested in the real world. We introduce Perturbed Public Voices (P$^{2}$V), an IRB-approved dataset capturing three critical aspects of malicious deepfakes: (1) identity-consistent transcripts via LLMs, (2) environmental and adversarial noise, and (3) state-of-the-art voice cloning (2020-2025). Experiments reveal alarming vulnerabilities of 22 recent audio deepfake detectors: models trained on current datasets lose 43% performance when tested on P$^{2}$V, with performance measured as the mean of F1 score on deepfake audio, AUC, and 1-EER. Simple adversarial perturbations induce up to 16% performance degradation, while advanced cloning techniques reduce detectability by 20-30%. In contrast, P$^{2}$V-trained models maintain robustness against these attacks while generalizing to existing datasets, establishing a new benchmark for robust audio deepfake detection. P$^{2}$V will be publicly released upon acceptance by a conference/journal.

♻ ☆ Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation ACM MM 2025

Joonwoo Kwon, Heehwan Wang, Jinwoo Lee, Sooyoung Kim, Shinjae Yoo, Yuewei Lin, Jiook Cha

In this paper, we introduce RevisitAffectiveMemory, a novel task designed to reconstruct autobiographical memories through audio-visual generation guided by affect extracted from electroencephalogram (EEG) signals. To support this pioneering task, we present the EEG-AffectiveMemory dataset, which encompasses textual descriptions, visuals, music, and EEG recordings collected during memory recall from nine participants. Furthermore, we propose RYM (Revisit Your Memory), a three-stage framework for generating synchronized audio-visual contents while maintaining dynamic personal memory affect trajectories. Experimental results demonstrate our method successfully decodes individual affect dynamics trajectories from neural signals during memory recall (F1=0.9). Also, our approach faithfully reconstructs affect-contextualized audio-visual memory across all subjects, both qualitatively and quantitatively, with participants reporting strong affective concordance between their recalled memories and the generated content. Especially, contents generated from subject-reported affect dynamics showed higher correlation with participants' reported affect dynamics trajectories (r=0.265, p<.05) and received stronger user preference (preference=56%) compared to those generated from randomly reordered affect dynamics. Our approaches advance affect decoding research and its practical applications in personalized media creation via neural-based affect comprehension. Codes and the dataset are available at https://github.com/ioahKwon/Revisiting-Your-Memory.

comment: Accepted at the ACM MM 2025 - The 1st CogMAEC Workshop (Oral)

♻ ☆ Multi-Target Backdoor Attacks Against Speaker Recognition

Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, Jesus Villalba Lopez, Najim Dehak, Patrick Cardinal

In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously, achieving success rates of up to 95.04%. To simulate more realistic attack conditions, we vary the signal-to-noise ratio between speech and trigger, demonstrating a trade-off between stealth and effectiveness. We further extend the attack to the speaker verification task by selecting the most similar training speaker - based on cosine similarity - as a proxy target. The attack is most effective when target and enrolled speaker pairs are highly similar, reaching success rates of up to 90% in such cases.

comment: Accepted to IEEE Automatic Speech Recognition and Understanding Workshop 2025

♻ ☆ FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities

Lilit Grigoryan, Vladimir Bataev, Nikolay Karpov, Andrei Andrusenko, Vitaly Lavrukhin, Boris Ginsburg

While beam search improves speech recognition quality over greedy decoding, standard implementations are slow, often sequential, and CPU-bound. To fully leverage modern hardware capabilities, we present a novel open-source FlexCTC toolkit for fully GPU-based beam decoding, designed for Connectionist Temporal Classification (CTC) models. Developed entirely in Python and PyTorch, it offers a fast, user-friendly, and extensible alternative to traditional C++, CUDA, or WFST-based decoders. The toolkit features a high-performance, fully batched GPU implementation with eliminated CPU-GPU synchronization and minimized kernel launch overhead via CUDA Graphs. It also supports advanced contextualization techniques, including GPU-powered N-gram language model fusion and phrase-level boosting. These features enable accurate and efficient decoding, making them suitable for both research and production use.

comment: Accepted to Automatic Speech Recognition and Understanding Workshop (ASRU) 2025

♻ ☆ ReverbFX: A Dataset of Room Impulse Responses Derived from Reverb Effect Plugins for Singing Voice Dereverberation

Julius Richter, Till Svajda, Timo Gerkmann

We present ReverbFX, a new room impulse response (RIR) dataset designed for singing voice dereverberation research. Unlike existing datasets based on real recorded RIRs, ReverbFX features a diverse collection of RIRs captured from various reverb audio effect plugins commonly used in music production. We conduct comprehensive experiments using the proposed dataset to benchmark the challenge of dereverberation of singing voice recordings affected by artificial reverbs. We train two state-of-the-art generative models using ReverbFX and demonstrate that models trained with plugin-derived RIRs outperform those trained on realistic RIRs in artificial reverb scenarios.

comment: Accepted at ITG Conference on Speech Communication

♻ ☆ Leveraging Audio and Text Modalities in Mental Health: A Study of LLMs Performance

Abdelrahman A. Ali, Aya E. Fouda, Radwa J. Hanafy, Mohammed E. Fouda

Mental health disorders are increasingly prevalent worldwide, creating an urgent need for innovative tools to support early diagnosis and intervention. This study explores the potential of Large Language Models (LLMs) in multimodal mental health diagnostics, specifically for detecting depression and Post Traumatic Stress Disorder through text and audio modalities. Using the E-DAIC dataset, we compare text and audio modalities to investigate whether LLMs can perform equally well or better with audio inputs. We further examine the integration of both modalities to determine if this can enhance diagnostic accuracy, which generally results in improved performance metrics. Our analysis specifically utilizes custom-formulated metrics; Modal Superiority Score and Disagreement Resolvement Score to evaluate how combined modalities influence model performance. The Gemini 1.5 Pro model achieves the highest scores in binary depression classification when using the combined modality, with an F1 score of 0.67 and a Balanced Accuracy (BA) of 77.4%, assessed across the full dataset. These results represent an increase of 3.1% over its performance with the text modality and 2.7% over the audio modality, highlighting the effectiveness of integrating modalities to enhance diagnostic accuracy. Notably, all results are obtained in zero-shot inferring, highlighting the robustness of the models without requiring task-specific fine-tuning. To explore the impact of different configurations on model performance, we conduct binary, severity, and multiclass tasks using both zero-shot and few-shot prompts, examining the effects of prompt variations on performance. The results reveal that models such as Gemini 1.5 Pro in text and audio modalities, and GPT-4o mini in the text modality, often surpass other models in balanced accuracy and F1 scores across multiple tasks.

♻ ☆ Acoustic source depth estimation method based on a single hydrophone in Arctic underwater

Jinbao Weng, Yubo Qi, Yanming Yang, Hongtao Wen, Hongtao Zhou, Benqing Chen, Dewei Xu, Ruichao Xue, Caigao Zeng

Based on the normal mode and ray theory, this article discusses the characteristics of surface sound source and reception at the surface layer, and explores depth estimation methods based on normal modes and rays, and proposes a depth estimation method based on the upper limit of modal frequency. Data verification is conducted to discuss the applicability and limitations of different methods. For the surface refracted normal mode waveguide, modes can be separated through warping transformation. Based on the characteristics of normal mode amplitude variation with frequency and number, the sound source depth can be estimated by matching amplitude information. Based on the spatial variation characteristics of eigenfunctions with frequency, a sound source depth estimation method matching the cutoff frequency of normal modes is proposed. For the deep Arctic sea, the sound ray arrival structure at the receiving end is obtained through the analysis of deep inversion sound ray trajectories, and the sound source depth can be estimated by matching the time difference of ray arrivals. Experimental data is used to verify the sound field patterns and the effectiveness of the sound source depth estimation method.

♻ ☆ Inversion of Arctic dual-channel sound speed profile based on random airgun signal

Jinbao Weng, Yubo Qi, Yanming Yang, Hongtao Wen, Hongtao Zhou, Benqing Chen, Dewei Xu, Ruichao Xue, Caigao Zeng

For the unique dual-channel sound speed profiles of the Canadian Basin and the Chukchi Plateau in the Arctic, based on the propagation characteristics of refracted normal modes under dual-channel sound speed profiles, an inversion method using refracted normal modes for dual-channel sound speed profiles is proposed. This method proposes a dual-parameter representation method for dual-channel sound speed profiles, tailored to the characteristics of dual-channel sound speed profiles. A dispersion structure extraction method is proposed for the dispersion structure characteristics of refracted normal modes under dual-channel sound speed profiles. Combining the parameter representation method of sound speed profiles and the dispersion structure extraction method, an inversion method for dual-channel sound speed profiles is proposed. For the common horizontal variation of sound speed profiles in long-distance acoustic propagation, a method for inverting horizontally varying dual-channel sound speed profiles is proposed. Finally, this article verifies the effectiveness of the dual-channel sound speed profile inversion method using the Arctic low-frequency long-range acoustic propagation experiment. Compared with previous sound speed profile inversion methods, the method proposed in this article has the advantages of fewer inversion parameters and faster inversion speed. It can be implemented using only a single hydrophone passively receiving random air gun signals, and it also solves the inversion problem of horizontal variation of sound speed profiles. It has significant advantages such as low cost, easy deployment, and fast computation speed.

♻ ☆ DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models

Yuanyuan Wang, Dongchao Yang, Yiwen Shao, Hangting Chen, Jiankun Zhao, Zhiyong Wu, Helen Meng, Xixin Wu

Extending pre-trained Large Language Models (LLMs)'s speech understanding or generation abilities by introducing various effective speech tokens has attracted great attention in the speech community. However, building a unified speech understanding and generation model still faces the following challenges: (1) Due to the huge modality gap between speech tokens and text tokens, extending text LLMs to unified speech LLMs relies on large-scale paired data for fine-tuning, and (2) Generation and understanding tasks prefer information at different levels, e.g., generation benefits from detailed acoustic features, while understanding favors high-level semantics. This divergence leads to difficult performance optimization in one unified model. To solve these challenges, in this paper, we present two key insights in speech tokenization and speech language modeling. Specifically, we first propose an Understanding-driven Speech Tokenizer (USTokenizer), which extracts high-level semantic information essential for accomplishing understanding tasks using text LLMs. In this way, USToken enjoys better modality commonality with text, which reduces the difficulty of modality alignment in adapting text LLMs to speech LLMs. Secondly, we present DualSpeechLM, a dual-token modeling framework that concurrently models USToken as input and acoustic token as output within a unified, end-to-end framework, seamlessly integrating speech understanding and generation capabilities. Furthermore, we propose a novel semantic supervision loss and a Chain-of-Condition (CoC) strategy to stabilize model training and enhance speech generation performance. Experimental results demonstrate that our proposed approach effectively fosters a complementary relationship between understanding and generation tasks, highlighting the promising strategy of mutually enhancing both tasks in one unified model.

♻ ☆ A2SB: Audio-to-Audio Schrodinger Bridges

Zhifeng Kong, Kevin J Shih, Weili Nie, Arash Vahdat, Sang-gil Lee, Joao Felipe Santos, Ante Jukic, Rafael Valle, Bryan Catanzaro

Real-world audio is often degraded by numerous factors. This work presents an audio restoration model tailored for high-res music at 44.1kHz. Our model, Audio-to-Audio Schr\"odinger Bridges (A2SB), is capable of both bandwidth extension (predicting high-frequency components) and inpainting (re-generating missing segments). Critically, A2SB is end-to-end requiring no vocoder to predict waveform outputs, able to restore hour-long audio inputs, and trained on permissively licensed music data. A2SB is capable of achieving state-of-the-art band-width extension and inpainting quality on several out-of-distribution music test sets.

♻ ☆ A Training-Free Approach for Music Style Transfer with Latent Diffusion Models

Heehwan Wang, Joonwoo Kwon, Sooyoung Kim, Shinjae Yoo, Yuewei Lin, Jiook Cha

Music style transfer enables personalized music creation by combining the structure of one piece with the stylistic characteristics of another. While recent approaches have explored text-conditioned generation and diffusion-based synthesis, most require extensive training, paired datasets, or detailed textual annotations. In this work, we introduce Stylus, a novel training-free framework for music style transfer that directly manipulates the self-attention layers of a pre-trained Latent Diffusion Model (LDM). Operating in the mel-spectrogram domain, Stylus transfers musical style by replacing key and value representations from the content audio with those of the style reference, without any fine-tuning. To enhance stylization quality and controllability, we further incorporate query preservation, CFG-inspired guidance scaling, multi-style interpolation, and phase-preserving reconstruction. Our method significantly improves perceptual quality and structural preservation compared to prior work, while remaining lightweight and easy to deploy. This work highlights the potential of diffusion-based attention manipulation for efficient, high-fidelity, and interpretable music generation-without training. Codes will be released upon acceptance.

comment: Codes will be released upon acceptance

Audio and Speech Processing 17

☆ Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learning

Carlos Franzreb, Arnab Das, Tim Polzehl, Sebastian Möller

The current privacy evaluation for speaker anonymization often overestimates privacy when a same-gender target selection algorithm (TSA) is used, although this TSA leaks the speaker's gender and should hence be more vulnerable. We hypothesize that this occurs because the evaluation does not account for the fact that anonymized speech contains information from both the source and target speakers. To address this, we propose to add a target classifier that measures the influence of target speaker information in the evaluation, which can also be removed with adversarial learning. Experiments demonstrate that this approach is effective for multiple anonymizers, particularly when using a same-gender TSA, leading to a more reliable assessment.

☆ HingeNet: A Harmonic-Aware Fine-Tuning Approach for Beat Tracking

Ganghui Ru, Jieying Wang, Jiahao Zhao, Yulun Wu, Yi Yu, Nannan Jiang, Wei Wang, Wei Li

comment: This paper has been accepted by ICME2025

☆ UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech

Shuhei Kato

We propose UtterTune, a lightweight adaptation method that fine-tunes a multilingual text-to-speech (TTS) system based on a large language model (LLM) architecture, designed to enhance the controllability of pronunciation in a target language while preserving performance in others. While LLM architectures have enabled TTS models to achieve remarkable naturalness, accurately modeling grapheme-to-phoneme (G2P) mapping and prosody remains challenging, especially when the model omits an explicit G2P module and directly processes minimally encoded text (e.g., byte-pair encoding). UtterTune leverages low-rank adaptation to enable the control of segmental pronunciation and pitch accent at the phoneme level for Japanese speech, the target language in this paper, while maintaining naturalness and speaker similarity in a zero-shot setting. Objective and subjective evaluations confirm its effectiveness.

☆ $\text{M}^3\text{PDB}$: A Multimodal, Multi-Label, Multilingual Prompt Database for Speech Generation

Boyu Zhu, Cheng Gong, Muyang Wu, Ruihao Jing, Fan Liu, Xiaolei Zhang, Chi Zhang, Xuelong Li

☆ Perturbed Public Voices (P$^{2}$V): A Dataset for Robust Audio Deepfake Detection

Chongyang Gao, Marco Postiglione, Isabel Gortner, Sarit Kraus, V. S. Subrahmanian

♻ ☆ Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation ACM MM 2025

Joonwoo Kwon, Heehwan Wang, Jinwoo Lee, Sooyoung Kim, Shinjae Yoo, Yuewei Lin, Jiook Cha

comment: Accepted at the ACM MM 2025 - The 1st CogMAEC Workshop (Oral)

♻ ☆ FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities

Lilit Grigoryan, Vladimir Bataev, Nikolay Karpov, Andrei Andrusenko, Vitaly Lavrukhin, Boris Ginsburg

comment: Accepted to Automatic Speech Recognition and Understanding Workshop (ASRU) 2025

♻ ☆ ReverbFX: A Dataset of Room Impulse Responses Derived from Reverb Effect Plugins for Singing Voice Dereverberation

Julius Richter, Till Svajda, Timo Gerkmann

comment: Accepted at ITG Conference on Speech Communication

♻ ☆ Leveraging Audio and Text Modalities in Mental Health: A Study of LLMs Performance

Abdelrahman A. Ali, Aya E. Fouda, Radwa J. Hanafy, Mohammed E. Fouda

♻ ☆ EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting

Guanrou Yang, Chen Yang, Qian Chen, Ziyang Ma, Wenxi Chen, Wen Wang, Tianrui Wang, Yifan Yang, Zhikang Niu, Wenrui Liu, Fan Yu, Zhihao Du, Zhifu Gao, ShiLiang Zhang, Xie Chen

Human speech goes beyond the mere transfer of information; it is a profound exchange of emotions and a connection between individuals. While Text-to-Speech (TTS) models have made huge progress, they still face challenges in controlling the emotional expression in the generated speech. In this work, we propose EmoVoice, a novel emotion-controllable TTS model that exploits large language models (LLMs) to enable fine-grained freestyle natural language emotion control, and a phoneme boost variant design that makes the model output phoneme tokens and audio tokens in parallel to enhance content consistency, inspired by chain-of-thought (CoT) and chain-of-modality (CoM) techniques. Besides, we introduce EmoVoice-DB, a high-quality 40-hour English emotion dataset featuring expressive speech and fine-grained emotion labels with natural language descriptions. EmoVoice achieves state-of-the-art performance on the English EmoVoice-DB test set using only synthetic training data, and on the Chinese Secap test set using our in-house data. We further investigate the reliability of existing emotion evaluation metrics and their alignment with human perceptual preferences, and explore using SOTA multimodal LLMs GPT-4o-audio and Gemini to assess emotional speech. Dataset, code, checkpoints, and demo samples are available at https://github.com/yanghaha0908/EmoVoice.

comment: Accepted at ACMMM 2025

♻ ☆ Acoustic source depth estimation method based on a single hydrophone in Arctic underwater

Jinbao Weng, Yubo Qi, Yanming Yang, Hongtao Wen, Hongtao Zhou, Benqing Chen, Dewei Xu, Ruichao Xue, Caigao Zeng

♻ ☆ Inversion of Arctic dual-channel sound speed profile based on random airgun signal

Jinbao Weng, Yubo Qi, Yanming Yang, Hongtao Wen, Hongtao Zhou, Benqing Chen, Dewei Xu, Ruichao Xue, Caigao Zeng

♻ ☆ DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models

Yuanyuan Wang, Dongchao Yang, Yiwen Shao, Hangting Chen, Jiankun Zhao, Zhiyong Wu, Helen Meng, Xixin Wu

♻ ☆ Non-native Children's Automatic Speech Assessment Challenge (NOCASA)

Yaroslav Getman, Tamás Grósz, Mikko Kurimo, Giampiero Salvi

This paper presents the "Non-native Children's Automatic Speech Assessment" (NOCASA) - a data competition part of the IEEE MLSP 2025 conference. NOCASA challenges participants to develop new systems that can assess single-word pronunciations of young second language (L2) learners as part of a gamified pronunciation training app. To achieve this, several issues must be addressed, most notably the limited nature of available training data and the highly unbalanced distribution among the pronunciation level categories. To expedite the development, we provide a pseudo-anonymized training data (TeflonNorL2), containing 10,334 recordings from 44 speakers attempting to pronounce 205 distinct Norwegian words, human-rated on a 1 to 5 scale (number of stars that should be given in the game). In addition to the data, two already trained systems are released as official baselines: an SVM classifier trained on the ComParE_16 acoustic feature set and a multi-task wav2vec 2.0 model. The latter achieves the best performance on the challenge test set, with an unweighted average recall (UAR) of 36.37%.

comment: Final version of the baseline paper for the NOCASA competition (https://teflon.aalto.fi/nocasa-2025/), Accepted at IEEE MLSP 2025

♻ ☆ A2SB: Audio-to-Audio Schrodinger Bridges

Zhifeng Kong, Kevin J Shih, Weili Nie, Arash Vahdat, Sang-gil Lee, Joao Felipe Santos, Ante Jukic, Rafael Valle, Bryan Catanzaro

♻ ☆ LCS-CTC: Leveraging Soft Alignments to Enhance Phonetic Transcription Robustness

Zongli Ye, Jiachen Lian, Akshaj Gupta, Xuanru Zhou, Haodong Li, Krish Patel, Hwi Joo Park, Dingkun Zhou, Chenxu Guo, Shuhe Li, Sam Wang, Iris Zhou, Cheol Jun Cho, Zoe Ezzes, Jet M. J. Vonk, Brittany T. Morin, Rian Bogley, Lisa Wauters, Zachary A. Miller, Maria Luisa Gorno-Tempini, Gopala Anumanchipalli

Phonetic speech transcription is crucial for fine-grained linguistic analysis and downstream speech applications. While Connectionist Temporal Classification (CTC) is a widely used approach for such tasks due to its efficiency, it often falls short in recognition performance, especially under unclear and nonfluent speech. In this work, we propose LCS-CTC, a two-stage framework for phoneme-level speech recognition that combines a similarity-aware local alignment algorithm with a constrained CTC training objective. By predicting fine-grained frame-phoneme cost matrices and applying a modified Longest Common Subsequence (LCS) algorithm, our method identifies high-confidence alignment zones which are used to constrain the CTC decoding path space, thereby reducing overfitting and improving generalization ability, which enables both robust recognition and text-free forced alignment. Experiments on both LibriSpeech and PPA demonstrate that LCS-CTC consistently outperforms vanilla CTC baselines, suggesting its potential to unify phoneme modeling across fluent and non-fluent speech.

comment: 2025 ASRU. Correct Author List

♻ ☆ A Training-Free Approach for Music Style Transfer with Latent Diffusion Models

Heehwan Wang, Joonwoo Kwon, Sooyoung Kim, Shinjae Yoo, Yuewei Lin, Jiook Cha

comment: Codes will be released upon acceptance

Computer Vision and Pattern Recognition 150

☆ Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

Junyan Ye, Dongzhi Jiang, Zihao Wang, Leqi Zhu, Zhenghao Hu, Zilong Huang, Jun He, Zhiyuan Yan, Jinghua Yu, Hongsheng Li, Conghui He, Weijia Li

Recently, GPT-4o has garnered significant attention for its strong performance in image generation, yet open-source models still lag behind. Several studies have explored distilling image data from GPT-4o to enhance open-source models, achieving notable progress. However, a key question remains: given that real-world image datasets already constitute a natural source of high-quality data, why should we use GPT-4o-generated synthetic data? In this work, we identify two key advantages of synthetic images. First, they can complement rare scenarios in real-world datasets, such as surreal fantasy or multi-reference image generation, which frequently occur in user queries. Second, they provide clean and controllable supervision. Real-world data often contains complex background noise and inherent misalignment between text descriptions and image content, whereas synthetic images offer pure backgrounds and long-tailed supervision signals, facilitating more accurate text-to-image alignment. Building on these insights, we introduce Echo-4o-Image, a 180K-scale synthetic dataset generated by GPT-4o, harnessing the power of synthetic image data to address blind spots in real-world coverage. Using this dataset, we fine-tune the unified multimodal generation baseline Bagel to obtain Echo-4o. In addition, we propose two new evaluation benchmarks for a more accurate and challenging assessment of image generation capabilities: GenEval++, which increases instruction complexity to mitigate score saturation, and Imagine-Bench, which focuses on evaluating both the understanding and generation of imaginative content. Echo-4o demonstrates strong performance across standard benchmarks. Moreover, applying Echo-4o-Image to other foundation models (e.g., OmniGen2, BLIP3-o) yields consistent performance gains across multiple metrics, highlighting the datasets strong transferability.

comment: 19 pages, 8 figures

☆ Story2Board: A Training-Free Approach for Expressive Storyboard Generation

David Dinkevich, Matan Levy, Omri Avrahami, Dvir Samuel, Dani Lischinski

We present Story2Board, a training-free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key aspects of visual storytelling such as spatial composition, background evolution, and narrative pacing. To address this, we introduce a lightweight consistency framework composed of two components: Latent Panel Anchoring, which preserves a shared character reference across panels, and Reciprocal Attention Value Mixing, which softly blends visual features between token pairs with strong reciprocal attention. Together, these mechanisms enhance coherence without architectural changes or fine-tuning, enabling state-of-the-art diffusion models to generate visually diverse yet consistent storyboards. To structure generation, we use an off-the-shelf language model to convert free-form stories into grounded panel-level prompts. To evaluate, we propose the Rich Storyboard Benchmark, a suite of open-domain narratives designed to assess layout diversity and background-grounded storytelling, in addition to consistency. We also introduce a new Scene Diversity metric that quantifies spatial and pose variation across storyboards. Our qualitative and quantitative results, as well as a user study, show that Story2Board produces more dynamic, coherent, and narratively engaging storyboards than existing baselines.

comment: Project page is available at https://daviddinkevich.github.io/Story2Board/

☆ LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit

Chengtao Lv, Bilang Zhang, Yang Yong, Ruihao Gong, Yushi Huang, Shiqiao Gu, Jiajun Wu, Yumeng Shi, Jinyang Guo, Wenya Wang

Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands, due to their long visual token sequences and massive parameter sizes. To address these issues, recent works have proposed training-free compression methods. However, existing efforts often suffer from three major limitations: (1) Current approaches do not decompose techniques into comparable modules, hindering fair evaluation across spatial and temporal redundancy. (2) Evaluation confined to simple single-turn tasks, failing to reflect performance in realistic scenarios. (3) Isolated use of individual compression techniques, without exploring their joint potential. To overcome these gaps, we introduce LLMC+, a comprehensive VLM compression benchmark with a versatile, plug-and-play toolkit. LLMC+ supports over 20 algorithms across five representative VLM families and enables systematic study of token-level and model-level compression. Our benchmark reveals that: (1) Spatial and temporal redundancies demand distinct technical strategies. (2) Token reduction methods degrade significantly in multi-turn dialogue and detail-sensitive tasks. (3) Combining token and model compression achieves extreme compression with minimal performance loss. We believe LLMC+ will facilitate fair evaluation and inspire future research in efficient VLM. Our code is available at https://github.com/ModelTC/LightCompress.

comment: 13 pages, 4 figures

☆ A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation

Shuting He, Peilin Ji, Yitong Yang, Changshuo Wang, Jiayi Ji, Yinglin Wang, Henghui Ding

3D Gaussian Splatting (3DGS) has recently emerged as a powerful alternative to Neural Radiance Fields (NeRF) for 3D scene representation, offering high-fidelity photorealistic rendering with real-time performance. Beyond novel view synthesis, the explicit and compact nature of 3DGS enables a wide range of downstream applications that require geometric and semantic understanding. This survey provides a comprehensive overview of recent progress in 3DGS applications. It first introduces 2D foundation models that support semantic understanding and control in 3DGS applications, followed by a review of NeRF-based methods that inform their 3DGS counterparts. We then categorize 3DGS applications into segmentation, editing, generation, and other functional tasks. For each, we summarize representative methods, supervision strategies, and learning paradigms, highlighting shared design principles and emerging trends. Commonly used datasets and evaluation protocols are also summarized, along with comparative analyses of recent methods across public benchmarks. To support ongoing research and development, a continually updated repository of papers, code, and resources is maintained at https://github.com/heshuting555/Awesome-3DGS-Applications.

comment: GitHub Repo: https://github.com/heshuting555/Awesome-3DGS-Applications

☆ PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image

Geonhee Sim, Gyeongsik Moon

Two major approaches exist for creating animatable human avatars. The first, a 3D-based approach, optimizes a NeRF- or 3DGS-based avatar from videos of a single person, achieving personalization through a disentangled identity representation. However, modeling pose-driven deformations, such as non-rigid cloth deformations, requires numerous pose-rich videos, which are costly and impractical to capture in daily life. The second, a diffusion-based approach, learns pose-driven deformations from large-scale in-the-wild videos but struggles with identity preservation and pose-dependent identity entanglement. We present PERSONA, a framework that combines the strengths of both approaches to obtain a personalized 3D human avatar with pose-driven deformations from a single image. PERSONA leverages a diffusion-based approach to generate pose-rich videos from the input image and optimizes a 3D avatar based on them. To ensure high authenticity and sharp renderings across diverse poses, we introduce balanced sampling and geometry-weighted optimization. Balanced sampling oversamples the input image to mitigate identity shifts in diffusion-generated training videos. Geometry-weighted optimization prioritizes geometry constraints over image loss, preserving rendering quality in diverse poses.

comment: Accepted to ICCV 2025. https://mks0601.github.io/PERSONA/

☆ Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

Luca Eyring, Shyamgopal Karthik, Alexey Dosovitskiy, Nataniel Ruiz, Zeynep Akata

The new paradigm of test-time scaling has yielded remarkable breakthroughs in Large Language Models (LLMs) (e.g. reasoning models) and in generative vision models, allowing models to allocate additional computation during inference to effectively tackle increasingly complex problems. Despite the improvements of this approach, an important limitation emerges: the substantial increase in computation time makes the process slow and impractical for many applications. Given the success of this paradigm and its growing usage, we seek to preserve its benefits while eschewing the inference overhead. In this work we propose one solution to the critical problem of integrating test-time scaling knowledge into a model during post-training. Specifically, we replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise. We propose a theoretically grounded framework for learning this reward-tilted distribution for distilled generators, through a tractable noise-space objective that maintains fidelity to the base model while optimizing for desired characteristics. We show that our approach recovers a substantial portion of the quality gains from explicit test-time optimization at a fraction of the computational cost. Code is available at https://github.com/ExplainableML/HyperNoise

comment: Project page: https://noisehypernetworks.github.io/

☆ MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification

Tianqi Xiang, Yi Li, Qixiang Zhang, Xiaomeng Li

Recent advances in histopathology vision-language foundation models (VLFMs) have shown promise in addressing data scarcity for whole slide image (WSI) classification via zero-shot adaptation. However, these methods remain outperformed by conventional multiple instance learning (MIL) approaches trained on large datasets, motivating recent efforts to enhance VLFM-based WSI classification through fewshot learning paradigms. While existing few-shot methods improve diagnostic accuracy with limited annotations, their reliance on conventional classifier designs introduces critical vulnerabilities to data scarcity. To address this problem, we propose a Meta-Optimized Classifier (MOC) comprising two core components: (1) a meta-learner that automatically optimizes a classifier configuration from a mixture of candidate classifiers and (2) a classifier bank housing diverse candidate classifiers to enable a holistic pathological interpretation. Extensive experiments demonstrate that MOC outperforms prior arts in multiple few-shot benchmarks. Notably, on the TCGA-NSCLC benchmark, MOC improves AUC by 10.4% over the state-of-the-art few-shot VLFM-based methods, with gains up to 26.25% under 1-shot conditions, offering a critical advancement for clinical deployments where diagnostic training data is severely limited. Code is available at https://github.com/xmed-lab/MOC.

comment: Accepted in MICCAI 2025

☆ January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis

Amir Hosseinian, Ashkan Dehghani Zahedani, Umer Mansoor, Noosheen Hashemi, Mark Woodward

Progress in AI for automated nutritional analysis is critically hampered by the lack of standardized evaluation methodologies and high-quality, real-world benchmark datasets. To address this, we introduce three primary contributions. First, we present the January Food Benchmark (JFB), a publicly available collection of 1,000 food images with human-validated annotations. Second, we detail a comprehensive benchmarking framework, including robust metrics and a novel, application-oriented overall score designed to assess model performance holistically. Third, we provide baseline results from both general-purpose Vision-Language Models (VLMs) and our own specialized model, january/food-vision-v1. Our evaluation demonstrates that the specialized model achieves an Overall Score of 86.2, a 12.1-point improvement over the best-performing general-purpose configuration. This work offers the research community a valuable new evaluation dataset and a rigorous framework to guide and benchmark future developments in automated nutritional analysis.

☆ LIA-X: Interpretable Latent Portrait Animator

Yaohui Wang, Di Yang, Xinyuan Chen, Francois Bremond, Yu Qiao, Antitza Dantcheva

We introduce LIA-X, a novel interpretable portrait animator designed to transfer facial dynamics from a driving video to a source portrait with fine-grained control. LIA-X is an autoencoder that models motion transfer as a linear navigation of motion codes in latent space. Crucially, it incorporates a novel Sparse Motion Dictionary that enables the model to disentangle facial dynamics into interpretable factors. Deviating from previous 'warp-render' approaches, the interpretability of the Sparse Motion Dictionary allows LIA-X to support a highly controllable 'edit-warp-render' strategy, enabling precise manipulation of fine-grained facial semantics in the source portrait. This helps to narrow initial differences with the driving video in terms of pose and expression. Moreover, we demonstrate the scalability of LIA-X by successfully training a large-scale model with approximately 1 billion parameters on extensive datasets. Experimental results show that our proposed method outperforms previous approaches in both self-reenactment and cross-reenactment tasks across several benchmarks. Additionally, the interpretable and controllable nature of LIA-X supports practical applications such as fine-grained, user-guided image and video editing, as well as 3D-aware portrait video manipulation.

comment: Project Page: https://wyhsirius.github.io/LIA-X-project/

☆ Stable Diffusion Models are Secretly Good at Visual In-Context Learning

Trevine Oorloff, Vishwanath Sindagi, Wele Gedara Chaminda Bandara, Ali Shafahi, Amin Ghiasi, Charan Prakash, Reza Ardekani

Large language models (LLM) in natural language processing (NLP) have demonstrated great potential for in-context learning (ICL) -- the ability to leverage a few sets of example prompts to adapt to various tasks without having to explicitly update the model weights. ICL has recently been explored for computer vision tasks with promising early outcomes. These approaches involve specialized training and/or additional data that complicate the process and limit its generalizability. In this work, we show that off-the-shelf Stable Diffusion models can be repurposed for visual in-context learning (V-ICL). Specifically, we formulate an in-place attention re-computation within the self-attention layers of the Stable Diffusion architecture that explicitly incorporates context between the query and example prompts. Without any additional fine-tuning, we show that this repurposed Stable Diffusion model is able to adapt to six different tasks: foreground segmentation, single object detection, semantic segmentation, keypoint detection, edge detection, and colorization. For example, the proposed approach improves the mean intersection over union (mIoU) for the foreground segmentation task on Pascal-5i dataset by 8.9% and 3.2% over recent methods such as Visual Prompting and IMProv, respectively. Additionally, we show that the proposed method is able to effectively leverage multiple prompts through ensembling to infer the task better and further improve the performance.

comment: Accepted to ICCV 2025

☆ VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

Lingjie Jiang, Shaohan Huang, Xun Wu, Yixia Li, Dongdong Zhang, Furu Wei

Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding. However, their ability to generate code from multimodal inputs remains limited. In this work, we introduce VisCodex, a unified framework that seamlessly merges vision and coding language models to empower MLLMs with strong multimodal code generation abilities. Leveraging a task vector-based model merging technique, we integrate a state-of-the-art coding LLM into a strong vision-language backbone, while preserving both visual comprehension and advanced coding skills. To support training and evaluation, we introduce the Multimodal Coding Dataset (MCD), a large-scale and diverse collection of 598k samples, including high-quality HTML code, chart image-code pairs, image-augmented StackOverflow QA, and algorithmic problems. Furthermore, we propose InfiBench-V, a novel and challenging benchmark specifically designed to assess models on visually-rich, real-world programming questions that demand a nuanced understanding of both textual and visual contexts. Extensive experiments show that VisCodex achieves state-of-the-art performance among open-source MLLMs and approaches proprietary models like GPT-4o, highlighting the effectiveness of our model merging strategy and new datasets.

☆ AST-n: A Fast Sampling Approach for Low-Dose CT Reconstruction using Diffusion Models

Tomás de la Sotta, José M. Saavedra, Héctor Henríquez, Violeta Chang, Aline Xavier

Low-dose CT (LDCT) protocols reduce radiation exposure but increase image noise, compromising diagnostic confidence. Diffusion-based generative models have shown promise for LDCT denoising by learning image priors and performing iterative refinement. In this work, we introduce AST-n, an accelerated inference framework that initiates reverse diffusion from intermediate noise levels, and integrate high-order ODE solvers within conditioned models to further reduce sampling steps. We evaluate two acceleration paradigms--AST-n sampling and standard scheduling with high-order solvers -- on the Low Dose CT Grand Challenge dataset, covering head, abdominal, and chest scans at 10-25 % of standard dose. Conditioned models using only 25 steps (AST-25) achieve peak signal-to-noise ratio (PSNR) above 38 dB and structural similarity index (SSIM) above 0.95, closely matching standard baselines while cutting inference time from ~16 seg to under 1 seg per slice. Unconditional sampling suffers substantial quality loss, underscoring the necessity of conditioning. We also assess DDIM inversion, which yields marginal PSNR gains at the cost of doubling inference time, limiting its clinical practicality. Our results demonstrate that AST-n with high-order samplers enables rapid LDCT reconstruction without significant loss of image fidelity, advancing the feasibility of diffusion-based methods in clinical workflows.

☆ Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?

Vittorio Pippi, Konstantina Nikolaidou, Silvia Cascianelli, George Retsinas, Giorgos Sfikas, Rita Cucchiara, Marcus Liwicki

The digitization of historical manuscripts presents significant challenges for Handwritten Text Recognition (HTR) systems, particularly when dealing with small, author-specific collections that diverge from the training data distributions. Handwritten Text Generation (HTG) techniques, which generate synthetic data tailored to specific handwriting styles, offer a promising solution to address these challenges. However, the effectiveness of various HTG models in enhancing HTR performance, especially in low-resource transcription settings, has not been thoroughly evaluated. In this work, we systematically compare three state-of-the-art styled HTG models (representing the generative adversarial, diffusion, and autoregressive paradigms for HTG) to assess their impact on HTR fine-tuning. We analyze how visual and linguistic characteristics of synthetic data influence fine-tuning outcomes and provide quantitative guidelines for selecting the most effective HTG model. The results of our analysis provide insights into the current capabilities of HTG methods and highlight key areas for further improvement in their application to low-resource HTR.

comment: Accepted at ICCV Workshop VisionDocs

☆ Towards Comprehensive Cellular Characterisation of H&E slides

Benjamin Adjadj, Pierre-Antoine Bannier, Guillaume Horent, Sebastien Mandela, Aurore Lyon, Kathryn Schutte, Ulysse Marteau, Valentin Gaury, Laura Dumont, Thomas Mathieu, Reda Belbahri, Benoît Schmauch, Eric Durand, Katharina Von Loga, Lucie Gillet

Cell detection, segmentation and classification are essential for analyzing tumor microenvironments (TME) on hematoxylin and eosin (H&E) slides. Existing methods suffer from poor performance on understudied cell types (rare or not present in public datasets) and limited cross-domain generalization. To address these shortcomings, we introduce HistoPLUS, a state-of-the-art model for cell analysis, trained on a novel curated pan-cancer dataset of 108,722 nuclei covering 13 cell types. In external validation across 4 independent cohorts, HistoPLUS outperforms current state-of-the-art models in detection quality by 5.2% and overall F1 classification score by 23.7%, while using 5x fewer parameters. Notably, HistoPLUS unlocks the study of 7 understudied cell types and brings significant improvements on 8 of 13 cell types. Moreover, we show that HistoPLUS robustly transfers to two oncology indications unseen during training. To support broader TME biomarker research, we release the model weights and inference code at https://github.com/owkin/histoplus/.

comment: 33 pages, 4 figures

☆ T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis

Xiaojiao Xiao, Jianfeng Zhao, Qinmin Vivian Hu, Guanghui Wang

Magnetic resonance imaging (MRI) is a leading modality for the diagnosis of liver cancer, significantly improving the classification of the lesion and patient outcomes. However, traditional MRI faces challenges including risks from contrast agent (CA) administration, time-consuming manual assessment, and limited annotated datasets. To address these limitations, we propose a Time-Conditioned Autoregressive Contrast Enhancement (T-CACE) framework for synthesizing multi-phase contrast-enhanced MRI (CEMRI) directly from non-contrast MRI (NCMRI). T-CACE introduces three core innovations: a conditional token encoding (CTE) mechanism that unifies anatomical priors and temporal phase information into latent representations; and a dynamic time-aware attention mask (DTAM) that adaptively modulates inter-phase information flow using a Gaussian-decayed attention mechanism, ensuring smooth and physiologically plausible transitions across phases. Furthermore, a constraint for temporal classification consistency (TCC) aligns the lesion classification output with the evolution of the physiological signal, further enhancing diagnostic reliability. Extensive experiments on two independent liver MRI datasets demonstrate that T-CACE outperforms state-of-the-art methods in image synthesis, segmentation, and lesion classification. This framework offers a clinically relevant and efficient alternative to traditional contrast-enhanced imaging, improving safety, diagnostic efficiency, and reliability for the assessment of liver lesion. The implementation of T-CACE is publicly available at: https://github.com/xiaojiao929/T-CACE.

comment: IEEE Journal of Biomedical and Health Informatics, 2025

☆ E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras

Chaoran Feng, Zhenyu Tang, Wangbo Yu, Yatian Pang, Yian Zhao, Jianbin Zhao, Li Yuan, Yonghong Tian

Novel view synthesis and 4D reconstruction techniques predominantly rely on RGB cameras, thereby inheriting inherent limitations such as the dependence on adequate lighting, susceptibility to motion blur, and a limited dynamic range. Event cameras, offering advantages of low power, high temporal resolution and high dynamic range, have brought a new perspective to addressing the scene reconstruction challenges in high-speed motion and low-light scenes. To this end, we propose E-4DGS, the first event-driven dynamic Gaussian Splatting approach, for novel view synthesis from multi-view event streams with fast-moving cameras. Specifically, we introduce an event-based initialization scheme to ensure stable training and propose event-adaptive slicing splatting for time-aware reconstruction. Additionally, we employ intensity importance pruning to eliminate floating artifacts and enhance 3D consistency, while incorporating an adaptive contrast threshold for more precise optimization. We design a synthetic multi-view camera setup with six moving event cameras surrounding the object in a 360-degree configuration and provide a benchmark multi-view event stream dataset that captures challenging motion scenarios. Our approach outperforms both event-only and event-RGB fusion baselines and paves the way for the exploration of multi-view event-based reconstruction as a novel approach for rapid scene capture.

comment: 16 pages, 10 figures, 5 Tables, accepted by ACMMM 2025

☆ SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection NeurIPS 2024

Yachao Liang, Min Yu, Gang Li, Jianguo Jiang, Boquan Li, Feng Yu, Ning Zhang, Xiang Meng, Weiqing Huang

Detection of face forgery videos remains a formidable challenge in the field of digital forensics, especially the generalization to unseen datasets and common perturbations. In this paper, we tackle this issue by leveraging the synergy between audio and visual speech elements, embarking on a novel approach through audio-visual speech representation learning. Our work is motivated by the finding that audio signals, enriched with speech content, can provide precise information effectively reflecting facial movements. To this end, we first learn precise audio-visual speech representations on real videos via a self-supervised masked prediction task, which encodes both local and global semantic information simultaneously. Then, the derived model is directly transferred to the forgery detection task. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of cross-dataset generalization and robustness, without the participation of any fake video in model training. Code is available at https://github.com/Eleven4AI/SpeechForensics.

comment: Accepted by NeurIPS 2024

☆ COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets

Lingyu Chen, Yawen Zeng, Yue Wang, Peng Wan, Guo-chen Ning, Hongen Liao, Daoqiang Zhang, Fang Chen

Conventional single-dataset training often fails with new data distributions, especially in ultrasound (US) image analysis due to limited data, acoustic shadows, and speckle noise. Therefore, constructing a universal framework for multi-heterogeneous US datasets is imperative. However, a key challenge arises: how to effectively mitigate inter-dataset interference while preserving dataset-specific discriminative features for robust downstream task? Previous approaches utilize either a single source-specific decoder or a domain adaptation strategy, but these methods experienced a decline in performance when applied to other domains. Considering this, we propose a Universal Collaborative Mixture of Heterogeneous Source-Specific Experts (COME). Specifically, COME establishes dual structure-semantic shared experts that create a universal representation space and then collaborate with source-specific experts to extract discriminative features through providing complementary features. This design enables robust generalization by leveraging cross-datasets experience distributions and providing universal US priors for small-batch or unseen data scenarios. Extensive experiments under three evaluation modes (single-dataset, intra-organ, and inter-organ integration datasets) demonstrate COME's superiority, achieving significant mean AP improvements over state-of-the-art methods. Our project is available at: https://universalcome.github.io/UniversalCOME/.

comment: ICCV 2025

☆ HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics

Weiqi Li, Zehao Zhang, Liang Lin, Guangrun Wang

\textbf{Synthetic human dynamics} aims to generate photorealistic videos of human subjects performing expressive, intention-driven motions. However, current approaches face two core challenges: (1) \emph{geometric inconsistency} and \emph{coarse reconstruction}, due to limited 3D modeling and detail preservation; and (2) \emph{motion generalization limitations} and \emph{scene inharmonization}, stemming from weak generative capabilities. To address these, we present \textbf{HumanGenesis}, a framework that integrates geometric and generative modeling through four collaborative agents: (1) \textbf{Reconstructor} builds 3D-consistent human-scene representations from monocular video using 3D Gaussian Splatting and deformation decomposition. (2) \textbf{Critique Agent} enhances reconstruction fidelity by identifying and refining poor regions via multi-round MLLM-based reflection. (3) \textbf{Pose Guider} enables motion generalization by generating expressive pose sequences using time-aware parametric encoders. (4) \textbf{Video Harmonizer} synthesizes photorealistic, coherent video via a hybrid rendering pipeline with diffusion, refining the Reconstructor through a Back-to-4D feedback loop. HumanGenesis achieves state-of-the-art performance on tasks including text-guided synthesis, video reenactment, and novel-pose generalization, significantly improving expressiveness, geometric fidelity, and scene integration.

☆ OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better

Yupeng Zhou, Zhen Li, Ziheng Ouyang, Yuming Chen, Ruoyi Du, Daquan Zhou, Bin Fu, Yihao Liu, Peng Gao, Ming-Ming Cheng, Qibin Hou

Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compared to continuous video representation. Previous discrete video VAEs experienced unstable training, long training time, and degraded reconstruction quality. Given the easier training and superior performance of continuous VAEs, an intuitive idea is to enhance discrete video VAEs by leveraging continuous VAEs. After rethinking the intrinsic link between discrete and continuous representations, we found that FSQ could effectively preserve pre-trained continuous VAE priors compared to other quantization methods. By leveraging continuous VAE priors, it converges several times faster than training from scratch and achieves superior performance at convergence. Meanwhile, two structural improvements are proposed. First, inspired by how continuous VAEs enhance reconstruction via enlarged latent dimensions, we introduce a multi-token quantization mechanism, which achieves nearly a 1 dB improvement in PSNR without compromising the token compression ratio. Second, to tackle reconstruction challenges in high-compression video VAEs, we strengthen first-frame reconstruction, enabling the causal VAE to leverage this information in subsequent frames and markedly improving the performance of 4 x 16 x 16 discrete VAEs. Furthermore, we propose a joint discrete-continuous optimization scheme that unifies the two paradigms and, for the first time, achieves competitive performance on both continuous and discrete representations within a single network. We name our method OneVAE to reflect this connection.

☆ Toward Human-Robot Teaming: Learning Handover Behaviors from 3D Scenes

Yuekun Wu, Yik Lung Pang, Andrea Cavallaro, Changjae Oh

Human-robot teaming (HRT) systems often rely on large-scale datasets of human and robot interactions, especially for close-proximity collaboration tasks such as human-robot handovers. Learning robot manipulation policies from raw, real-world image data requires a large number of robot-action trials in the physical environment. Although simulation training offers a cost-effective alternative, the visual domain gap between simulation and robot workspace remains a major limitation. We introduce a method for training HRT policies, focusing on human-to-robot handovers, solely from RGB images without the need for real-robot training or real-robot data collection. The goal is to enable the robot to reliably receive objects from a human with stable grasping while avoiding collisions with the human hand. The proposed policy learner leverages sparse-view Gaussian Splatting reconstruction of human-to-robot handover scenes to generate robot demonstrations containing image-action pairs captured with a camera mounted on the robot gripper. As a result, the simulated camera pose changes in the reconstructed scene can be directly translated into gripper pose changes. Experiments in both Gaussian Splatting reconstructed scene and real-world human-to-robot handover experiments demonstrate that our method serves as a new and effective representation for the human-to-robot handover task, contributing to more seamless and robust HRT.

comment: 3 pages, 3 figures

☆ Perceptual Reality Transformer: Neural Architectures for Simulating Neurological Perception Conditions

Baihan Lin

Neurological conditions affecting visual perception create profound experiential divides between affected individuals and their caregivers, families, and medical professionals. We present the Perceptual Reality Transformer, a comprehensive framework employing six distinct neural architectures to simulate eight neurological perception conditions with scientifically-grounded visual transformations. Our system learns mappings from natural images to condition-specific perceptual states, enabling others to experience approximations of simultanagnosia, prosopagnosia, ADHD attention deficits, visual agnosia, depression-related changes, anxiety tunnel vision, and Alzheimer's memory effects. Through systematic evaluation across ImageNet and CIFAR-10 datasets, we demonstrate that Vision Transformer architectures achieve optimal performance, outperforming traditional CNN and generative approaches. Our work establishes the first systematic benchmark for neurological perception simulation, contributes novel condition-specific perturbation functions grounded in clinical literature, and provides quantitative metrics for evaluating simulation fidelity. The framework has immediate applications in medical education, empathy training, and assistive technology development, while advancing our fundamental understanding of how neural networks can model atypical human perception.

☆ Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment

Pablo Hernández-Cámara, Jose Manuel Jaén-Lorites, Jorge Vila-Tomás, Valero Laparra, Jesus Malo

Vision Transformers (ViTs) achieve remarkable performance in image recognition tasks, yet their alignment with human perception remains largely unexplored. This study systematically analyzes how model size, dataset size, data augmentation and regularization impact ViT perceptual alignment with human judgments on the TID2013 dataset. Our findings confirm that larger models exhibit lower perceptual alignment, consistent with previous works. Increasing dataset diversity has a minimal impact, but exposing models to the same images more times reduces alignment. Stronger data augmentation and regularization further decrease alignment, especially in models exposed to repeated training cycles. These results highlight a trade-off between model complexity, training strategies, and alignment with human perception, raising important considerations for applications requiring human-like visual understanding.

☆ ARI3D: A Software for Interactive Quantification of Regions in X-Ray CT 3D Images

Jan Phillipp Albrecht, Jose R. A. Godinho, Christina Hübers, Deborah Schmidt

X-ray computed tomography (CT) is the main 3D technique for imaging the internal microstructures of materials. Quantitative analysis of the microstructures is usually achieved by applying a sequence of steps that are implemented to the entire 3D image. This is challenged by various imaging artifacts inherent from the technique, e.g., beam hardening and partial volume. Consequently, the analysis requires users to make a number of decisions to segment and classify the microstructures based on the voxel gray-values. In this context, a software tool, here called ARI3D, is proposed to interactively analyze regions in three-dimensional X-ray CT images, assisting users through the various steps of a protocol designed to classify and quantify objects within regions of a three-dimensional image. ARI3D aims to 1) Improve phase identification; 2) Account for partial volume effect; 3) Increase the detection limit and accuracy of object quantification; and 4) Harmonize quantitative 3D analysis that can be implemented in different fields of science.

comment: 2 figures and 6 pages main article, 17 pages total, 8 figures total, to be published in SoftwareX

☆ Enhancing Diffusion Face Generation with Contrastive Embeddings and SegFormer Guidance

Dhruvraj Singh Rawat, Enggen Sherpa, Rishikesan Kirupanantha, Tin Hoang

We present a benchmark of diffusion models for human face generation on a small-scale CelebAMask-HQ dataset, evaluating both unconditional and conditional pipelines. Our study compares UNet and DiT architectures for unconditional generation and explores LoRA-based fine-tuning of pretrained Stable Diffusion models as a separate experiment. Building on the multi-conditioning approach of Giambi and Lisanti, which uses both attribute vectors and segmentation masks, our main contribution is the integration of an InfoNCE loss for attribute embedding and the adoption of a SegFormer-based segmentation encoder. These enhancements improve the semantic alignment and controllability of attribute-guided synthesis. Our results highlight the effectiveness of contrastive embedding learning and advanced segmentation encoding for controlled face generation in limited data settings.

comment: 10 pages, preprint

☆ Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment

Hao Yang, Xu Zhang, Jiaqi Ma, Linwei Zhu, Yun Zhang, Huan Zhang

Current Omnidirectional Image Quality Assessment (OIQA) methods struggle to evaluate locally non-uniform distortions due to inadequate modeling of spatial variations in quality and ineffective feature representation capturing both local details and global context. To address this, we propose a graph neural network-based OIQA framework that explicitly models structural relationships between viewports to enhance perception of spatial distortion non-uniformity. Our approach employs Fibonacci sphere sampling to generate viewports with well-structured topology, representing each as a graph node. Multi-stage feature extraction networks then derive high-dimensional node representation. To holistically capture spatial dependencies, we integrate a Graph Attention Network (GAT) modeling fine-grained local distortion variations among adjacent viewports, and a graph transformer capturing long-range quality interactions across distant regions. Extensive experiments on two large-scale OIQA databases with complex spatial distortions demonstrate that our method significantly outperforms existing approaches, confirming its effectiveness and strong generalization capability.

☆ Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

Weigao Sun, Jiaxi Hu, Yucheng Zhou, Jusen Du, Disen Lan, Kexin Wang, Tong Zhu, Xiaoye Qu, Yu Zhang, Xiaoyu Mo, Daizong Liu, Yuxuan Liang, Wenliang Chen, Guoqi Li, Yu Cheng

Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models. Transformer models, as the foundation of modern LLMs, offer a strong baseline with excellent scaling properties. However, the traditional transformer architecture requires substantial computations and poses significant obstacles for large-scale training and practical deployment. In this survey, we offer a systematic examination of innovative LLM architectures that address the inherent limitations of transformers and boost the efficiency. Starting from language modeling, this survey covers the background and technical details of linear and sparse sequence modeling methods, efficient full attention variants, sparse mixture-of-experts, hybrid model architectures incorporating the above techniques, and emerging diffusion LLMs. Additionally, we discuss applications of these techniques to other modalities and consider their wider implications for developing scalable, resource-aware foundation models. By grouping recent studies into the above category, this survey presents a blueprint of modern efficient LLM architectures, and we hope this could help motivate future research toward more efficient, versatile AI systems.

comment: Survey, 82 pages, GitHub: https://github.com/weigao266/Awesome-Efficient-Arch

☆ Robustness analysis of Deep Sky Objects detection models on HPC

Olivier Parisot, Diogo Ramalho Fernandes

Astronomical surveys and the growing involvement of amateur astronomers are producing more sky images than ever before, and this calls for automated processing methods that are accurate and robust. Detecting Deep Sky Objects -- such as galaxies, nebulae, and star clusters -- remains challenging because of their faint signals and complex backgrounds. Advances in Computer Vision and Deep Learning now make it possible to improve and automate this process. In this paper, we present the training and comparison of different detection models (YOLO, RET-DETR) on smart telescope images, using High-Performance Computing (HPC) to parallelise computations, in particular for robustness testing.

comment: 11 pages, 4 figures, NEOD project

☆ RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians

Shenxing Wei, Jinxi Li, Yafei Yang, Siyuan Zhou, Bo Yang

In this paper, we present a generalizable method for 3D surface reconstruction from raw point clouds or pre-estimated 3D Gaussians by 3DGS from RGB images. Unlike existing coordinate-based methods which are often computationally intensive when rendering explicit surfaces, our proposed method, named RayletDF, introduces a new technique called raylet distance field, which aims to directly predict surface points from query rays. Our pipeline consists of three key modules: a raylet feature extractor, a raylet distance field predictor, and a multi-raylet blender. These components work together to extract fine-grained local geometric features, predict raylet distances, and aggregate multiple predictions to reconstruct precise surface points. We extensively evaluate our method on multiple public real-world datasets, demonstrating superior performance in surface reconstruction from point clouds or 3D Gaussians. Most notably, our method achieves exceptional generalization ability, successfully recovering 3D surfaces in a single-forward pass across unseen datasets in testing.

comment: ICCV 2025 Highlight. Shenxing and Jinxi are co-first authors. Code and data are available at: https://github.com/vLAR-group/RayletDF

☆ Reverse Convolution and Its Applications to Image Restoration

Xuhong Huang, Shiqi Liu, Kai Zhang, Ying Tai, Jian Yang, Hui Zeng, Lei Zhang

comment: ICCV 2025; https://github.com/cszn/ConverseNet

☆ KonfAI: A Modular and Fully Configurable Framework for Deep Learning in Medical Imaging

Valentin Boussot, Jean-Louis Dillenseger

KonfAI is a modular, extensible, and fully configurable deep learning framework specifically designed for medical imaging tasks. It enables users to define complete training, inference, and evaluation workflows through structured YAML configuration files, without modifying the underlying code. This declarative approach enhances reproducibility, transparency, and experimental traceability while reducing development time. Beyond the capabilities of standard pipelines, KonfAI provides native abstractions for advanced strategies including patch-based learning, test-time augmentation, model ensembling, and direct access to intermediate feature representations for deep supervision. It also supports complex multi-model training setups such as generative adversarial architectures. Thanks to its modular and extensible architecture, KonfAI can easily accommodate custom models, loss functions, and data processing components. The framework has been successfully applied to segmentation, registration, and image synthesis tasks, and has contributed to top-ranking results in several international medical imaging challenges. KonfAI is open source and available at \href{https://github.com/vboussot/KonfAI}{https://github.com/vboussot/KonfAI}.

comment: https://github.com/vboussot/KonfAI

☆ Physical Autoregressive Model for Robotic Manipulation without Action Pretraining

Zijian Song, Sihan Qin, Tianshui Chen, Liang Lin, Guangrun Wang

The scarcity of manipulation data has motivated the use of pretrained large models from other modalities in robotics. In this work, we build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR), where physical tokens combine frames and actions to represent the joint evolution of the robot and its environment. PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining, enabling accurate video prediction and consistent action trajectories. It also adopts a DiT-based de-tokenizer to model frames and actions as continuous tokens, mitigating quantization errors and facilitating mutual enhancement. Furthermore, we incorporate a causal mask with inverse kinematics, parallel training, and the KV-cache mechanism to further improve performance and efficiency. Experiments on the ManiSkill benchmark show that PAR achieves a 100\% success rate on the PushCube task, matches the performance of action-pretrained baselines on other tasks, and accurately predicts future videos with tightly aligned action trajectories. These findings underscore a promising direction for robotic manipulation by transferring world knowledge from autoregressive video pretraining.

comment: 16 pages, 6 figures

☆ ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video

Rajan Das Gupta, Md Yeasin Rahat, Nafiz Fahad, Abir Ahmed, Liew Tze Hui

This study investigates how large language models (LLMs) can be used to understand human behavior using motion and video data. We think that mixing both types is essential to completely capture the nuanced movements and meanings of human actions, in contrast to recent models that simply concentrate on motion data or films. To address this, we provide ViMoNet, a straightforward yet effective framework for comprehending, characterizing, and deducing human action. ViMoNet employs a joint training strategy that leverages the advantages of two data types: detailed motion-text data, which is more exact, and generic video-text data, which is more comprehensive but less detailed. This aids in the model's acquisition of rich data regarding time and space in human behavior. Additionally, we provide a brand new dataset named VIMOS that contains a variety of films, motion sequences, instructions, and subtitles. We developed ViMoNet-Bench, a standardized benchmark with carefully labeled samples, to evaluate how well models understand human behavior. Our tests show that ViMoNet outperforms existing methods in caption generation, motion understanding, and behavior interpretation.

comment: Accepted in ICCVDM '25

☆ Evolution of Low-Level and Texture Human-CLIP Alignment

Pablo Hernández-Cámara, Jose Manuel Jaén-Lorites, Jorge Vila-Tomás, Jesus Malo, Valero Laparra

During the training of multi-modal models like CLIP, we observed an intriguing phenomenon: the correlation with low-level human image quality assessments peaks in the early epochs before gradually declining. This study investigates this observation and seeks to understand its causes through two key factors: shape-texture bias alignment and classification accuracy drop under noise. Our findings suggest that CLIP initially learn low-level visual features, enhancing its alignment with low-level human perception but also increasing its sensitivity to noise and its texture bias. As training progresses, the model shifts toward more abstract shape-based representations, improving noise robustness but reducing alignment with low-level human perception. These results suggest that these factors shared an underlying learning mechanism and provide new insights into optimizing the trade-off between perceptual alignment and robustness in vision-language models.

☆ Poaching Hotspot Identification Using Satellite Imagery

Aryan Pandhi, Shrey Baid, Sanjali Jha

Elephant Poaching in African countries has been a decade-old problem. So much so that African Forest Elephants are now listed as an endangered species, and African Savannah Elephants as critically endangered by the IUCN (International Union for Conservation of Nature). [1] Elephants are hunted primarily for their ivory tusks which caused many elephants to be born tuskless as a genetic modification for survival. [2] Data gathered by recent studies shows that though poaching methods remain the same, the poaching grounds are rather dynamic. Poachers have shifted to areas with less ranger patrols and several other factors like watering holes, seasons, altitude etc. cause constant shifts in poaching hotspot locations. [3] After a period of low poaching from 2000-2014, poaching numbers in African countries are now on the rise again -- WWF (World Wildlife Foundation) says there are 20,000 elephants poached annually [4]. In African countries, anti-poaching efforts are concentrated near towns, while a majority of poaching occurs in the deserted regions. All of these factors result in the need for a Computer Vision Model to identify poaching hotspots through locating the geographic indicators of favorable poaching regions. A CV model eliminates the need to manually track poachers and account for the environmental factors to deploy resources and its combination with satellite imagery allows us to survey large areas without disturbing local species or cross border aviation restrictions.

☆ TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos

Jinxi Li, Ziyang Song, Bo Yang

In this paper, we aim to model 3D scene geometry, appearance, and physical information just from dynamic multi-view videos in the absence of any human labels. By leveraging physics-informed losses as soft constraints or integrating simple physics models into neural nets, existing works often fail to learn complex motion physics, or doing so requires additional labels such as object types or masks. We propose a new framework named TRACE to model the motion physics of complex dynamic 3D scenes. The key novelty of our method is that, by formulating each 3D point as a rigid particle with size and orientation in space, we directly learn a translation rotation dynamics system for each particle, explicitly estimating a complete set of physical parameters to govern the particle's motion over time. Extensive experiments on three existing dynamic datasets and one newly created challenging synthetic datasets demonstrate the extraordinary performance of our method over baselines in the task of future frame extrapolation. A nice property of our framework is that multiple objects or parts can be easily segmented just by clustering the learned physical parameters.

comment: ICCV 2025. Code and data are available at: https://github.com/vLAR-group/TRACE

☆ Automated Segmentation of Coronal Brain Tissue Slabs for 3D Neuropathology

Jonathan Williams Ramirez, Dina Zemlyanker, Lucas Deden-Binder, Rogeny Herisse, Erendira Garcia Pallares, Karthik Gopinath, Harshvardhan Gazula, Christopher Mount, Liana N. Kozanno, Michael S. Marshall, Theresa R. Connors, Matthew P. Frosch, Mark Montine, Derek H. Oakley, Christine L. Mac Donald, C. Dirk Keene, Bradley T. Hyman, Juan Eugenio Iglesias

Advances in image registration and machine learning have recently enabled volumetric analysis of \emph{postmortem} brain tissue from conventional photographs of coronal slabs, which are routinely collected in brain banks and neuropathology laboratories worldwide. One caveat of this methodology is the requirement of segmentation of the tissue from photographs, which currently requires costly manual intervention. In this article, we present a deep learning model to automate this process. The automatic segmentation tool relies on a U-Net architecture that was trained with a combination of \textit{(i)}1,414 manually segmented images of both fixed and fresh tissue, from specimens with varying diagnoses, photographed at two different sites; and \textit{(ii)}~2,000 synthetic images with randomized contrast and corresponding masks generated from MRI scans for improved generalizability to unseen photographic setups. Automated model predictions on a subset of photographs not seen in training were analyzed to estimate performance compared to manual labels -- including both inter- and intra-rater variability. Our model achieved a median Dice score over 0.98, mean surface distance under 0.4~mm, and 95\% Hausdorff distance under 1.60~mm, which approaches inter-/intra-rater levels. Our tool is publicly available at surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools.

comment: 19 pages, 10 figures

☆ MUJICA: Reforming SISR Models for PBR Material Super-Resolution via Cross-Map Attention

Xin Du, Maoyuan Xu, Zhi Ying

Physically Based Rendering (PBR) materials are typically characterized by multiple 2D texture maps such as basecolor, normal, metallic, and roughness which encode spatially-varying bi-directional reflectance distribution function (SVBRDF) parameters to model surface reflectance properties and microfacet interactions. Upscaling SVBRDF material is valuable for modern 3D graphics applications. However, existing Single Image Super-Resolution (SISR) methods struggle with cross-map inconsistency, inadequate modeling of modality-specific features, and limited generalization due to data distribution shifts. In this work, we propose Multi-modal Upscaling Joint Inference via Cross-map Attention (MUJICA), a flexible adapter that reforms pre-trained Swin-transformer-based SISR models for PBR material super-resolution. MUJICA is seamlessly attached after the pre-trained and frozen SISR backbone. It leverages cross-map attention to fuse features while preserving remarkable reconstruction ability of the pre-trained SISR model. Applied to SISR models such as SwinIR, DRCT, and HMANet, MUJICA improves PSNR, SSIM, and LPIPS scores while preserving cross-map consistency. Experiments demonstrate that MUJICA enables efficient training even with limited resources and delivers state-of-the-art performance on PBR material datasets.

☆ MeMoSORT: Memory-Assisted Filtering and Motion-Adaptive Association Metric for Multi-Person Tracking

Yingjie Wang, Zhixing Wang, Le Zheng, Tianxiao Liu, Roujing Li, Xueyao Hu

Multi-object tracking (MOT) in human-dominant scenarios, which involves continuously tracking multiple people within video sequences, remains a significant challenge in computer vision due to targets' complex motion and severe occlusions. Conventional tracking-by-detection methods are fundamentally limited by their reliance on Kalman filter (KF) and rigid Intersection over Union (IoU)-based association. The motion model in KF often mismatches real-world object dynamics, causing filtering errors, while rigid association struggles under occlusions, leading to identity switches or target loss. To address these issues, we propose MeMoSORT, a simple, online, and real-time MOT tracker with two key innovations. First, the Memory-assisted Kalman filter (MeKF) uses memory-augmented neural networks to compensate for mismatches between assumed and actual object motion. Second, the Motion-adaptive IoU (Mo-IoU) adaptively expands the matching space and incorporates height similarity to reduce the influence of detection errors and association failures, while remaining lightweight. Experiments on DanceTrack and SportsMOT show that MeMoSORT achieves state-of-the-art performance, with HOTA scores of 67.9\% and 82.1\%, respectively.

☆ Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

Marco De Nadai, Andreas Damianou, Mounia Lalmas

Existing video recommender systems rely primarily on user-defined metadata or on low-level visual and acoustic signals extracted by specialised encoders. These low-level features describe what appears on the screen but miss deeper semantics such as intent, humour, and world knowledge that make clips resonate with viewers. For example, is a 30-second clip simply a singer on a rooftop, or an ironic parody filmed amid the fairy chimneys of Cappadocia, Turkey? Such distinctions are critical to personalised recommendations yet remain invisible to traditional encoding pipelines. In this paper, we introduce a simple, recommendation system-agnostic zero-finetuning framework that injects high-level semantics into the recommendation pipeline by prompting an off-the-shelf Multimodal Large Language Model (MLLM) to summarise each clip into a rich natural-language description (e.g. "a superhero parody with slapstick fights and orchestral stabs"), bridging the gap between raw content and user intent. We use MLLM output with a state-of-the-art text encoder and feed it into standard collaborative, content-based, and generative recommenders. On the MicroLens-100K dataset, which emulates user interactions with TikTok-style videos, our framework consistently surpasses conventional video, audio, and metadata features in five representative models. Our findings highlight the promise of leveraging MLLMs as on-the-fly knowledge extractors to build more intent-aware video recommenders.

☆ DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning

Linpu He, Yanan Li, Bingze Li, Elvis Han Cui, Donghui Wang

Learning from large-scale pre-trained models with strong generalization ability has shown remarkable success in a wide range of downstream tasks recently, but it is still underexplored in the challenging few-shot class-incremental learning (FSCIL) task. It aims to continually learn new concepts from limited training samples without forgetting the old ones at the same time. In this paper, we introduce DSS-Prompt, a simple yet effective approach that transforms the pre-trained Vision Transformer with minimal modifications in the way of prompts into a strong FSCIL classifier. Concretely, we synergistically utilize two complementary types of prompts in each Transformer block: static prompts to bridge the domain gap between the pre-training and downstream datasets, thus enabling better adaption; and dynamic prompts to capture instance-aware semantics, thus enabling easy transfer from base to novel classes. Specially, to generate dynamic prompts, we leverage a pre-trained multi-modal model to extract input-related diverse semantics, thereby generating complementary input-aware prompts, and then adaptively adjust their importance across different layers. In this way, on top of the prompted visual embeddings, a simple prototype classifier can beat state-of-the-arts without further training on the incremental tasks. We conduct extensive experiments on four benchmarks to validate the effectiveness of our DSS-Prompt and show that it consistently achieves better performance than existing approaches on all datasets and can alleviate the catastrophic forgetting issue as well.

comment: Accepted to ACMMM 2025

☆ Combinative Matching for Geometric Shape Assembly

Nahyuk Lee, Juhong Min, Junhong Lee, Chunghyun Park, Minsu Cho

This paper introduces a new shape-matching methodology, combinative matching, to combine interlocking parts for geometric shape assembly. Previous methods for geometric assembly typically rely on aligning parts by finding identical surfaces between the parts as in conventional shape matching and registration. In contrast, we explicitly model two distinct properties of interlocking shapes: 'identical surface shape' and 'opposite volume occupancy.' Our method thus learns to establish correspondences across regions where their surface shapes appear identical but their volumes occupy the inverted space to each other. To facilitate this process, we also learn to align regions in rotation by estimating their shape orientations via equivariant neural networks. The proposed approach significantly reduces local ambiguities in matching and allows a robust combination of parts in assembly. Experimental results on geometric assembly benchmarks demonstrate the efficacy of our method, consistently outperforming the state of the art. Project page: https://nahyuklee.github.io/cmnet.

comment: Accepted to ICCV 2025 (Highlight)

☆ MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models

Dianyi Wang, Siyuan Wang, Zejun Li, Yikun Wang, Yitong Li, Duyu Tang, Xiaoyu Shen, Xuanjing Huang, Zhongyu Wei

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across multi-modal tasks by scaling model size and training data. However, these dense LVLMs incur significant computational costs and motivate the exploration of sparse Mixture of Experts (MoE) architectures. While MoE improve parameter efficiency, effectively applying MoE to simultaneously model modality-specific features and cross-modal associations in LVLMs remains challenging. In this work, we propose to incorporate Mixture of Intra- and Inter-Modality Experts (MoIIE) to LVLMs. For each token, expert routing is guided by its modality, directing tokens to their respective intra-modality experts as well as a shared pool of inter-modality experts, enabling the model to jointly learn rich intra-modal features and cross-modal interactions. We further introduce an effective and straightforward two-stage training strategy, which facilitates the direct activation of both MoE and multi-modal capabilities. Extensive experiments across different data scales and LLM backbone demonstrate the effectiveness, efficiency and generality of our approach. Notably, our MoIIE models with 5.5B and 11.3B activated parameters match or even surpass the performance of existing advanced open-source MoE-LLMs based multi-modal models that involve more activated parameters. The code is available at https://github.com/AlenjandroWang/MoIIE.

☆ Region-to-Region: Enhancing Generative Image Harmonization with Adaptive Regional Injection

Zhiqiu Zhang, Dongqi Fan, Mingjie Wang, Qiang Tang, Jian Yang, Zili Yi

The goal of image harmonization is to adjust the foreground in a composite image to achieve visual consistency with the background. Recently, latent diffusion model (LDM) are applied for harmonization, achieving remarkable results. However, LDM-based harmonization faces challenges in detail preservation and limited harmonization ability. Additionally, current synthetic datasets rely on color transfer, which lacks local variations and fails to capture complex real-world lighting conditions. To enhance harmonization capabilities, we propose the Region-to-Region transformation. By injecting information from appropriate regions into the foreground, this approach preserves original details while achieving image harmonization or, conversely, generating new composite data. From this perspective, We propose a novel model R2R. Specifically, we design Clear-VAE to preserve high-frequency details in the foreground using Adaptive Filter while eliminating disharmonious elements. To further enhance harmonization, we introduce the Harmony Controller with Mask-aware Adaptive Channel Attention (MACA), which dynamically adjusts the foreground based on the channel importance of both foreground and background regions. To address the limitation of existing datasets, we propose Random Poisson Blending, which transfers color and lighting information from a suitable region to the foreground, thereby generating more diverse and challenging synthetic images. Using this method, we construct a new synthetic dataset, RPHarmony. Experiments demonstrate the superiority of our method over other methods in both quantitative metrics and visual harmony. Moreover, our dataset helps the model generate more realistic images in real examples. Our code, dataset, and model weights have all been released for open access.

☆ Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, Junbo Zhao, Wei Li

We introduce M3-Agent, a novel multimodal agent framework equipped with long-term memory. Like humans, M3-Agent can process real-time visual and auditory inputs to build and update its long-term memory. Beyond episodic memory, it also develops semantic memory, enabling it to accumulate world knowledge over time. Its memory is organized in an entity-centric, multimodal format, allowing deeper and more consistent understanding of the environment. Given an instruction, M3-Agent autonomously performs multi-turn, iterative reasoning and retrieves relevant information from memory to accomplish the task. To evaluate memory effectiveness and memory-based reasoning in multimodal agents, we develop M3-Bench, a new long-video question answering benchmark. M3-Bench comprises 100 newly recorded real-world videos captured from a robot's perspective (M3-Bench-robot) and 929 web-sourced videos across diverse scenarios (M3-Bench-web). We annotate question-answer pairs designed to test key capabilities essential for agent applications, such as human understanding, general knowledge extraction, and cross-modal reasoning. Experimental results show that M3-Agent, trained via reinforcement learning, outperforms the strongest baseline, a prompting agent using Gemini-1.5-pro and GPT-4o, achieving 6.7%, 7.7%, and 5.3% higher accuracy on M3-Bench-robot, M3-Bench-web and VideoMME-long, respectively. Our work advances the multimodal agents toward more human-like long-term memory and provides insights into their practical design. Model, code and data are available at https://github.com/bytedance-seed/m3-agent

☆ Predictive Uncertainty for Runtime Assurance of a Real-Time Computer Vision-Based Landing System

Romeo Valentin, Sydney M. Katz, Artur B. Carneiro, Don Walker, Mykel J. Kochenderfer

Recent advances in data-driven computer vision have enabled robust autonomous navigation capabilities for civil aviation, including automated landing and runway detection. However, ensuring that these systems meet the robustness and safety requirements for aviation applications remains a major challenge. In this work, we present a practical vision-based pipeline for aircraft pose estimation from runway images that represents a step toward the ability to certify these systems for use in safety-critical aviation applications. Our approach features three key innovations: (i) an efficient, flexible neural architecture based on a spatial Soft Argmax operator for probabilistic keypoint regression, supporting diverse vision backbones with real-time inference; (ii) a principled loss function producing calibrated predictive uncertainties, which are evaluated via sharpness and calibration metrics; and (iii) an adaptation of Residual-based Receiver Autonomous Integrity Monitoring (RAIM), enabling runtime detection and rejection of faulty model outputs. We implement and evaluate our pose estimation pipeline on a dataset of runway images. We show that our model outperforms baseline architectures in terms of accuracy while also producing well-calibrated uncertainty estimates with sub-pixel precision that can be used downstream for fault detection.

comment: 8 pages, 5 figures, accepted at DASC 2025

☆ Multimodal Sheaf-based Network for Glioblastoma Molecular Subtype Prediction

Shekhnaz Idrissova, Islem Rekik

Glioblastoma is a highly invasive brain tumor with rapid progression rates. Recent studies have shown that glioblastoma molecular subtype classification serves as a significant biomarker for effective targeted therapy selection. However, this classification currently requires invasive tissue extraction for comprehensive histopathological analysis. Existing multimodal approaches combining MRI and histopathology images are limited and lack robust mechanisms for preserving shared structural information across modalities. In particular, graph-based models often fail to retain discriminative features within heterogeneous graphs, and structural reconstruction mechanisms for handling missing or incomplete modality data are largely underexplored. To address these limitations, we propose a novel sheaf-based framework for structure-aware and consistent fusion of MRI and histopathology data. Our model outperforms baseline methods and demonstrates robustness in incomplete or missing data scenarios, contributing to the development of virtual biopsy tools for rapid diagnostics. Our source code is available at https://github.com/basiralab/MMSN/.

☆ NEURAL: Attention-Guided Pruning for Unified Multimodal Resource-Constrained Clinical Evaluation

Devvrat Joshi, Islem Rekik

The rapid growth of multimodal medical imaging data presents significant storage and transmission challenges, particularly in resource-constrained clinical settings. We propose NEURAL, a novel framework that addresses this by using semantics-guided data compression. Our approach repurposes cross-attention scores between the image and its radiological report from a fine-tuned generative vision-language model to structurally prune chest X-rays, preserving only diagnostically critical regions. This process transforms the image into a highly compressed, graph representation. This unified graph-based representation fuses the pruned visual graph with a knowledge graph derived from the clinical report, creating a universal data structure that simplifies downstream modeling. Validated on the MIMIC-CXR and CheXpert Plus dataset for pneumonia detection, NEURAL achieves a 93.4-97.7\% reduction in image data size while maintaining a high diagnostic performance of 0.88-0.95 AUC, outperforming other baseline models that use uncompressed data. By creating a persistent, task-agnostic data asset, NEURAL resolves the trade-off between data size and clinical utility, enabling efficient workflows and teleradiology without sacrificing performance. Our NEURAL code is available at https://github.com/basiralab/NEURAL.

☆ MangaDiT: Reference-Guided Line Art Colorization with Hierarchical Attention in Diffusion Transformers

Qianru Qiu, Jiafeng Mao, Kento Masui, Xueting Wang

Recent advances in diffusion models have significantly improved the performance of reference-guided line art colorization. However, existing methods still struggle with region-level color consistency, especially when the reference and target images differ in character pose or motion. Instead of relying on external matching annotations between the reference and target, we propose to discover semantic correspondences implicitly through internal attention mechanisms. In this paper, we present MangaDiT, a powerful model for reference-guided line art colorization based on Diffusion Transformers (DiT). Our model takes both line art and reference images as conditional inputs and introduces a hierarchical attention mechanism with a dynamic attention weighting strategy. This mechanism augments the vanilla attention with an additional context-aware path that leverages pooled spatial features, effectively expanding the model's receptive field and enhancing region-level color alignment. Experiments on two benchmark datasets demonstrate that our method significantly outperforms state-of-the-art approaches, achieving superior performance in both qualitative and quantitative evaluations.

comment: Codes and benchmarks will be released soon

☆ Slot Attention-based Feature Filtering for Few-Shot Learning

Javier Rodenas, Eduardo Aguilar, Petia Radeva

Irrelevant features can significantly degrade few-shot learn ing performance. This problem is used to match queries and support images based on meaningful similarities despite the limited data. However, in this process, non-relevant fea tures such as background elements can easily lead to confu sion and misclassification. To address this issue, we pro pose Slot Attention-based Feature Filtering for Few-Shot Learning (SAFF) that leverages slot attention mechanisms to discriminate and filter weak features, thereby improving few-shot classification performance. The key innovation of SAFF lies in its integration of slot attention with patch em beddings, unifying class-aware slots into a single attention mechanism to filter irrelevant features effectively. We intro duce a similarity matrix that computes across support and query images to quantify the relevance of filtered embed dings for classification. Through experiments, we demon strate that Slot Attention performs better than other atten tion mechanisms, capturing discriminative features while reducing irrelevant information. We validate our approach through extensive experiments on few-shot learning bench marks: CIFAR-FS, FC100, miniImageNet and tieredIma geNet, outperforming several state-of-the-art methods.

comment: CVPR Workshop LatinX 2025

☆ Combating Noisy Labels via Dynamic Connection Masking

Xinlei Zhang, Fan Liu, Chuanyi Zhang, Fan Cheng, Yuhui Zheng

Noisy labels are inevitable in real-world scenarios. Due to the strong capacity of deep neural networks to memorize corrupted labels, these noisy labels can cause significant performance degradation. Existing research on mitigating the negative effects of noisy labels has mainly focused on robust loss functions and sample selection, with comparatively limited exploration of regularization in model architecture. Inspired by the sparsity regularization used in Kolmogorov-Arnold Networks (KANs), we propose a Dynamic Connection Masking (DCM) mechanism for both Multi-Layer Perceptron Networks (MLPs) and KANs to enhance the robustness of classifiers against noisy labels. The mechanism can adaptively mask less important edges during training by evaluating their information-carrying capacity. Through theoretical analysis, we demonstrate its efficiency in reducing gradient error. Our approach can be seamlessly integrated into various noise-robust training methods to build more robust deep networks, including robust loss functions, sample selection strategies, and regularization techniques. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our method consistently outperforms state-of-the-art (SOTA) approaches. Furthermore, we are also the first to investigate KANs as classifiers against noisy labels, revealing their superior noise robustness over MLPs in real-world noisy scenarios. Our code will soon be publicly available.

☆ PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training

Yin Xie, Zhichao Chen, Xiaoze Yu, Yongle Zhao, Xiang An, Kaicheng Yang, Zimin Ran, Jia Guo, Ziyong Feng, Jiankang Deng

Facial representation pre-training is crucial for tasks like facial recognition, expression analysis, and virtual reality. However, existing methods face three key challenges: (1) failing to capture distinct facial features and fine-grained semantics, (2) ignoring the spatial structure inherent to facial anatomy, and (3) inefficiently utilizing limited labeled data. To overcome these, we introduce PaCo-FR, an unsupervised framework that combines masked image modeling with patch-pixel alignment. Our approach integrates three innovative components: (1) a structured masking strategy that preserves spatial coherence by aligning with semantically meaningful facial regions, (2) a novel patch-based codebook that enhances feature discrimination with multiple candidate tokens, and (3) spatial consistency constraints that preserve geometric relationships between facial components. PaCo-FR achieves state-of-the-art performance across several facial analysis tasks with just 2 million unlabeled images for pre-training. Our method demonstrates significant improvements, particularly in scenarios with varying poses, occlusions, and lighting conditions. We believe this work advances facial representation learning and offers a scalable, efficient solution that reduces reliance on expensive annotated datasets, driving more effective facial analysis systems.

☆ Surg-InvNeRF: Invertible NeRF for 3D tracking and reconstruction in surgical vision

Gerardo Loza, Junlei Hu, Dominic Jones, Sharib Ali, Pietro Valdastri

We proposed a novel test-time optimisation (TTO) approach framed by a NeRF-based architecture for long-term 3D point tracking. Most current methods in point tracking struggle to obtain consistent motion or are limited to 2D motion. TTO approaches frame the solution for long-term tracking as optimising a function that aggregates correspondences from other specialised state-of-the-art methods. Unlike the state-of-the-art on TTO, we propose parametrising such a function with our new invertible Neural Radiance Field (InvNeRF) architecture to perform both 2D and 3D tracking in surgical scenarios. Our approach allows us to exploit the advantages of a rendering-based approach by supervising the reprojection of pixel correspondences. It adapts strategies from recent rendering-based methods to obtain a bidirectional deformable-canonical mapping, to efficiently handle a defined workspace, and to guide the rays' density. It also presents our multi-scale HexPlanes for fast inference and a new algorithm for efficient pixel sampling and convergence criteria. We present results in the STIR and SCARE datasets, for evaluating point tracking and testing the integration of kinematic data in our pipeline, respectively. In 2D point tracking, our approach surpasses the precision and accuracy of the TTO state-of-the-art methods by nearly 50% on average precision, while competing with other approaches. In 3D point tracking, this is the first TTO approach, surpassing feed-forward methods while incorporating the benefits of a deformable NeRF-based reconstruction.

comment: 10 pages

☆ GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

Xingyilang Yin, Qi Zhang, Jiahao Chang, Ying Feng, Qingnan Fan, Xi Yang, Chi-Man Pun, Huaqi Zhang, Xiaodong Cun

Reconstructing 3D scenes using 3D Gaussian Splatting (3DGS) from sparse views is an ill-posed problem due to insufficient information, often resulting in noticeable artifacts. While recent approaches have sought to leverage generative priors to complete information for under-constrained regions, they struggle to generate content that remains consistent with input observations. To address this challenge, we propose GSFixer, a novel framework designed to improve the quality of 3DGS representations reconstructed from sparse inputs. The core of our approach is the reference-guided video restoration model, built upon a DiT-based video diffusion model trained on paired artifact 3DGS renders and clean frames with additional reference-based conditions. Considering the input sparse views as references, our model integrates both 2D semantic features and 3D geometric features of reference views extracted from the visual geometry foundation model, enhancing the semantic coherence and 3D consistency when fixing artifact novel views. Furthermore, considering the lack of suitable benchmarks for 3DGS artifact restoration evaluation, we present DL3DV-Res which contains artifact frames rendered using low-quality 3DGS. Extensive experiments demonstrate our GSFixer outperforms current state-of-the-art methods in 3DGS artifact restoration and sparse-view 3D reconstruction. Project page: https://github.com/GVCLab/GSFixer.

☆ NegFaceDiff: The Power of Negative Context in Identity-Conditioned Diffusion for Synthetic Face Generation

Eduarda Caldeira, Naser Damer, Fadi Boutros

The use of synthetic data as an alternative to authentic datasets in face recognition (FR) development has gained significant attention, addressing privacy, ethical, and practical concerns associated with collecting and using authentic data. Recent state-of-the-art approaches have proposed identity-conditioned diffusion models to generate identity-consistent face images, facilitating their use in training FR models. However, these methods often lack explicit sampling mechanisms to enforce inter-class separability, leading to identity overlap in the generated data and, consequently, suboptimal FR performance. In this work, we introduce NegFaceDiff, a novel sampling method that incorporates negative conditions into the identity-conditioned diffusion process. NegFaceDiff enhances identity separation by leveraging negative conditions that explicitly guide the model away from unwanted features while preserving intra-class consistency. Extensive experiments demonstrate that NegFaceDiff significantly improves the identity consistency and separability of data generated by identity-conditioned diffusion models. Specifically, identity separability, measured by the Fisher Discriminant Ratio (FDR), increases from 2.427 to 5.687. These improvements are reflected in FR systems trained on the NegFaceDiff dataset, which outperform models trained on data generated without negative conditions across multiple benchmarks.

comment: Accepted at ICCV Workshops

☆ Noise-adapted Neural Operator for Robust Non-Line-of-Sight Imaging

Lianfang Wang, Kuilin Qin, Xueying Liu, Huibin Chang, Yong Wang, Yuping Duan

Computational imaging, especially non-line-of-sight (NLOS) imaging, the extraction of information from obscured or hidden scenes is achieved through the utilization of indirect light signals resulting from multiple reflections or scattering. The inherently weak nature of these signals, coupled with their susceptibility to noise, necessitates the integration of physical processes to ensure accurate reconstruction. This paper presents a parameterized inverse problem framework tailored for large-scale linear problems in 3D imaging reconstruction. Initially, a noise estimation module is employed to adaptively assess the noise levels present in transient data. Subsequently, a parameterized neural operator is developed to approximate the inverse mapping, facilitating end-to-end rapid image reconstruction. Our 3D image reconstruction framework, grounded in operator learning, is constructed through deep algorithm unfolding, which not only provides commendable model interpretability but also enables dynamic adaptation to varying noise levels in the acquired data, thereby ensuring consistently robust and accurate reconstruction outcomes. Furthermore, we introduce a novel method for the fusion of global and local spatiotemporal data features. By integrating structural and detailed information, this method significantly enhances both accuracy and robustness. Comprehensive numerical experiments conducted on both simulated and real datasets substantiate the efficacy of the proposed method. It demonstrates remarkable performance with fast scanning data and sparse illumination point data, offering a viable solution for NLOS imaging in complex scenarios.

☆ TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos

Hao Xu, Arbind Agrahari Baniya, Sam Wells, Mohamed Reda Bouadjenek, Richard Dazely, Sunil Aryal

Robust ball tracking under occlusion remains a key challenge in sports video analysis, affecting tasks like event detection and officiating. We present TOTNet, a Temporal Occlusion Tracking Network that leverages 3D convolutions, visibility-weighted loss, and occlusion augmentation to improve performance under partial and full occlusions. Developed in collaboration with Paralympics Australia, TOTNet is designed for real-world sports analytics. We introduce TTA, a new occlusion-rich table tennis dataset collected from professional-level Paralympic matches, comprising 9,159 samples with 1,996 occlusion cases. Evaluated on four datasets across tennis, badminton, and table tennis, TOTNet significantly outperforms prior state-of-the-art methods, reducing RMSE from 37.30 to 7.19 and improving accuracy on fully occluded frames from 0.63 to 0.80. These results demonstrate TOTNets effectiveness for offline sports analytics in fast-paced scenarios. Code and data access:\href{https://github.com/AugustRushG/TOTNet}{AugustRushG/TOTNet}.

comment: 8 pages, 6 figures,

☆ The Brain Resection Multimodal Image Registration (ReMIND2Reg) 2025 Challenge

Reuben Dorent, Laura Rigolo, Colin P. Galvin, Junyu Chen, Mattias P. Heinrich, Aaron Carass, Olivier Colliot, Demian Wassermann, Alexandra Golby, Tina Kapur, William Wells

Accurate intraoperative image guidance is critical for achieving maximal safe resection in brain tumor surgery, yet neuronavigation systems based on preoperative MRI lose accuracy during the procedure due to brain shift. Aligning post-resection intraoperative ultrasound (iUS) with preoperative MRI can restore spatial accuracy by estimating brain shift deformations, but it remains a challenging problem given the large anatomical and topological changes and substantial modality intensity gap. The ReMIND2Reg 2025 Challenge provides the largest public benchmark for this task, built upon the ReMIND dataset. It offers 99 training cases, 5 validation cases, and 10 private test cases comprising paired 3D ceT1 MRI, T2 MRI, and post-resection 3D iUS volumes. Data are provided without annotations for training, while validation and test performance are evaluated on manually annotated anatomical landmarks. Metrics include target registration error (TRE), robustness to worst-case landmark misalignment (TRE30), and runtime. By establishing a standardized evaluation framework for this clinically critical and technically complex problem, ReMIND2Reg aims to accelerate the development of robust, generalizable, and clinically deployable multimodal registration algorithms for image-guided neurosurgery.

☆ Multi-Sequence Parotid Gland Lesion Segmentation via Expert Text-Guided Segment Anything Model

Zhongyuan Wu, Chuan-Xian Ren, Yu Wang, Xiaohua Ban, Jianning Xiao, Xiaohui Duan

Parotid gland lesion segmentation is essential for the treatment of parotid gland diseases. However, due to the variable size and complex lesion boundaries, accurate parotid gland lesion segmentation remains challenging. Recently, the Segment Anything Model (SAM) fine-tuning has shown remarkable performance in the field of medical image segmentation. Nevertheless, SAM's interaction segmentation model relies heavily on precise lesion prompts (points, boxes, masks, etc.), which are very difficult to obtain in real-world applications. Besides, current medical image segmentation methods are automatically generated, ignoring the domain knowledge of medical experts when performing segmentation. To address these limitations, we propose the parotid gland segment anything model (PG-SAM), an expert diagnosis text-guided SAM incorporating expert domain knowledge for cross-sequence parotid gland lesion segmentation. Specifically, we first propose an expert diagnosis report guided prompt generation module that can automatically generate prompt information containing the prior domain knowledge to guide the subsequent lesion segmentation process. Then, we introduce a cross-sequence attention module, which integrates the complementary information of different modalities to enhance the segmentation effect. Finally, the multi-sequence image features and generated prompts are feed into the decoder to get segmentation result. Experimental results demonstrate that PG-SAM achieves state-of-the-art performance in parotid gland lesion segmentation across three independent clinical centers, validating its clinical applicability and the effectiveness of diagnostic text for enhancing image segmentation in real-world clinical settings.

☆ Multi-Contrast Fusion Module: An attention mechanism integrating multi-contrast features for fetal torso plane classification

Shengjun Zhu, Siyu Liu, Runqing Xiong, Liping Zheng, Duo Ma, Rongshang Chen, Jiaxin Cai

Purpose: Prenatal ultrasound is a key tool in evaluating fetal structural development and detecting abnormalities, contributing to reduced perinatal complications and improved neonatal survival. Accurate identification of standard fetal torso planes is essential for reliable assessment and personalized prenatal care. However, limitations such as low contrast and unclear texture details in ultrasound imaging pose significant challenges for fine-grained anatomical recognition. Methods: We propose a novel Multi-Contrast Fusion Module (MCFM) to enhance the model's ability to extract detailed information from ultrasound images. MCFM operates exclusively on the lower layers of the neural network, directly processing raw ultrasound data. By assigning attention weights to image representations under different contrast conditions, the module enhances feature modeling while explicitly maintaining minimal parameter overhead. Results: The proposed MCFM was evaluated on a curated dataset of fetal torso plane ultrasound images. Experimental results demonstrate that MCFM substantially improves recognition performance, with a minimal increase in model complexity. The integration of multi-contrast attention enables the model to better capture subtle anatomical structures, contributing to higher classification accuracy and clinical reliability. Conclusions: Our method provides an effective solution for improving fetal torso plane recognition in ultrasound imaging. By enhancing feature representation through multi-contrast fusion, the proposed approach supports clinicians in achieving more accurate and consistent diagnoses, demonstrating strong potential for clinical adoption in prenatal screening. The codes are available at https://github.com/sysll/MCFM.

☆ Preacher: Paper-to-Video Agentic System

Jingwei Liu, Ling Yang, Hao Luo, Fan Wang Hongyan Li, Mengdi Wang

The paper-to-video task converts a research paper into a structured video abstract, distilling key concepts, methods, and conclusions into an accessible, well-organized format. While state-of-the-art video generation models demonstrate potential, they are constrained by limited context windows, rigid video duration constraints, limited stylistic diversity, and an inability to represent domain-specific knowledge. To address these limitations, we introduce Preacher, the first paper-to-video agentic system. Preacher employs a top-down approach to decompose, summarize, and reformulate the paper, followed by bottom-up video generation, synthesizing diverse video segments into a coherent abstract. To align cross-modal representations, we define key scenes and introduce a Progressive Chain of Thought (P-CoT) for granular, iterative planning. Preacher successfully generates high-quality video abstracts across five research fields, demonstrating expertise beyond current video generation models. Code will be released at: https://github.com/GenVerse/Paper2Video

☆ Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors

Giorgos Karvounas, Nikolaos Kyriazis, Iason Oikonomidis, Georgios Pavlakos, Antonis A. Argyros

We revisit the role of texture in monocular 3D hand reconstruction, not as an afterthought for photorealism, but as a dense, spatially grounded cue that can actively support pose and shape estimation. Our observation is simple: even in high-performing models, the overlay between predicted hand geometry and image appearance is often imperfect, suggesting that texture alignment may be an underused supervisory signal. We propose a lightweight texture module that embeds per-pixel observations into UV texture space and enables a novel dense alignment loss between predicted and observed hand appearances. Our approach assumes access to a differentiable rendering pipeline and a model that maps images to 3D hand meshes with known topology, allowing us to back-project a textured hand onto the image and perform pixel-based alignment. The module is self-contained and easily pluggable into existing reconstruction pipelines. To isolate and highlight the value of texture-guided supervision, we augment HaMeR, a high-performing yet unadorned transformer architecture for 3D hand pose estimation. The resulting system improves both accuracy and realism, demonstrating the value of appearance-guided alignment in hand reconstruction.

☆ Semantic-aware DropSplat: Adaptive Pruning of Redundant Gaussians for 3D Aerial-View Segmentation AAAI 2026

Xu Tang, Junan Jia, Yijing Wang, Jingjing Ma, Xiangrong Zhang

comment: 9 pages, 4 figures, AAAI 2026

☆ Plane Detection and Ranking via Model Information Optimization

Daoxin Zhong, Jun Li, Meng Yee Michael Chuah

Plane detection from depth images is a crucial subtask with broad robotic applications, often accomplished by iterative methods such as Random Sample Consensus (RANSAC). While RANSAC is a robust strategy with strong probabilistic guarantees, the ambiguity of its inlier threshold criterion makes it susceptible to false positive plane detections. This issue is particularly prevalent in complex real-world scenes, where the true number of planes is unknown and multiple planes coexist. In this paper, we aim to address this limitation by proposing a generalised framework for plane detection based on model information optimization. Building on previous works, we treat the observed depth readings as discrete random variables, with their probability distributions constrained by the ground truth planes. Various models containing different candidate plane constraints are then generated through repeated random sub-sampling to explain our observations. By incorporating the physics and noise model of the depth sensor, we can calculate the information for each model, and the model with the least information is accepted as the most likely ground truth. This information optimization process serves as an objective mechanism for determining the true number of planes and preventing false positive detections. Additionally, the quality of each detected plane can be ranked by summing the information reduction of inlier points for each plane. We validate these properties through experiments with synthetic data and find that our algorithm estimates plane parameters more accurately compared to the default Open3D RANSAC plane segmentation. Furthermore, we accelerate our algorithm by partitioning the depth map using neural network segmentation, which enhances its ability to generate more realistic plane parameters in real-world data.

comment: Accepted as contributed paper in the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

☆ MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography

Daniel Barco, Marc Stadelmann, Martin Oswald, Ivo Herzig, Lukas Lichtensteiger, Pascal Paysan, Igor Peterlik, Michal Walczak, Bjoern Menze, Frank-Peter Schilling

We present MInDI-3D (Medical Inversion by Direct Iteration in 3D), the first 3D conditional diffusion-based model for real-world sparse-view Cone Beam Computed Tomography (CBCT) artefact removal, aiming to reduce imaging radiation exposure. A key contribution is extending the "InDI" concept from 2D to a full 3D volumetric approach for medical images, implementing an iterative denoising process that refines the CBCT volume directly from sparse-view input. A further contribution is the generation of a large pseudo-CBCT dataset (16,182) from chest CT volumes of the CT-RATE public dataset to robustly train MInDI-3D. We performed a comprehensive evaluation, including quantitative metrics, scalability analysis, generalisation tests, and a clinical assessment by 11 clinicians. Our results show MInDI-3D's effectiveness, achieving a 12.96 (6.10) dB PSNR gain over uncorrected scans with only 50 projections on the CT-RATE pseudo-CBCT (independent real-world) test set and enabling an 8x reduction in imaging radiation exposure. We demonstrate its scalability by showing that performance improves with more training data. Importantly, MInDI-3D matches the performance of a 3D U-Net on real-world scans from 16 cancer patients across distortion and task-based metrics. It also generalises to new CBCT scanner geometries. Clinicians rated our model as sufficient for patient positioning across all anatomical sites and found it preserved lung tumour boundaries well.

☆ BridgeTA: Bridging the Representation Gap in Knowledge Distillation via Teacher Assistant for Bird's Eye View Map Segmentation

Beomjun Kim, Suhan Woo, Sejong Heo, Euntai Kim

Bird's-Eye-View (BEV) map segmentation is one of the most important and challenging tasks in autonomous driving. Camera-only approaches have drawn attention as cost-effective alternatives to LiDAR, but they still fall behind LiDAR-Camera (LC) fusion-based methods. Knowledge Distillation (KD) has been explored to narrow this gap, but existing methods mainly enlarge the student model by mimicking the teacher's architecture, leading to higher inference cost. To address this issue, we introduce BridgeTA, a cost-effective distillation framework to bridge the representation gap between LC fusion and Camera-only models through a Teacher Assistant (TA) network while keeping the student's architecture and inference cost unchanged. A lightweight TA network combines the BEV representations of the teacher and student, creating a shared latent space that serves as an intermediate representation. To ground the framework theoretically, we derive a distillation loss using Young's Inequality, which decomposes the direct teacher-student distillation path into teacher-TA and TA-student dual paths, stabilizing optimization and strengthening knowledge transfer. Extensive experiments on the challenging nuScenes dataset demonstrate the effectiveness of our method, achieving an improvement of 4.2% mIoU over the Camera-only baseline, up to 45% higher than the improvement of other state-of-the-art KD methods.

comment: 9 pages, 6 figures

☆ Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality

Jie Shao, Ke Zhu, Minghao Fu, Guo-hua Wang, Jianxin Wu

Diffusion models have achieved remarkable progress in class-to-image generation. However, we observe that despite impressive FID scores, state-of-the-art models often generate distorted or low-quality images, especially in certain classes. This gap arises because FID evaluates global distribution alignment, while ignoring the perceptual quality of individual samples. We further examine the role of CFG, a common technique used to enhance generation quality. While effective in improving metrics and suppressing outliers, CFG can introduce distribution shift and visual artifacts due to its misalignment with both training objectives and user expectations. In this work, we propose FaME, a training-free and inference-efficient method for improving perceptual quality. FaME uses an image quality assessment model to identify low-quality generations and stores their sampling trajectories. These failure modes are then used as negative guidance to steer future sampling away from poor-quality regions. Experiments on ImageNet demonstrate that FaME brings consistent improvements in visual quality without compromising FID. FaME also shows the potential to be extended to improve text-to-image generation.

☆ SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

Heyi Sun, Cong Wang, Tian-Xing Xu, Jingwei Huang, Di Kang, Chunchao Guo, Song-Hai Zhang

☆ Hierarchical Brain Structure Modeling for Predicting Genotype of Glioma

Haotian Tang, Jianwei Chen, Xinrui Tang, Yunjia Wu, Zhengyang Miao, Chao Li

Isocitrate DeHydrogenase (IDH) mutation status is a crucial biomarker for glioma prognosis. However, current prediction methods are limited by the low availability and noise of functional MRI. Structural and morphological connectomes offer a non-invasive alternative, yet existing approaches often ignore the brain's hierarchical organisation and multiscale interactions. To address this, we propose Hi-SMGNN, a hierarchical framework that integrates structural and morphological connectomes from regional to modular levels. It features a multimodal interaction module with a Siamese network and cross-modal attention, a multiscale feature fusion mechanism for reducing redundancy, and a personalised modular partitioning strategy to enhance individual specificity and interpretability. Experiments on the UCSF-PDGM dataset demonstrate that Hi-SMGNN outperforms baseline and state-of-the-art models, showing improved robustness and effectiveness in IDH mutation prediction.

☆ Offline Auto Labeling: BAAS

Stefan Haag, Bharanidhar Duraisamy, Felix Govaers, Wolfgang Koch, Martin Fritzsche, Juergen Dickmann

This paper introduces BAAS, a new Extended Object Tracking (EOT) and fusion-based label annotation framework for radar detections in autonomous driving. Our framework utilizes Bayesian-based tracking, smoothing and eventually fusion methods to provide veritable and precise object trajectories along with shape estimation to provide annotation labels on the detection level under various supervision levels. Simultaneously, the framework provides evaluation of tracking performance and label annotation. If manually labeled data is available, each processing module can be analyzed independently or combined with other modules to enable closed-loop continuous improvements. The framework performance is evaluated in a challenging urban real-world scenario in terms of tracking performance and the label annotation errors. We demonstrate the functionality of the proposed approach for varying dynamic objects and class types

☆ SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs

Bei Yan, Zhiyuan Chen, Yuecong Min, Jie Zhang, Jiahao Wang, Xiaozhen Wang, Shiguang Shan

Despite rapid advances, Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge, which correspond to faithfulness and factuality hallucinations, respectively. Prior studies primarily evaluate faithfulness hallucination at a coarse level (e.g., object-level) and lack fine-grained analysis. Additionally, existing benchmarks rely on costly manual curation or reused public datasets, raising concerns about scalability and data leakage. To address these limitations, we propose an automated data construction pipeline that produces scalable, controllable, and diverse evaluation data. We also design a hierarchical hallucination induction framework with input perturbations to simulate realistic noisy scenarios. Integrating these designs, we construct SHALE, a Scalable HALlucination Evaluation benchmark designed to assess both faithfulness and factuality hallucinations via a fine-grained hallucination categorization scheme. SHALE comprises over 30K image-instruction pairs spanning 12 representative visual perception aspects for faithfulness and 6 knowledge domains for factuality, considering both clean and noisy scenarios. Extensive experiments on over 20 mainstream LVLMs reveal significant factuality hallucinations and high sensitivity to semantic perturbations.

☆ Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion

Jiwon Kim, Pureum Kim, SeonHwa Kim, Soobin Park, Eunju Cha, Kyong Hwan Jin

Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring auxiliary module training. However, these models often struggle to accurately preserve spatial structures and fail to capture fine-grained conditions related to object poses and scene layouts. To address these challenges, we propose a training-free Dual Recursive Feedback (DRF) system that properly reflects control conditions in controllable T2I models. The proposed DRF consists of appearance feedback and generation feedback that recursively refines the intermediate latents to better reflect the given appearance information and the user's intent. This dual-update mechanism guides latent representations toward reliable manifolds, effectively integrating structural and appearance attributes. Our approach enables fine-grained generation even between class-invariant structure-appearance fusion, such as transferring human motion onto a tiger's form. Extensive experiments demonstrate the efficacy of our method in producing high-quality, semantically coherent, and structurally consistent image generations. Our source code is available at https://github.com/jwonkm/DRF.

☆ A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation

Haibo Jin, Haoxuan Che, Sunan He, Hao Chen

Despite the progress of radiology report generation (RRG), existing works face two challenges: 1) The performances in clinical efficacy are unsatisfactory, especially for lesion attributes description; 2) the generated text lacks explainability, making it difficult for radiologists to trust the results. To address the challenges, we focus on a trustworthy RRG model, which not only generates accurate descriptions of abnormalities, but also provides basis of its predictions. To this end, we propose a framework named chain of diagnosis (CoD), which maintains a chain of diagnostic process for clinically accurate and explainable RRG. It first generates question-answer (QA) pairs via diagnostic conversation to extract key findings, then prompts a large language model with QA diagnoses for accurate generation. To enhance explainability, a diagnosis grounding module is designed to match QA diagnoses and generated sentences, where the diagnoses act as a reference. Moreover, a lesion grounding module is designed to locate abnormalities in the image, further improving the working efficiency of radiologists. To facilitate label-efficient training, we propose an omni-supervised learning strategy with clinical consistency to leverage various types of annotations from different datasets. Our efforts lead to 1) an omni-labeled RRG dataset with QA pairs and lesion boxes; 2) a evaluation tool for assessing the accuracy of reports in describing lesion location and severity; 3) extensive experiments to demonstrate the effectiveness of CoD, where it outperforms both specialist and generalist models consistently on two RRG benchmarks and shows promising explainability by accurately grounding generated sentences to QA diagnoses and images.

comment: Accepted to IEEE TMI

☆ WEC-DG: Multi-Exposure Wavelet Correction Method Guided by Degradation Description

Ming Zhao, Pingping Liu, Tongshun Zhang, Zhe Zhang

Multi-exposure correction technology is essential for restoring images affected by insufficient or excessive lighting, enhancing the visual experience by improving brightness, contrast, and detail richness. However, current multi-exposure correction methods often encounter challenges in addressing intra-class variability caused by diverse lighting conditions, shooting environments, and weather factors, particularly when processing images captured at a single exposure level. To enhance the adaptability of these models under complex imaging conditions, this paper proposes a Wavelet-based Exposure Correction method with Degradation Guidance (WEC-DG). Specifically, we introduce a degradation descriptor within the Exposure Consistency Alignment Module (ECAM) at both ends of the processing pipeline to ensure exposure consistency and achieve final alignment. This mechanism effectively addresses miscorrected exposure anomalies caused by existing methods' failure to recognize 'blurred' exposure degradation. Additionally, we investigate the light-detail decoupling properties of the wavelet transform to design the Exposure Restoration and Detail Reconstruction Module (EDRM), which processes low-frequency information related to exposure enhancement before utilizing high-frequency information as a prior guide for reconstructing spatial domain details. This serial processing strategy guarantees precise light correction and enhances detail recovery. Extensive experiments conducted on multiple public datasets demonstrate that the proposed method outperforms existing algorithms, achieving significant performance improvements and validating its effectiveness and practical applicability.

☆ WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization

Jiahao Wen, Hang Yu, Zhedong Zheng

Visual geo-localization for drones faces critical degradation under weather perturbations, \eg, rain and fog, where existing methods struggle with two inherent limitations: 1) Heavy reliance on limited weather categories that constrain generalization, and 2) Suboptimal disentanglement of entangled scene-weather features through pseudo weather categories. We present WeatherPrompt, a multi-modality learning paradigm that establishes weather-invariant representations through fusing the image embedding with the text context. Our framework introduces two key contributions: First, a Training-free Weather Reasoning mechanism that employs off-the-shelf large multi-modality models to synthesize multi-weather textual descriptions through human-like reasoning. It improves the scalability to unseen or complex weather, and could reflect different weather strength. Second, to better disentangle the scene and weather feature, we propose a multi-modality framework with the dynamic gating mechanism driven by the text embedding to adaptively reweight and fuse visual features across modalities. The framework is further optimized by the cross-modal objectives, including image-text contrastive learning and image-text matching, which maps the same scene with different weather conditions closer in the respresentation space. Extensive experiments validate that, under diverse weather conditions, our method achieves competitive recall rates compared to state-of-the-art drone geo-localization methods. Notably, it improves Recall@1 by +13.37\% under night conditions and by 18.69\% under fog and snow conditions.

comment: 13 pages, 4figures

☆ Topological Invariant-Based Iris Identification via Digital Homology and Machine Learning

Ahmet Öztel, İsmet Karaca

Objective - This study presents a biometric identification method based on topological invariants from 2D iris images, representing iris texture via formally defined digital homology and evaluating classification performance. Methods - Each normalized iris image (48x482 pixels) is divided into grids (e.g., 6x54 or 3x27). For each subregion, we compute Betti0, Betti1, and their ratio using a recent algorithm for homology groups in 2D digital images. The resulting invariants form a feature matrix used with logistic regression, KNN, and SVM (with PCA and 100 randomized repetitions). A convolutional neural network (CNN) is trained on raw images for comparison. Results - Logistic regression achieved 97.78 +/- 0.82% accuracy, outperforming CNN (96.44 +/- 1.32%) and other feature-based models. The topological features showed high accuracy with low variance. Conclusion - This is the first use of topological invariants from formal digital homology for iris recognition. The method offers a compact, interpretable, and accurate alternative to deep learning, useful when explainability or limited data is important. Beyond iris recognition, it can apply to other biometrics, medical imaging, materials science, remote sensing, and interpretable AI. It runs efficiently on CPU-only systems and produces robust, explainable features valuable for security-critical domains.

comment: 10 pages, 5 figures, includes visual abstract, focuses on topological invariants for iris recognition

☆ Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification

Haowen Wang, Guowei Zhang, Xiang Zhang, Zeyuan Chen, Haiyang Xu, Dou Hoon Kwark, Zhuowen Tu

In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to enhance the classification performance? (i.e., closed-set generative data augmentation). We start by exploring the distinctions and similarities between real images and closed-set synthetic images generated by advanced generative models. Through extensive experiments, we offer systematic insights into the effective use of closed-set synthetic data for augmentation. Notably, we empirically determine the equivalent scale of synthetic images needed for augmentation. In addition, we also show quantitative equivalence between the real data augmentation and open-set generative augmentation (generative models trained using data beyond the given training set). While it aligns with the common intuition that real images are generally preferred, our empirical formulation also offers a guideline to quantify the increased scale of synthetic data augmentation required to achieve comparable image classification performance. Our results on natural and medical image datasets further illustrate how this effect varies with the baseline training set size and the amount of synthetic data incorporated.

☆ GoViG: Goal-Conditioned Visual Navigation Instruction Generation

Fengyi Wu, Yifei Dong, Zhi-Qi Cheng, Yilong Dai, Guangyu Chen, Hang Wang, Qi Dai, Alexander G. Hauptmann

We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to autonomously generate precise and contextually coherent navigation instructions solely from egocentric visual observations of initial and goal states. Unlike conventional approaches that rely on structured inputs such as semantic annotations or environmental maps, GoViG exclusively leverages raw egocentric visual data, substantially improving its adaptability to unseen and unstructured environments. Our method addresses this task by decomposing it into two interconnected subtasks: (1) visual forecasting, which predicts intermediate visual states bridging the initial and goal views; and (2) instruction generation, which synthesizes linguistically coherent instructions grounded in both observed and anticipated visuals. These subtasks are integrated within an autoregressive multimodal large language model trained with tailored objectives to ensure spatial accuracy and linguistic clarity. Furthermore, we introduce two complementary multimodal reasoning strategies, one-pass and interleaved reasoning, to mimic incremental human cognitive processes during navigation. To evaluate our method, we propose the R2R-Goal dataset, combining diverse synthetic and real-world trajectories. Empirical results demonstrate significant improvements over state-of-the-art methods, achieving superior BLEU-4 and CIDEr scores along with robust cross-domain generalization.

comment: Under review. Code: https://github.com/F1y1113/GoViG

☆ Iterative Volume Fusion for Asymmetric Stereo Matching

Yuanting Gao, Linghao Shen

☆ COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection

Peiran Peng, Tingfa Xu, Liqiang Song, Mengqi Zhu, Yuqiang Fang, Jianan Li

Detecting tiny objects in multimodal Red-Green-Blue-Thermal (RGBT) imagery is a critical challenge in computer vision, particularly in surveillance, search and rescue, and autonomous navigation. Drone-based scenarios exacerbate these challenges due to spatial misalignment, low-light conditions, occlusion, and cluttered backgrounds. Current methods struggle to leverage the complementary information between visible and thermal modalities effectively. We propose COXNet, a novel framework for RGBT tiny object detection, addressing these issues through three core innovations: i) the Cross-Layer Fusion Module, fusing high-level visible and low-level thermal features for enhanced semantic and spatial accuracy; ii) the Dynamic Alignment and Scale Refinement module, correcting cross-modal spatial misalignments and preserving multi-scale features; and iii) an optimized label assignment strategy using the GeoShape Similarity Measure for better localization. COXNet achieves a 3.32\% mAP$_{50}$ improvement on the RGBTDronePerson dataset over state-of-the-art methods, demonstrating its effectiveness for robust detection in complex environments.

☆ Physics-guided Deep Unfolding Network for Enhanced Kronecker Compressive sensing

Gang Qu, Ping Wang, Siming Zheng, Xin Yuan

Deep networks have achieved remarkable success in image compressed sensing (CS) task, namely reconstructing a high-fidelity image from its compressed measurement. However, existing works are deficient inincoherent compressed measurement at sensing phase and implicit measurement representations at reconstruction phase, limiting the overall performance. In this work, we answer two questions: 1) how to improve the measurement incoherence for decreasing the ill-posedness; 2) how to learn informative representations from measurements. To this end, we propose a novel asymmetric Kronecker CS (AKCS) model and theoretically present its better incoherence than previous Kronecker CS with minimal complexity increase. Moreover, we reveal that the unfolding networks' superiority over non-unfolding ones result from sufficient gradient descents, called explicit measurement representations. We propose a measurement-aware cross attention (MACA) mechanism to learn implicit measurement representations. We integrate AKCS and MACA into widely-used unfolding architecture to get a measurement-enhanced unfolding network (MEUNet). Extensive experiences demonstrate that our MEUNet achieves state-of-the-art performance in reconstruction accuracy and inference speed.

comment: 9 pages, 4 figures

☆ Learning Spatial Decay for Vision Transformers

Yuxin Mao, Zhen Qin, Jinxing Zhou, Bin Fan, Jing Zhang, Yiran Zhong, Yuchao Dai

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce data-independent spatial decay based on fixed distance metrics, applying uniform attention weighting regardless of image content and limiting adaptability to diverse visual scenarios. Inspired by recent advances in large language models where content-aware gating mechanisms (e.g., GLA, HGRN2, FOX) significantly outperform static alternatives, we present the first successful adaptation of data-dependent spatial decay to 2D vision transformers. We introduce \textbf{Spatial Decay Transformer (SDT)}, featuring a novel Context-Aware Gating (CAG) mechanism that generates dynamic, data-dependent decay for patch interactions. Our approach learns to modulate spatial attention based on both content relevance and spatial proximity. We address the fundamental challenge of 1D-to-2D adaptation through a unified spatial-content fusion framework that integrates manhattan distance-based spatial priors with learned content representations. Extensive experiments on ImageNet-1K classification and generation tasks demonstrate consistent improvements over strong baselines. Our work establishes data-dependent spatial decay as a new paradigm for enhancing spatial attention in vision transformers.

☆ SOI is the Root of All Evil: Quantifying and Breaking Similar Object Interference in Single Object Tracking

Yipei Wang, Shiyu Hu, Shukun Jia, Panxi Xu, Hongfei Ma, Yiping Ma, Jing Zhang, Xiaobo Lu, Xin Zhao

♻ ☆ Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models

Meng Cao, Pengfei Hu, Yingyao Wang, Jihao Gu, Haoran Tang, Haoze Zhao, Chen Wang, Jiahua Dong, Wangbo Yu, Ge Zhang, Jun Song, Xiang Li, Bo Zheng, Ian Reid, Xiaodan Liang

Recent advancements in Large Video Language Models (LVLMs) have highlighted their potential for multi-modal understanding, yet evaluating their factual grounding in videos remains a critical unsolved challenge. To address this gap, we introduce Video SimpleQA, the first comprehensive benchmark tailored for factuality evaluation in video contexts. Our work differs from existing video benchmarks through the following key features: 1) Knowledge required: demanding integration of external knowledge beyond the video's explicit narrative; 2) Multi-hop fact-seeking question: Each question involves multiple explicit facts and requires strict factual grounding without hypothetical or subjective inferences. We also include per-hop single-fact-based sub-QAs alongside final QAs to enable fine-grained, stepby-step evaluation; 3) Short-form definitive answer: Answers are crafted as unambiguous and definitively correct in a short format with minimal scoring variance; 4) Temporal grounded required: Requiring answers to rely on one or more temporal segments in videos, rather than single frames. We extensively evaluate 33 state-of-the-art LVLMs and summarize key findings as follows: 1) Current LVLMs exhibit notable deficiencies in factual adherence, with the best-performing model o3 merely achieving an F-score of 66.3%; 2) Most LVLMs are overconfident in what they generate, with self-stated confidence exceeding actual accuracy; 3) Retrieval-augmented generation demonstrates consistent improvements at the cost of additional inference time overhead; 4) Multi-hop QA demonstrates substantially degraded performance compared to single-hop sub-QAs, with first-hop object or event recognition emerging as the primary bottleneck. We position Video SimpleQA as the cornerstone benchmark for video factuality assessment, aiming to steer LVLM development toward verifiable grounding in real-world contexts.

♻ ☆ LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

Yiren Song, Danze Chen, Mike Zheng Shou

Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer based framework that bridges this gap by learning designers' layered SVG creation processes from a novel dataset of sequential design operations. Our approach operates in two phases: First, a text-conditioned DiT generates multi-phase rasterized construction blueprints that simulate human design workflows. Second, layer-wise vectorization with path deduplication produces clean, editable SVGs. For image vectorization, we introduce a conditional diffusion mechanism that encodes reference images into latent tokens, guiding hierarchical reconstruction while preserving structural integrity. Extensive experiments demonstrate LayerTracer's superior performance against optimization-based and neural baselines in both generation quality and editability, effectively aligning AI-generated vectors with professional design cognition.

♻ ☆ GenAI Confessions: Black-box Membership Inference for Generative Image Models

Matyas Bohacek, Hany Farid

From a simple text prompt, generative-AI image models can create stunningly realistic and creative images bounded, it seems, by only our imagination. These models have achieved this remarkable feat thanks, in part, to the ingestion of billions of images collected from nearly every corner of the internet. Many creators have understandably expressed concern over how their intellectual property has been ingested without their permission or a mechanism to opt out of training. As a result, questions of fair use and copyright infringement have quickly emerged. We describe a method that allows us to determine if a model was trained on a specific image or set of images. This method is computationally efficient and assumes no explicit knowledge of the model architecture or weights (so-called black-box membership inference). We anticipate that this method will be crucial for auditing existing models and, looking ahead, ensuring the fairer development and deployment of generative AI models.

comment: https://genai-confessions.github.io

♻ ☆ SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

Ziyang Gong, Wenhao Li, Oliver Ma, Songyuan Li, Jiayi Ji, Xue Yang, Gen Luo, Junchi Yan, Rongrong Ji

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in various multimodal tasks. To pursue higher intelligence in space, MLLMs require integrating multiple atomic spatial capabilities to handle complex and dynamic tasks. However, existing benchmarks struggle to comprehensively evaluate the spatial intelligence of common MLLMs from the atomic level to the compositional level. To fill this gap, we present SpaCE-10, a comprehensive benchmark for compositional spatial evaluations. In SpaCE-10, we define 10 atomic spatial capabilities, which are combined to form 8 compositional capabilities. Based on these definitions, we propose a novel hierarchical annotation pipeline to generate high-quality and diverse question-answer (QA) pairs. With over 150+ hours of human expert effort, we obtain over 5k QA pairs for 811 real indoor scenes in SpaCE-10, which covers various evaluation settings like point cloud input and multi-choice QA. We conduct an extensive evaluation of common MLLMs on SpaCE-10 and find that even the most advanced MLLM still lags behind humans by large margins. Through our careful study, we also draw several significant findings that benefit the MLLM community. For example, we reveal that the shortcoming of counting capability greatly limits the compositional spatial capabilities of existing MLLMs. The evaluation code and benchmark datasets are available at https://github.com/Cuzyoung/SpaCE-10.

♻ ☆ Grounding Emotion Recognition with Visual Prototypes: VEGA -- Revisiting CLIP in MERC ACM MM

Guanyu Hu, Dimitrios Kollias, Xinyu Yang

Multimodal Emotion Recognition in Conversations remains a challenging task due to the complex interplay of textual, acoustic and visual signals. While recent models have improved performance via advanced fusion strategies, they often lack psychologically meaningful priors to guide multimodal alignment. In this paper, we revisit the use of CLIP and propose a novel Visual Emotion Guided Anchoring (VEGA) mechanism that introduces class-level visual semantics into the fusion and classification process. Distinct from prior work that primarily utilizes CLIP's textual encoder, our approach leverages its image encoder to construct emotion-specific visual anchors based on facial exemplars. These anchors guide unimodal and multimodal features toward a perceptually grounded and psychologically aligned representation space, drawing inspiration from cognitive theories (prototypical emotion categories and multisensory integration). A stochastic anchor sampling strategy further enhances robustness by balancing semantic stability and intra-class diversity. Integrated into a dual-branch architecture with self-distillation, our VEGA-augmented model achieves sota performance on IEMOCAP and MELD. Code is available at: https://github.com/dkollias/VEGA.

comment: accepted for publication at ACM Multimedia (ACM MM) 2025

♻ ☆ ViewDelta: Scaling Scene Change Detection through Text-Conditioning

Subin Varghese, Joshua Gao, Vedhus Hoskere

We introduce a generalized framework for Scene Change Detection (SCD) that addresses the core ambiguity of distinguishing "relevant" from "nuisance" changes, enabling effective joint training of a single model across diverse domains and applications. Existing methods struggle to generalize due to differences in dataset labeling, where changes such as vegetation growth or lane marking alterations may be labeled as relevant in one dataset and irrelevant in another. To resolve this ambiguity, we propose ViewDelta, a text conditioned change detection framework that uses natural language prompts to define relevant changes precisely, such as a single attribute, a specific set of classes, or all observable differences. To facilitate training in this paradigm, we release the Conditional Change Segmentation dataset (CSeg), the first large-scale synthetic dataset for text conditioned SCD, consisting of over 500,000 image pairs with more than 300,000 unique textual prompts describing relevant changes. Experiments demonstrate that a single ViewDelta model trained jointly on CSeg, SYSU-CD, PSCD, VL-CMU-CD, and their unaligned variants achieves performance competitive with or superior to dataset specific models, highlighting text conditioning as a powerful approach for generalizable SCD. Our code and dataset are available at https://joshuakgao.github.io/viewdelta/.

♻ ☆ RoHOI: Robustness Benchmark for Human-Object Interaction Detection

Di Wen, Kunyu Peng, Kailun Yang, Yufan Chen, Ruiping Liu, Junwei Zheng, Alina Roitberg, Danda Pani Paudel, Luc Van Gool, Rainer Stiefelhagen

Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support. However, models trained on clean datasets degrade in real-world conditions due to unforeseen corruptions, leading to inaccurate prediction. To address this, we introduce the first robustness benchmark for HOI detection, evaluating model resilience under diverse challenges. Despite advances, current models struggle with environmental variability, occlusions, and noise. Our benchmark, RoHOI, includes 20 corruption types based on the HICO-DET and V-COCO datasets and a new robustness-focused metric. We systematically analyze existing models in the HOI field, revealing significant performance drops under corruptions. To improve robustness, we propose a Semantic-Aware Masking-based Progressive Learning (SAMPL) strategy to guide the model to be optimized based on holistic and partial cues, thus dynamically adjusting the model's optimization to enhance robust feature learning. Extensive experiments show that our approach outperforms state-of-the-art methods, setting a new standard for robust HOI detection. Benchmarks, datasets, and code will be made publicly available at https://github.com/Kratos-Wen/RoHOI.

comment: Benchmarks, datasets, and code will be made publicly available at https://github.com/Kratos-Wen/RoHOI

♻ ☆ MIND: A Noise-Adaptive Denoising Framework for Medical Images Integrating Multi-Scale Transformer

Tao Tang, Chengxu Yang

The core role of medical images in disease diagnosis makes their quality directly affect the accuracy of clinical judgment. However, due to factors such as low-dose scanning, equipment limitations and imaging artifacts, medical images are often accompanied by non-uniform noise interference, which seriously affects structure recognition and lesion detection. This paper proposes a medical image adaptive denoising model (MI-ND) that integrates multi-scale convolutional and Transformer architecture, introduces a noise level estimator (NLE) and a noise adaptive attention module (NAAB), and realizes channel-spatial attention regulation and cross-modal feature fusion driven by noise perception. Systematic testing is carried out on multimodal public datasets. Experiments show that this method significantly outperforms the comparative methods in image quality indicators such as PSNR, SSIM, and LPIPS, and improves the F1 score and ROC-AUC in downstream diagnostic tasks, showing strong prac-tical value and promotional potential. The model has outstanding benefits in structural recovery, diagnostic sensitivity, and cross-modal robustness, and provides an effective solution for medical image enhancement and AI-assisted diagnosis and treatment.

comment: Accepted by the 7th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP 2025). 6 pages, 6 figures

♻ ☆ Pretrained Reversible Generation as Unsupervised Visual Representation Learning

Rongkun Xue, Jinouwen Zhang, Yazhe Niu, Dazhong Shen, Bingqi Ma, Yu Liu, Jing Yang

Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have not fully leveraged the capabilities of these models for discriminative tasks due to their intricate designs. We propose Pretrained Reversible Generation (PRG), which extracts unsupervised representations by reversing the generative process of a pretrained continuous generation model. PRG effectively reuses unsupervised generative models, leveraging their high capacity to serve as robust and generalizable feature extractors for downstream tasks. This framework enables the flexible selection of feature hierarchies tailored to specific downstream tasks. Our method consistently outperforms prior approaches across multiple benchmarks, achieving state-of-the-art performance among generative model based methods, including 78% top-1 accuracy on ImageNet at a resolution of 64*64. Extensive ablation studies, including out-of-distribution evaluations, further validate the effectiveness of our approach.PRG is available at https://github.com/opendilab/PRG.

comment: Accepted by ICCV 2025

♻ ☆ CAS-IQA: Teaching Vision-Language Models for Synthetic Angiography Quality Assessment

Bo Wang, De-Xing Huang, Xiao-Hu Zhou, Mei-Jiang Gui, Nu-Fang Xiao, Jian-Long Hao, Ming-Yuan Liu, Zeng-Guang Hou

Synthetic X-ray angiographies generated by modern generative models hold great potential to reduce the use of contrast agents in vascular interventional procedures. However, low-quality synthetic angiographies can significantly increase procedural risk, underscoring the need for reliable image quality assessment (IQA) methods. Existing IQA models, however, fail to leverage auxiliary images as references during evaluation and lack fine-grained, task-specific metrics necessary for clinical relevance. To address these limitations, this paper proposes CAS-IQA, a vision-language model (VLM)-based framework that predicts fine-grained quality scores by effectively incorporating auxiliary information from related images. In the absence of angiography datasets, CAS-3K is constructed, comprising 3,565 synthetic angiographies along with score annotations. To ensure clinically meaningful assessment, three task-specific evaluation metrics are defined. Furthermore, a Multi-path featUre fuSion and rouTing (MUST) module is designed to enhance image representations by adaptively fusing and routing visual tokens to metric-specific branches. Extensive experiments on the CAS-3K dataset demonstrate that CAS-IQA significantly outperforms state-of-the-art IQA methods by a considerable margin.

comment: Camera ready version for ICONIP 2025

♻ ☆ Yan: Foundational Interactive Video Generation

♻ ☆ Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos

Shijia Feng, Michael Wray, Brian Sullivan, Youngkyoon Jang, Casimir Ludwig, Iain Gilchrist, Walterio Mayol-Cuevas

Determining when people are struggling allows for a finer-grained understanding of actions that complements conventional action classification and error detection. Struggle detection, as defined in this paper, is a distinct and important task that can be identified without explicit step or activity knowledge. We introduce the first struggle dataset with three real-world problem-solving activities that are labelled by both expert and crowd-source annotators. Video segments were scored w.r.t. their level of struggle using a forced choice 4-point scale. This dataset contains 5.1 hours of video from 73 participants. We conducted a series of experiments to identify the most suitable modelling approaches for struggle determination. Additionally, we compared various deep learning models, establishing baseline results for struggle classification, struggle regression, and struggle label distribution learning. Our results indicate that struggle detection in video can achieve up to $88.24\%$ accuracy in binary classification, while detecting the level of struggle in a four-way classification setting performs lower, with an overall accuracy of $52.45\%$. Our work is motivated toward a more comprehensive understanding of action in video and potentially the improvement of assistive systems that analyse struggle and can better support users during manual activities.

comment: Accepted by International Journal of Computer Vision (IJCV, 2025)

♻ ☆ Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning

Yue Ma, Yulong Liu, Qiyuan Zhu, Ayden Yang, Kunyu Feng, Xinhua Zhang, Zhifeng Li, Sirui Han, Chenyang Qi, Qifeng Chen

Recently, breakthroughs in the video diffusion transformer have shown remarkable capabilities in diverse motion generations. As for the motion-transfer task, current methods mainly use two-stage Low-Rank Adaptations (LoRAs) finetuning to obtain better performance. However, existing adaptation-based motion transfer still suffers from motion inconsistency and tuning inefficiency when applied to large video diffusion transformers. Naive two-stage LoRA tuning struggles to maintain motion consistency between generated and input videos due to the inherent spatial-temporal coupling in the 3D attention operator. Additionally, they require time-consuming fine-tuning processes in both stages. To tackle these issues, we propose Follow-Your-Motion, an efficient two-stage video motion transfer framework that finetunes a powerful video diffusion transformer to synthesize complex motion. Specifically, we propose a spatial-temporal decoupled LoRA to decouple the attention architecture for spatial appearance and temporal motion processing. During the second training stage, we design the sparse motion sampling and adaptive RoPE to accelerate the tuning speed. To address the lack of a benchmark for this field, we introduce MotionBench, a comprehensive benchmark comprising diverse motion, including creative camera motion, single object motion, multiple object motion, and complex human motion. We show extensive evaluations on MotionBench to verify the superiority of Follow-Your-Motion.

comment: project page: https://follow-your-motion.github.io/

♻ ☆ Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization

Jihwan Park, Taehoon song, Sanghyeok Lee, Miso Choi, Hyunwoo J. Kim

Vision-Language Models (VLMs) have been widely used in various visual recognition tasks due to their remarkable generalization capabilities. As these models grow in size and complexity, fine-tuning becomes costly, emphasizing the need to reuse adaptation knowledge from 'weaker' models to efficiently enhance 'stronger' ones. However, existing adaptation transfer methods exhibit limited transferability across models due to their model-specific design and high computational demands. To tackle this, we propose Transferable Model-agnostic adapter (TransMiter), a light-weight adapter that improves vision-language models 'without backpropagation'. TransMiter captures the knowledge gap between pre-trained and fine-tuned VLMs, in an 'unsupervised' manner. Once trained, this knowledge can be seamlessly transferred across different models without the need for backpropagation. Moreover, TransMiter consists of only a few layers, inducing a negligible additional inference cost. Notably, supplementing the process with a few labeled data further yields additional performance gain, often surpassing a fine-tuned stronger model, with a marginal training cost. Experimental results and analyses demonstrate that TransMiter effectively and efficiently transfers adaptation knowledge while preserving generalization abilities across VLMs of different sizes and architectures in visual recognition tasks.

♻ ☆ ProbRadarM3F: mmWave Radar based Human Skeletal Pose Estimation with Probability Map Guided Multi-Format Feature Fusion

Bing Zhu, Zixin He, Weiyi Xiong, Guanhua Ding, Tao Huang, Wei Xiang

Millimeter wave (mmWave) radar is a non-intrusive privacy and relatively convenient and inexpensive device, which has been demonstrated to be applicable in place of RGB cameras in human indoor pose estimation tasks. However, mmWave radar relies on the collection of reflected signals from the target, and the radar signals containing information is difficult to be fully applied. This has been a long-standing hindrance to the improvement of pose estimation accuracy. To address this major challenge, this paper introduces a probability map guided multi-format feature fusion model, ProbRadarM3F. This is a novel radar feature extraction framework using a traditional FFT method in parallel with a probability map based positional encoding method. ProbRadarM3F fuses the traditional heatmap features and the positional features, then effectively achieves the estimation of 14 keypoints of the human body. Experimental evaluation on the HuPR dataset proves the effectiveness of the model proposed in this paper, outperforming other methods experimented on this dataset with an AP of 69.9 %. The emphasis of our study is focusing on the position information that is not exploited before in radar singal. This provides direction to investigate other potential non-redundant information from mmWave rader.

♻ ☆ Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction

Bo Jia, Yanan Guo, Ying Chang, Benkui Zhang, Ying Xie, Kangning Du, Lin Cao

3D Gaussian Splatting (3DGS) achieves remarkable results in the field of surface reconstruction. However, when Gaussian normal vectors are aligned within the single-view projection plane, while the geometry appears reasonable in the current view, biases may emerge upon switching to nearby views. To address the distance and global matching challenges in multi-view scenes, we design multi-view normal and distance-guided Gaussian splatting. This method achieves geometric depth unification and high-accuracy reconstruction by constraining nearby depth maps and aligning 3D normals. Specifically, for the reconstruction of small indoor and outdoor scenes, we propose a multi-view distance reprojection regularization module that achieves multi-view Gaussian alignment by computing the distance loss between two nearby views and the same Gaussian surface. Additionally, we develop a multi-view normal enhancement module, which ensures consistency across views by matching the normals of pixel points in nearby views and calculating the loss. Extensive experimental results demonstrate that our method outperforms the baseline in both quantitative and qualitative evaluations, significantly enhancing the surface reconstruction capability of 3DGS. Our code will be made publicly available at (https://github.com/Bistu3DV/MND-GS/).

comment: This paper has been accepted by IROS 2025. Code: https://github.com/Bistu3DV/MND-GS/

♻ ☆ STAC: Leveraging Spatio-Temporal Data Associations For Efficient Cross-Camera Streaming and Analytics

Ragini Gupta, Lingzhi Zhao, Jiaxi Li, Volodymyr Vakhniuk, Claudiu Danilov, Josh Eckhardt, Keyshla Bernard, Klara Nahrstedt

In IoT based distributed network of cameras, real-time multi-camera video analytics is challenged by high bandwidth demands and redundant visual data, creating a fundamental tension where reducing data saves network overhead but can degrade model performance, and vice versa. We present STAC, a cross-cameras surveillance system that leverages spatio-temporal associations for efficient object tracking under constrained network conditions. STAC integrates multi-resolution feature learning, ensuring robustness under variable networked system level optimizations such as frame filtering, FFmpeg-based compression, and Region-of-Interest (RoI) masking, to eliminate redundant content across distributed video streams while preserving downstream model accuracy for object identification and tracking. Evaluated on NVIDIA's AICity Challenge dataset, STAC achieves a 76\% improvement in tracking accuracy and an 8.6x reduction in inference latency over a standard multi-object multi-camera tracking baseline (using YOLOv4 and DeepSORT). Furthermore, 29\% of redundant frames are filtered, significantly reducing data volume without compromising inference quality.

♻ ☆ Cryo-em images are intrinsically low dimensional

Luke Evans, Octavian-Vlad Murad, Lars Dingeldein, Pilar Cossio, Roberto Covino, Marina Meila

Simulation-based inference provides a powerful framework for cryo-electron microscopy, employing neural networks in methods like CryoSBI to infer biomolecular conformations via learned latent representations. This latent space represents a rich opportunity, encoding valuable information about the physical system and the inference process. Harnessing this potential hinges on understanding the underlying geometric structure of these representations. We investigate this structure by applying manifold learning techniques to CryoSBI representations of hemagglutinin (simulated and experimental). We reveal that these high-dimensional data inherently populate low-dimensional, smooth manifolds, with simulated data effectively covering the experimental counterpart. By characterizing the manifold's geometry using Diffusion Maps and identifying its principal axes of variation via coordinate interpretation methods, we establish a direct link between the latent structure and key physical parameters. Discovering this intrinsic low-dimensionality and interpretable geometric organization not only validates the CryoSBI approach but enables us to learn more from the data structure and provides opportunities for improving future inference strategies by exploiting this revealed manifold geometry.

♻ ☆ MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection

Yuxiang Wang, Xuecheng Bai, Boyu Hu, Chuanzhi Xu, Haodong Chen, Vera Chung, Tingxue Li, Xiaoming Chen

Small object detection in UAV imagery is crucial for applications such as search-and-rescue, traffic monitoring, and environmental surveillance, but it is hampered by tiny object size, low signal-to-noise ratios, and limited feature extraction. Existing multi-scale fusion methods help, but add computational burden and blur fine details, making small object detection in cluttered scenes difficult. To overcome these challenges, we propose the Multi-scale Global-detail Feature Integration Strategy (MGDFIS), a unified fusion framework that tightly couples global context with local detail to boost detection performance while maintaining efficiency. MGDFIS comprises three synergistic modules: the FusionLock-TSS Attention Module, which marries token-statistics self-attention with DynamicTanh normalization to highlight spectral and spatial cues at minimal cost; the Global-detail Integration Module, which fuses multi-scale context via directional convolution and parallel attention while preserving subtle shape and texture variations; and the Dynamic Pixel Attention Module, which generates pixel-wise weighting maps to rebalance uneven foreground and background distributions and sharpen responses to true object regions. Extensive experiments on the VisDrone benchmark demonstrate that MGDFIS consistently outperforms state-of-the-art methods across diverse backbone architectures and detection frameworks, achieving superior precision and recall with low inference time. By striking an optimal balance between accuracy and resource usage, MGDFIS provides a practical solution for small-object detection on resource-constrained UAV platforms.

comment: 9 pages, 5 figures, 3 tables

♻ ☆ Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions

Lucas Möller, Pascal Tilli, Ngoc Thang Vu, Sebastian Padó

Dual encoder architectures like Clip models map two types of inputs into a shared embedding space and predict similarities between them. Despite their wide application, it is, however, not understood how these models compare their two inputs. Common first-order feature-attribution methods explain importances of individual features and can, thus, only provide limited insights into dual encoders, whose predictions depend on interactions between features. In this paper, we first derive a second-order method enabling the attribution of predictions by any differentiable dual encoder onto feature-interactions between its inputs. Second, we apply our method to Clip models and show that they learn fine-grained correspondences between parts of captions and regions in images. They match objects across input modes and also account for mismatches. This intrinsic visual-linguistic grounding ability, however, varies heavily between object classes, exhibits pronounced out-of-domain effects and we can identify individual errors as well as systematic failure categories. Code is publicly available: https://github.com/lucasmllr/exCLIP

comment: Accepted at Transactions on Machine Learning Research (TMLR)

♻ ☆ GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

GLM-V Team, :, Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, Shuaiqi Duan, Weihan Wang, Yan Wang, Yean Cheng, Zehai He, Zhe Su, Zhen Yang, Ziyang Pan, Aohan Zeng, Baoxu Wang, Bin Chen, Boyan Shi, Changyu Pang, Chenhui Zhang, Da Yin, Fan Yang, Guoqing Chen, Jiazheng Xu, Jiale Zhu, Jiali Chen, Jing Chen, Jinhao Chen, Jinghao Lin, Jinjiang Wang, Junjie Chen, Leqi Lei, Letian Gong, Leyi Pan, Mingdao Liu, Mingzhi Zhang, Qinkai Zheng, Sheng Yang, Shi Zhong, Shiyu Huang, Shuyuan Zhao, Siyan Xue, Shangqin Tu, Shengbiao Meng, Tianshu Zhang, Tianwei Luo, Tianxiang Hao, Wenkai Li, Wei Jia, Xiao Liu, Xiaohan Zhang, Xin Lyu, Xuancheng Huang, Yanling Wang, Yadong Xue, Yanfeng Wang, Yanzi Wang, Yifan An, Yifan Du, Yiming Shi, Yiheng Huang, Yilin Niu, Yuan Wang, Yuanchang Yue, Yuchen Li, Yutao Zhang, Yuting Wang, Yu Wang, Yuxuan Zhang, Zhanxiao Du, Zhenyu Hou, Zhao Xue, Zhengxiao Du, Zihan Wang, Peng Zhang, Debing Liu, Bin Xu, Juanzi Li, Minlie Huang, Yuxiao Dong, Jie Tang

♻ ☆ RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation

Run Ling, Wenji Wang, Yuting Liu, Guibing Guo, Haowei Liu, Jian Lu, Quanwei Zhang, Yexing Xu, Shuo Lu, Yun Wang, Yihua Shao, Zhanjie Zhang, Ao Ma, Linying Jiang, Xingwei Wang

Personalized image generation is crucial for improving the user experience, as it renders reference images into preferred ones according to user visual preferences. Although effective, existing methods face two main issues. First, existing methods treat all items in the user historical sequence equally when extracting user preferences, overlooking the varying semantic similarities between historical items and the reference item. Disproportionately high weights for low-similarity items distort users' visual preferences for the reference item. Second, existing methods heavily rely on consistency between generated and reference images to optimize the generation, which leads to underfitting user preferences and hinders personalization. To address these issues, we propose Retrieval Augment Personalized Image GenerAtion guided by Recommendation (RAGAR). Our approach uses a retrieval mechanism to assign different weights to historical items according to their similarities to the reference item, thereby extracting more refined users' visual preferences for the reference item. Then we introduce a novel rank task based on the multi-modal ranking model to optimize the personalization of the generated images instead of forcing depend on consistency. Extensive experiments and human evaluations on three real-world datasets demonstrate that RAGAR achieves significant improvements in both personalization and semantic metrics compared to five baselines.

♻ ☆ Debiased Fine-Tuning for Vision-language Models by Prompt Regularization AAAI2023

Beier Zhu, Yulei Niu, Saeil Lee, Minhoe Hur, Hanwang Zhang

We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-tuning which easily overfits to the downstream task data, ProReg uses the prediction by prompting the pretrained model to regularize the fine-tuning. The motivation is: by prompting the large model "a photo of a [CLASS]", the fil-lin answer is only dependent on the pretraining encyclopedic knowledge while independent of the task data distribution, which is usually biased. Specifically, given a training sample prediction during fine-tuning, we first calculate its KullbackLeibler loss of the prompt prediction and Cross-Entropy loss of the ground-truth label, and then combine them with a proposed sample-wise adaptive trade-off weight, which automatically adjusts the transfer between the pretrained and downstream domains. On various out-of-distribution benchmarks, we show the consistently strong performance of ProReg compared with conventional fine-tuning, zero-shot prompt, prompt tuning, and other state-of-the-art methods.

comment: AAAI2023 accepted

♻ ☆ PiT: Progressive Diffusion Transformer

Jiafu Wu, Yabiao Wang, Jian Li, Jinlong Peng, Yun Cao, Chengjie Wang, Jiangning Zhang

Diffusion Transformers (DiTs) achieve remarkable performance within image generation via the transformer architecture. Conventionally, DiTs are constructed by stacking serial isotropic global modeling transformers, which face significant quadratic computational cost. However, through empirical analysis, we find that DiTs do not rely as heavily on global information as previously believed. In fact, most layers exhibit significant redundancy in global computation. Additionally, conventional attention mechanisms suffer from low-frequency inertia, limiting their efficiency. To address these issues, we propose Pseudo Shifted Window Attention (PSWA), which fundamentally mitigates global attention redundancy. PSWA achieves moderate global-local information through window attention. It further utilizes a high-frequency bridging branch to simulate shifted window operations, which both enrich the high-frequency information and strengthen inter-window connections. Furthermore, we propose the Progressive Coverage Channel Allocation (PCCA) strategy that captures high-order attention without additional computational cost. Based on these innovations, we propose a series of Pseudo Progressive Diffusion Transformer (PiT). Our extensive experiments show their superior performance; for example, our proposed PiT-L achieves 54% FID improvement over DiT-XL/2 while using less computation.

♻ ☆ Learning Adaptive Node Selection with External Attention for Human Interaction Recognition ACM MM25

Chen Pang, Xuequan Lu, Qianyu Zhou, Lei Lyu

Most GCN-based methods model interacting individuals as independent graphs, neglecting their inherent inter-dependencies. Although recent approaches utilize predefined interaction adjacency matrices to integrate participants, these matrices fail to adaptively capture the dynamic and context-specific joint interactions across different actions. In this paper, we propose the Active Node Selection with External Attention Network (ASEA), an innovative approach that dynamically captures interaction relationships without predefined assumptions. Our method models each participant individually using a GCN to capture intra-personal relationships, facilitating a detailed representation of their actions. To identify the most relevant nodes for interaction modeling, we introduce the Adaptive Temporal Node Amplitude Calculation (AT-NAC) module, which estimates global node activity by combining spatial motion magnitude with adaptive temporal weighting, thereby highlighting salient motion patterns while reducing irrelevant or redundant information. A learnable threshold, regularized to prevent extreme variations, is defined to selectively identify the most informative nodes for interaction modeling. To capture interactions, we design the External Attention (EA) module to operate on active nodes, effectively modeling the interaction dynamics and semantic relationships between individuals. Extensive evaluations show that our method captures interaction relationships more effectively and flexibly, achieving state-of-the-art performance.

comment: Accepted by ACM MM25

♻ ☆ MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines

Lu Xu, Jiaqian Yu, Xiongfeng Peng, Yiwei Chen, Weiming Li, Jaewook Yoo, Sunghyun Chunag, Dongwook Lee, Daehyun Ji, Chao Zhang

To meet the growing demand for smarter, faster, and more efficient embodied AI solutions, we introduce a novel Mixture-of-Expert (MoE) method that significantly boosts reasoning and learning efficiency for embodied autonomous systems. General MoE models demand extensive training data and complex optimization, which limits their applicability in embodied AI such as autonomous driving (AD) and robotic manipulation. In this work, we propose a skill-oriented MoE called MoSE, which mimics the human learning and reasoning process skill-by-skill, step-by-step. We introduce a skill-oriented routing mechanism that begins with defining and annotating specific skills, enabling experts to identify the necessary competencies for various scenarios and reasoning tasks, thereby facilitating skill-by-skill learning. To better align with multi-step planning in human reasoning and in end-to-end driving models, we build a hierarchical skill dataset and pretrain the router to encourage the model to think step-by-step. Unlike other multi-round dialogues, MoSE integrates valuable auxiliary tasks (e.g. perception-prediction-planning for AD, and high-level and low-level planning for robots) in one single forward process without introducing any extra computational cost. With less than 3B sparsely activated parameters, our model effectively grows more diverse expertise and outperforms models on both AD corner-case reasoning tasks and robot reasoning tasks with less than 40% of the parameters.

♻ ☆ Analyzing Finetuning Representation Shift for Multimodal LLMs Steering

Pegah Khayatan, Mustafa Shukor, Jayneel Parekh, Arnaud Dapogny, Matthieu Cord

Multimodal LLMs (MLLMs) have reached remarkable levels of proficiency in understanding multimodal inputs. However, understanding and interpreting the behavior of such complex models is a challenging task, not to mention the dynamic shifts that may occur during fine-tuning, or due to covariate shift between datasets. In this work, we apply concept-level analysis towards MLLM understanding. More specifically, we propose to map hidden states to interpretable visual and textual concepts. This enables us to more efficiently compare certain semantic dynamics, such as the shift from an original and fine-tuned model, revealing concept alteration and potential biases that may occur during fine-tuning. We also demonstrate the use of shift vectors to capture these concepts changes. These shift vectors allow us to recover fine-tuned concepts by applying simple, computationally inexpensive additive concept shifts in the original model. Finally, our findings also have direct applications for MLLM steering, which can be used for model debiasing as well as enforcing safety in MLLM output. All in all, we propose a novel, training-free, ready-to-use framework for MLLM behavior interpretability and control. Our implementation is publicly available.

comment: ICCV 2025. The first three authors contributed equally. Project page and code: https://pegah- kh.github.io/projects/lmm-finetuning-analysis-and-steering/

♻ ☆ LM-MCVT: A Lightweight Multi-modal Multi-view Convolutional-Vision Transformer Approach for 3D Object Recognition

Songsong Xiong, Hamidreza Kasaei

In human-centered environments such as restaurants, homes, and warehouses, robots often face challenges in accurately recognizing 3D objects. These challenges stem from the complexity and variability of these environments, including diverse object shapes. In this paper, we propose a novel Lightweight Multi-modal Multi-view Convolutional-Vision Transformer network (LM-MCVT) to enhance 3D object recognition in robotic applications. Our approach leverages the Globally Entropy-based Embeddings Fusion (GEEF) method to integrate multi-views efficiently. The LM-MCVT architecture incorporates pre- and mid-level convolutional encoders and local and global transformers to enhance feature extraction and recognition accuracy. We evaluate our method on the synthetic ModelNet40 dataset and achieve a recognition accuracy of 95.6% using a four-view setup, surpassing existing state-of-the-art methods. To further validate its effectiveness, we conduct 5-fold cross-validation on the real-world OmniObject3D dataset using the same configuration. Results consistently show superior performance, demonstrating the method's robustness in 3D object recognition across synthetic and real-world 3D data.

♻ ☆ Towards flexible perception with visual memory ICML 2025

Robert Geirhos, Priyank Jaini, Austin Stone, Sourabh Medapati, Xi Yi, George Toderici, Abhijit Ogale, Jonathon Shlens

Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is hard, since all information is distributed across the network's weights. We here explore a simple, compelling alternative by marrying the representational power of deep neural networks with the flexibility of a database. Decomposing the task of image classification into image similarity (from a pre-trained embedding) and search (via fast nearest neighbor retrieval from a knowledge database), we build on well-established components to construct a simple and flexible visual memory that has the following key capabilities: (1.) The ability to flexibly add data across scales: from individual samples all the way to entire classes and billion-scale data; (2.) The ability to remove data through unlearning and memory pruning; (3.) An interpretable decision-mechanism on which we can intervene to control its behavior. Taken together, these capabilities comprehensively demonstrate the benefits of an explicit visual memory. We hope that it might contribute to a conversation on how knowledge should be represented in deep vision models -- beyond carving it in "stone" weights.

comment: ICML 2025 camera ready version

♻ ☆ DRWKV: Focusing on Object Edges for Low-Light Image Enhancement

Xuecheng Bai, Yuxiang Wang, Boyu Hu, Qinyuan Jie, Chuanzhi Xu, Hongru Xiao, Kechen Li, Vera Chung

Low-light image enhancement remains a challenging task, particularly in preserving object edge continuity and fine structural details under extreme illumination degradation. In this paper, we propose a novel model, DRWKV (Detailed Receptance Weighted Key Value), which integrates our proposed Global Edge Retinex (GER) theory, enabling effective decoupling of illumination and edge structures for enhanced edge fidelity. Secondly, we introduce Evolving WKV Attention, a spiral-scanning mechanism that captures spatial edge continuity and models irregular structures more effectively. Thirdly, we design the Bilateral Spectrum Aligner (Bi-SAB) and a tailored MS2-Loss to jointly align luminance and chrominance features, improving visual naturalness and mitigating artifacts. Extensive experiments on five LLIE benchmarks demonstrate that DRWKV achieves leading performance in PSNR, SSIM, and NIQE while maintaining low computational complexity. Furthermore, DRWKV enhances downstream performance in low-light multi-object tracking tasks, validating its generalization capabilities.

♻ ☆ Calibrated Self-supervised Vision Transformers Improve Intracranial Arterial Calcification Segmentation from Clinical CT Head Scans

Benjamin Jin, Grant Mair, Joanna M. Wardlaw, Maria del C. Valdés Hernández

Vision Transformers (ViTs) have gained significant popularity in the natural image domain but have been less successful in 3D medical image segmentation. Nevertheless, 3D ViTs are particularly interesting for large medical imaging volumes due to their efficient self-supervised training within the masked autoencoder (MAE) framework, which enables the use of imaging data without the need for expensive manual annotations. Intracranial arterial calcification (IAC) is an imaging biomarker visible on routinely acquired CT scans linked to neurovascular diseases such as stroke and dementia, and automated IAC quantification could enable their large-scale risk assessment. We pre-train ViTs with MAE and fine-tune them for IAC segmentation for the first time. To develop our models, we use highly heterogeneous data from a large clinical trial, the third International Stroke Trial (IST-3). We evaluate key aspects of MAE pre-trained ViTs in IAC segmentation, and analyse the clinical implications. We show: 1) our calibrated self-supervised ViT beats a strong supervised nnU-Net baseline by 3.2 Dice points, 2) low patch sizes are crucial for ViTs for IAC segmentation and interpolation upsampling with regular convolutions is preferable to transposed convolutions for ViT-based models, and 3) our ViTs increase robustness to higher slice thicknesses and improve risk group classification in a clinical scenario by 46%. Our code is available online.

comment: Accepted at the 3rd Data Engineering in Medical Imaging workshop @ MICCAI 2025

♻ ☆ Joint multi-dimensional dynamic attention and transformer for general image restoration

Huan Zhang, Xu Zhang, Nian Cai, Jianglei Di, Yun Zhang

Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks. Current image restoration methods struggle to handle complex degradation while maintaining efficiency. This paper introduces a novel image restoration architecture that combines multi-dimensional dynamic attention and self-attention within a U-Net framework. To leverage the global modeling capabilities of transformers and the local modeling capabilities of convolutions, we integrate sole CNNs in the encoder-decoder and sole transformers in the latent layer. Additionally, we design convolutional kernels with selected multi-dimensional dynamic attention to capture diverse degraded inputs efficiently. A transformer block with transposed self-attention further enhances global feature extraction while maintaining efficiency. Extensive experiments demonstrate that our method achieves a better balance between performance and computational complexity across five image restoration tasks: deraining, deblurring, denoising, dehazing, and enhancement, as well as superior performance for high-level vision tasks. The source code will be available at https://github.com/House-yuyu/MDDA-former.

♻ ☆ BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment

Tongfan Guan, Jiaxin Guo, Chen Wang, Yun-Hui Liu

Monocular and stereo depth estimation offer complementary strengths: monocular methods capture rich contextual priors but lack geometric precision, while stereo approaches leverage epipolar geometry yet struggle with ambiguities such as reflective or textureless surfaces. Despite post-hoc synergies, these paradigms remain largely disjoint in practice. We introduce a unified framework that bridges both through iterative bidirectional alignment of their latent representations. At its core, a novel cross-attentive alignment mechanism dynamically synchronizes monocular contextual cues with stereo hypothesis representations during stereo reasoning. This mutual alignment resolves stereo ambiguities (e.g., specular surfaces) by injecting monocular structure priors while refining monocular depth with stereo geometry within a single network. Extensive experiments demonstrate state-of-the-art results: \textbf{it reduces zero-shot generalization error by $\!>\!40\%$ on Middlebury and ETH3D}, while addressing longstanding failures on transparent and reflective surfaces. By harmonizing multi-view geometry with monocular context, our approach enables robust 3D perception that transcends modality-specific limitations. Codes available at https://github.com/aeolusguan/BridgeDepth.

comment: ICCV 2025 Highlight

♻ ☆ Pediatric brain tumor classification using digital histopathology and deep learning: evaluation of SOTA methods on a multi-center Swedish cohort

Iulian Emil Tampu, Per Nyman, Christoforos Spyretos, Ida Blystad, Alia Shamikh, Gabriela Prochazka, Teresita Díaz de Ståhl, Johanna Sandgren, Peter Lundberg, Neda Haj-Hosseini

Brain tumors are the most common solid tumors in children and young adults, but the scarcity of large histopathology datasets has limited the application of computational pathology in this group. This study implements two weakly supervised multiple-instance learning (MIL) approaches on patch-features obtained from state-of-the-art histology-specific foundation models to classify pediatric brain tumors in hematoxylin and eosin whole slide images (WSIs) from a multi-center Swedish cohort. WSIs from 540 subjects (age 8.5$\pm$4.9 years) diagnosed with brain tumor were gathered from the six Swedish university hospitals. Instance (patch)-level features were obtained from WSIs using three pre-trained feature extractors: ResNet50, UNI, and CONCH. Instances were aggregated using attention-based MIL (ABMIL) or clustering-constrained attention MIL (CLAM) for patient-level classification. Models were evaluated on three classification tasks based on the hierarchical classification of pediatric brain tumors: tumor category, family, and type. Model generalization was assessed by training on data from two of the centers and testing on data from four other centers. Model interpretability was evaluated through attention mapping. The highest classification performance was achieved using UNI features and ABMIL aggregation, with Matthew's correlation coefficient of 0.76$\pm$0.04, 0.63$\pm$0.04, and 0.60$\pm$0.05 for tumor category, family, and type classification, respectively. When evaluating generalization, models utilizing UNI and CONCH features outperformed those using ResNet50. However, the drop in performance from the in-site to out-of-site testing was similar across feature extractors. These results show the potential of state-of-the-art computational pathology methods in diagnosing pediatric brain tumors at different hierarchical levels with fair generalizability on a multi-center national dataset.

♻ ☆ CD-TVD: Contrastive Diffusion for 3D Super-Resolution with Scarce High-Resolution Time-Varying Data

Chongke Bi, Xin Gao, Jiangkang Deng, Guan Li, Jun Han

Large-scale scientific simulations require significant resources to generate high-resolution time-varying data (TVD). While super-resolution is an efficient post-processing strategy to reduce costs, existing methods rely on a large amount of HR training data, limiting their applicability to diverse simulation scenarios. To address this constraint, we proposed CD-TVD, a novel framework that combines contrastive learning and an improved diffusion-based super-resolution model to achieve accurate 3D super-resolution from limited time-step high-resolution data. During pre-training on historical simulation data, the contrastive encoder and diffusion superresolution modules learn degradation patterns and detailed features of high-resolution and low-resolution samples. In the training phase, the improved diffusion model with a local attention mechanism is fine-tuned using only one newly generated high-resolution timestep, leveraging the degradation knowledge learned by the encoder. This design minimizes the reliance on large-scale high-resolution datasets while maintaining the capability to recover fine-grained details. Experimental results on fluid and atmospheric simulation datasets confirm that CD-TVD delivers accurate and resource-efficient 3D super-resolution, marking a significant advancement in data augmentation for large-scale scientific simulations. The code is available at https://github.com/Xin-Gao-private/CD-TVD.

comment: Accepted to IEEE VIS 2025

♻ ☆ See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question Answering

Junjie Wang, Yunhan Tang, Yijie Wang, Zhihao Yuan, Huan Wang, Yangfan He, Bin Li

Multimodal Large Language Models (MLLMs) have pushed the frontiers of Knowledge-Based Visual Question Answering (KBVQA), yet their reasoning is fundamentally bottlenecked by a reliance on uni-dimensional evidence. This "seeing only the trees, but not the forest" approach prevents robust, multi-faceted understanding. Inspired by the principle of seeing both the forest and trees, we propose Synergos-VQA, a novel synergistic reasoning framework. At its core, Synergos-VQA concurrently generates and fuses three complementary evidence streams at inference time: (1) Holistic Evidence to perceive the entire scene (the "forest"), (2) Structural Evidence from a prototype-driven module to identify key objects (the "trees"), and (3) Causal Evidence from a counterfactual probe to ensure the reasoning is robustly grounded. By synergistically fusing this multi-faceted evidence, our framework achieves a more comprehensive and reliable reasoning process. Extensive experiments show that Synergos-VQA decisively establishes a new state-of-the-art on three challenging benchmarks, including OK-VQA and A-OKVQA. Furthermore, our approach demonstrates strong plug-and-play capabilities, significantly boosting various open-source MLLMs and proving that superior methodological design can outperform sheer model scale.

comment: We are withdrawing this preprint because it is undergoing a major revision and restructuring. We feel that the current version does not convey our core contributions and methodology with sufficient clarity and accuracy

♻ ☆ Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentation

Karol Gotkowski, Klaus H. Maier-Hein, Fabian Isensee

Scribble supervision has emerged as a promising approach for reducing annotation costs in medical 3D segmentation by leveraging sparse annotations instead of voxel-wise labels. While existing methods report strong performance, a closer analysis reveals that the majority of research is confined to the cardiac domain, predominantly using ACDC and MSCMR datasets. This over-specialization has resulted in severe overfitting, misleading claims of performance improvements, and a lack of generalization across broader segmentation tasks. In this work, we formulate a set of key requirements for practical scribble supervision and introduce ScribbleBench, a comprehensive benchmark spanning over seven diverse medical imaging datasets, to systematically evaluate the fulfillment of these requirements. Consequently, we uncover a general failure of methods to generalize across tasks and that many widely used novelties degrade performance outside of the cardiac domain, whereas simpler overlooked approaches achieve superior generalization. Finally, we raise awareness for a strong yet overlooked baseline, nnU-Net coupled with a partial loss, which consistently outperforms specialized methods across a diverse range of tasks. By identifying fundamental limitations in existing research and establishing a new benchmark-driven evaluation standard, this work aims to steer scribble supervision toward more practical, robust, and generalizable methodologies for medical image segmentation.

comment: accepted at MICCAI2025

♻ ☆ LiteFat: Lightweight Spatio-Temporal Graph Learning for Real-Time Driver Fatigue Detection

Jing Ren, Suyu Ma, Hong Jia, Xiwei Xu, Ivan Lee, Haytham Fayek, Xiaodong Li, Feng Xia

Detecting driver fatigue is critical for road safety, as drowsy driving remains a leading cause of traffic accidents. Many existing solutions rely on computationally demanding deep learning models, which result in high latency and are unsuitable for embedded robotic devices with limited resources (such as intelligent vehicles/cars) where rapid detection is necessary to prevent accidents. This paper introduces LiteFat, a lightweight spatio-temporal graph learning model designed to detect driver fatigue efficiently while maintaining high accuracy and low computational demands. LiteFat involves converting streaming video data into spatio-temporal graphs (STG) using facial landmark detection, which focuses on key motion patterns and reduces unnecessary data processing. LiteFat uses MobileNet to extract facial features and create a feature matrix for the STG. A lightweight spatio-temporal graph neural network is then employed to identify signs of fatigue with minimal processing and low latency. Experimental results on benchmark datasets show that LiteFat performs competitively while significantly decreasing computational complexity and latency as compared to current state-of-the-art methods. This work enables the development of real-time, resource-efficient human fatigue detection systems that can be implemented upon embedded robotic devices.

comment: 8 pages, 4 figures

♻ ☆ Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

Vlad Hosu, Lorenzo Agnolucci, Daisuke Iso, Dietmar Saupe

Image Quality Assessment (IQA) measures and predicts perceived image quality by human observers. Although recent studies have highlighted the critical influence that variations in the scale of an image have on its perceived quality, this relationship has not been systematically quantified. To bridge this gap, we introduce the Image Intrinsic Scale (IIS), defined as the largest scale where an image exhibits its highest perceived quality. We also present the Image Intrinsic Scale Assessment (IISA) task, which involves subjectively measuring and predicting the IIS based on human judgments. We develop a subjective annotation methodology and create the IISA-DB dataset, comprising 785 image-IIS pairs annotated by experts in a rigorously controlled crowdsourcing study. Furthermore, we propose WIISA (Weak-labeling for Image Intrinsic Scale Assessment), a strategy that leverages how the IIS of an image varies with downscaling to generate weak labels. Experiments show that applying WIISA during the training of several IQA methods adapted for IISA consistently improves the performance compared to using only ground-truth labels. The code, dataset, and pre-trained models are available at https://github.com/SonyResearch/IISA.

comment: Accepted at ICCV2025

♻ ☆ SpectralEarth: Training Hyperspectral Foundation Models at Scale

Nassim Ait Ali Braham, Conrad M Albrecht, Julien Mairal, Jocelyn Chanussot, Yi Wang, Xiao Xiang Zhu

Foundation models have triggered a paradigm shift in computer vision and are increasingly being adopted in remote sensing, particularly for multispectral imagery. Yet, their potential in hyperspectral imaging (HSI) remains untapped due to the absence of comprehensive and globally representative hyperspectral datasets. To close this gap, we introduce SpectralEarth, a large-scale multitemporal dataset designed to pretrain hyperspectral foundation models leveraging data from the environmental mapping and analysis program (EnMAP). SpectralEarth comprises 538 974 image patches covering 415 153 unique locations from 11 636 globally distributed EnMAP scenes spanning two years of archive. In addition, 17.5% of these locations include multiple timestamps, enabling multitemporal HSI analysis. Utilizing state-of-the-art self-supervised learning algorithms, we pretrain a series of foundation models on SpectralEarth, integrating a spectral adapter into classical vision backbones to accommodate the unique characteristics of HSI. In tandem, we construct nine downstream datasets for land-cover, crop-type mapping, and tree-species classification, providing benchmarks for model evaluation. Experimental results support the versatility of our models and their generalizability across different tasks and sensors. We also highlight computational efficiency during model fine-tuning.

♻ ☆ Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization

Hongbin Xu, Chaohui Yu, Feng Xiao, Jiazheng Xing, Hai Ci, Weitao Chen, Fan Wang, Ming Li

Despite the remarkable progress of 3D generation, achieving controllability, i.e., ensuring consistency between generated 3D content and input conditions like edge and depth, remains a significant challenge. Existing methods often struggle to maintain accurate alignment, leading to noticeable discrepancies. To address this issue, we propose \name{}, a new framework that enhances controllable 3D generation by explicitly encouraging cyclic consistency between the second-order 3D content, generated based on extracted signals from the first-order generation, and its original input controls. Specifically, we employ an efficient feed-forward backbone that can generate a 3D object from an input condition and a text prompt. Given an initial viewpoint and a control signal, a novel view is rendered from the generated 3D content, from which the extracted condition is used to regenerate the 3D content. This re-generated output is then rendered back to the initial viewpoint, followed by another round of control signal extraction, forming a cyclic process with two consistency constraints. \emph{View consistency} ensures coherence between the two generated 3D objects, measured by semantic similarity to accommodate generative diversity. \emph{Condition consistency} aligns the final extracted signal with the original input control, preserving structural or geometric details throughout the process. Extensive experiments on popular benchmarks demonstrate that \name{} significantly improves controllability, especially for fine-grained details, outperforming existing methods across various conditions (e.g., +14.17\% PSNR for edge, +6.26\% PSNR for sketch).

comment: Preprint version. Update with new experimental results

♻ ☆ SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Driving

Helin Cao, Rafael Materla, Sven Behnke

Perception systems in autonomous driving rely on sensors such as LiDAR and cameras to perceive the 3D environment. However, due to occlusions and data sparsity, these sensors often fail to capture complete information. Semantic Occupancy Prediction (SOP) addresses this challenge by inferring both occupancy and semantics of unobserved regions. Existing transformer-based SOP methods lack explicit modeling of spatial structure in attention computation, resulting in limited geometric awareness and poor performance in sparse or occluded areas. To this end, we propose Spatially-aware Window Attention (SWA), a novel mechanism that incorporates local spatial context into attention. SWA significantly improves scene completion and achieves state-of-the-art results on LiDAR-based SOP benchmarks. We further validate its generality by integrating SWA into a camera-based SOP pipeline, where it also yields consistent gains across modalities.

comment: 2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Vienna, Austria, Oct 2025

♻ ☆ OC-SOP: Enhancing Vision-Based 3D Semantic Occupancy Prediction by Object-Centric Awareness

Helin Cao, Sven Behnke

Autonomous driving perception faces significant challenges due to occlusions and incomplete scene data in the environment. To overcome these issues, the task of semantic occupancy prediction (SOP) is proposed, which aims to jointly infer both the geometry and semantic labels of a scene from images. However, conventional camera-based methods typically treat all categories equally and primarily rely on local features, leading to suboptimal predictions, especially for dynamic foreground objects. To address this, we propose Object-Centric SOP (OC-SOP), a framework that integrates high-level object-centric cues extracted via a detection branch into the semantic occupancy prediction pipeline. This object-centric integration significantly enhances the prediction accuracy for foreground objects and achieves state-of-the-art performance among all categories on SemanticKITTI.

comment: 2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Vienna, Austria, Oct 2025

♻ ☆ LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data

Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille, Sébastien Fournier

Multimodal Deep Learning enhances decision-making by integrating diverse information sources, such as texts, images, audio, and videos. To develop trustworthy multimodal approaches, it is essential to understand how uncertainty impacts these models. We propose LUMA, a unique multimodal dataset, featuring audio, image, and textual data from 50 classes, specifically designed for learning from uncertain data. It extends the well-known CIFAR 10/100 dataset with audio samples extracted from three audio corpora, and text data generated using the Gemma-7B Large Language Model (LLM). The LUMA dataset enables the controlled injection of varying types and degrees of uncertainty to achieve and tailor specific experiments and benchmarking initiatives. LUMA is also available as a Python package including the functions for generating multiple variants of the dataset with controlling the diversity of the data, the amount of noise for each modality, and adding out-of-distribution samples. A baseline pre-trained model is also provided alongside three uncertainty quantification methods: Monte-Carlo Dropout, Deep Ensemble, and Reliable Conflictive Multi-View Learning. This comprehensive dataset and its tools are intended to promote and support the development, evaluation, and benchmarking of trustworthy and robust multimodal deep learning approaches. We anticipate that the LUMA dataset will help the research community to design more trustworthy and robust machine learning approaches for safety critical applications. The code and instructions for downloading and processing the dataset can be found at: https://github.com/bezirganyan/LUMA/ .

comment: SIGIR 2025

♻ ☆ FROST-BRDF: A Fast and Robust Optimal Sampling Technique for BRDF Acquisition

Ehsan Miandji, Tanaboon Tongbuasirilai, Saghi Hajisharif, Behnaz Kavoosighafi, Jonas Unger

Efficient and accurate BRDF acquisition of real world materials is a challenging research problem that requires sampling millions of incident light and viewing directions. To accelerate the acquisition process, one needs to find a minimal set of sampling directions such that the recovery of the full BRDF is accurate and robust given such samples. In this paper, we formulate BRDF acquisition as a compressed sensing problem, where the sensing operator is one that performs sub-sampling of the BRDF signal according to a set of optimal sample directions. To solve this problem, we propose the Fast and Robust Optimal Sampling Technique (FROST) for designing a provably optimal sub-sampling operator that places light-view samples such that the recovery error is minimized. FROST casts the problem of designing an optimal sub-sampling operator for compressed sensing into a sparse representation formulation under the Multiple Measurement Vector (MMV) signal model. The proposed reformulation is exact, i.e. without any approximations, hence it converts an intractable combinatorial problem into one that can be solved with standard optimization techniques. As a result, FROST is accompanied by strong theoretical guarantees from the field of compressed sensing. We perform a thorough analysis of FROST-BRDF using a 10-fold cross-validation with publicly available BRDF datasets and show significant advantages compared to the state-of-the-art with respect to reconstruction quality. Finally, FROST is simple, both conceptually and in terms of implementation, it produces consistent results at each run, and it is at least two orders of magnitude faster than the prior art.

comment: Submitted to IEEE Transactions on Visualization and Computer Graphics (IEEE TVCG)

♻ ☆ Modulate and Reconstruct: Learning Hyperspectral Imaging from Misaligned Smartphone Views

Daniil Reutsky, Daniil Vladimirov, Yasin Mamedov, Georgy Perevozchikov, Nancy Mehta, Egor Ershov, Radu Timofte

Hyperspectral reconstruction (HSR) from RGB images is a fundamentally ill-posed problem due to severe spectral information loss. Existing approaches typically rely on a single RGB image, limiting reconstruction accuracy. In this work, we propose a novel multi-image-to-hyperspectral reconstruction (MI-HSR) framework that leverages a triple-camera smartphone system, where two lenses are equipped with carefully selected spectral filters. Our configuration, grounded in theoretical and empirical analysis, enables richer and more diverse spectral observations than conventional single-camera setups. To support this new paradigm, we introduce Doomer, the first dataset for MI-HSR, comprising aligned images from three smartphone cameras and a hyperspectral reference camera across diverse scenes. We show that the proposed HSR model achieves consistent improvements over existing methods on the newly proposed benchmark. In a nutshell, our setup allows 30% towards more accurately estimated spectra compared to an ordinary RGB camera. Our findings suggest that multi-view spectral filtering with commodity hardware can unlock more accurate and practical hyperspectral imaging solutions.

♻ ☆ SLTNet: Efficient Event-based Semantic Segmentation with Spike-driven Lightweight Transformer-based Networks

Xianlei Long, Xiaxin Zhu, Fangming Guo, Wanyi Zhang, Qingyi Gu, Chao Chen, Fuqiang Gu

Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their efficiency and application on resource-constrained edge/mobile platforms. To address these problems, we introduce SLTNet, a spike-driven lightweight transformer-based network designed for event-based semantic segmentation. Specifically, SLTNet is built on efficient spike-driven convolution blocks (SCBs) to extract rich semantic features while reducing the model's parameters. Then, to enhance the long-range contextural feature interaction, we propose novel spike-driven transformer blocks (STBs) with binary mask operations. Based on these basic blocks, SLTNet employs a high-efficiency single-branch architecture while maintaining the low energy consumption of the Spiking Neural Network (SNN). Finally, extensive experiments on DDD17 and DSEC-Semantic datasets demonstrate that SLTNet outperforms state-of-the-art (SOTA) SNN-based methods by at most 9.06% and 9.39% mIoU, respectively, with extremely 4.58x lower energy consumption and 114 FPS inference speed. Our code is open-sourced and available at https://github.com/longxianlei/SLTNet-v1.0.

comment: Accepted by IROS 2025 (2025 IEEE/RSJ International Conference on Intelligent Robots and Systems)

♻ ☆ UltraRay: Introducing Full-Path Ray Tracing in Physics-Based Ultrasound Simulation

Felix Duelmer, Mohammad Farid Azampour, Magdalena Wysocki, Nassir Navab

Traditional ultrasound simulators solve the wave equation to model pressure distribution fields, achieving high accuracy but requiring significant computational time and resources. To address this, ray tracing approaches have been introduced, modeling wave propagation as rays interacting with boundaries and scatterers. However, existing models simplify ray propagation, generating echoes at interaction points without considering return paths to the sensor. This can result in unrealistic artifacts and necessitates careful scene tuning for plausible results. We propose a novel ultrasound simulation pipeline that utilizes a ray tracing algorithm to generate echo data, tracing each ray from the transducer through the scene and back to the sensor. To replicate advanced ultrasound imaging, we introduce a ray emission scheme optimized for plane wave imaging, incorporating delay and steering capabilities. Furthermore, we integrate a standard signal processing pipeline to simulate end-to-end ultrasound image formation. We showcase the efficacy of the proposed pipeline by modeling synthetic scenes featuring highly reflective objects, such as bones. In doing so, our proposed approach, UltraRay, not only enhances the overall visual quality but also improves the realism of the simulated images by accurately capturing secondary reflections and reducing unnatural artifacts. By building on top of a differentiable framework, the proposed pipeline lays the groundwork for a fast and differentiable ultrasound simulation tool necessary for gradient-based optimization, enabling advanced ultrasound beamforming strategies, neural network integration, and accurate inverse scene reconstruction.

♻ ☆ ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs

Yin Xie, Kaicheng Yang, Peirou Liang, Xiang An, Yongle Zhao, Yumeng Wang, Ziyong Feng, Roy Miles, Ismail Elezi, Jiankang Deng

Large Multimodal Models (LMMs) often face a modality representation gap during pretraining: while language embeddings remain stable, visual representations are highly sensitive to contextual noise (e.g., background clutter). To address this issue, we introduce a visual comprehension stage, which we call ViCToR (Visual Comprehension via Token Reconstruction), a novel pretraining framework for LMMs. ViCToR employs a learnable visual token pool and utilizes the Hungarian matching algorithm to select semantically relevant tokens from this pool for visual token replacement. Furthermore, by integrating a visual token reconstruction loss with dense semantic supervision, ViCToR can learn tokens which retain high visual detail, thereby enhancing the large language model's (LLM's) understanding of visual information. After pretraining on 3 million publicly accessible images and captions, ViCToR achieves state-of-the-art results, improving over LLaVA-NeXT-8B by 10.4%, 3.2%, and 7.2% on the MMStar, SEED$^I$, and RealWorldQA benchmarks, respectively. Code is available at https://github.com/deepglint/Victor.

comment: 10 pages, 6 figures, 5 tables

♻ ☆ CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback

Chenhan Jiang, Yihan Zeng, Dit-Yan Yeung

Score Distillation Sampling (SDS) has achieved remarkable success in text-to-3D content generation. However, SDS-based methods struggle to maintain semantic fidelity for user prompts, particularly when involving multiple objects with intricate interactions. While existing approaches often address 3D consistency through multiview diffusion model fine-tuning on 3D datasets, this strategy inadvertently exacerbates text-3D alignment degradation. The limitation stems from SDS's inherent accumulation of view-independent biases during optimization, which progressively diverges from the ideal text alignment direction. To alleviate this limitation, we propose a novel SDS objective, dubbed as Textual Coherent Score Distillation (TCSD), which integrates alignment feedback from multimodal large language models (MLLMs). Our TCSD leverages cross-modal understanding capabilities of MLLMs to assess and guide the text-3D correspondence during the optimization. We further develop 3DLLaVA-CRITIC - a fine-tuned MLLM specialized for evaluating multiview text alignment in 3D generations. Additionally, we introduce an LLM-layout initialization that significantly accelerates optimization convergence through semantic-aware spatial configuration. Our framework, CoherenDream, achieves consistent improvement across multiple metrics on TIFA subset.As the first study to incorporate MLLMs into SDS optimization, we also conduct extensive ablation studies to explore optimal MLLM adaptations for 3D generation tasks.

♻ ☆ HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels

HunyuanWorld Team, Zhenwei Wang, Yuhao Liu, Junta Wu, Zixiao Gu, Haoyuan Wang, Xuhui Zuo, Tianyu Huang, Wenhuan Li, Sheng Zhang, Yihang Lian, Yulin Tsai, Lifu Wang, Sicong Liu, Puhua Jiang, Xianghui Yang, Dongyuan Guo, Yixuan Tang, Xinyue Mao, Jiaao Yu, Junlin Yu, Jihong Zhang, Meng Chen, Liang Dong, Yiwen Jia, Chao Zhang, Yonghao Tan, Hao Zhang, Zheng Ye, Peng He, Runzhou Wu, Minghui Chen, Zhan Li, Wangchen Qin, Lei Wang, Yifu Sun, Lin Niu, Xiang Yuan, Xiaofeng Yang, Yingping He, Jie Xiao, Yangyu Tao, Jianchen Zhu, Jinbao Xue, Kai Liu, Chongqing Zhao, Xinming Wu, Tian Liu, Peng Chen, Di Wang, Yuhong Liu, Linus, Jie Jiang, Tengfei Wang, Chunchao Guo

Creating immersive and playable 3D worlds from texts or images remains a fundamental challenge in computer vision and graphics. Existing world generation approaches typically fall into two categories: video-based methods that offer rich diversity but lack 3D consistency and rendering efficiency, and 3D-based methods that provide geometric consistency but struggle with limited training data and memory-inefficient representations. To address these limitations, we present HunyuanWorld 1.0, a novel framework that combines the best of both worlds for generating immersive, explorable, and interactive 3D scenes from text and image conditions. Our approach features three key advantages: 1) 360{\deg} immersive experiences via panoramic world proxies; 2) mesh export capabilities for seamless compatibility with existing computer graphics pipelines; 3) disentangled object representations for augmented interactivity. The core of our framework is a semantically layered 3D mesh representation that leverages panoramic images as 360{\deg} world proxies for semantic-aware world decomposition and reconstruction, enabling the generation of diverse 3D worlds. Extensive experiments demonstrate that our method achieves state-of-the-art performance in generating coherent, explorable, and interactive 3D worlds while enabling versatile applications in virtual reality, physical simulation, game development, and interactive content creation.

comment: Technical Report; Project Page: https://3d-models.hunyuan.tencent.com/world/

♻ ☆ HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

Xin Zhou, Dingkang Liang, Sifan Tu, Xiwu Chen, Yikang Ding, Dingyuan Zhang, Feiyang Tan, Hengshuang Zhao, Xiang Bai

Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to incorporate scene understanding, which involves interpreting and reasoning about the driving environment. In this paper, we present a unified Driving World Model named HERMES. We seamlessly integrate 3D scene understanding and future scene evolution (generation) through a unified framework in driving scenarios. Specifically, HERMES leverages a Bird's-Eye View (BEV) representation to consolidate multi-view spatial information while preserving geometric relationships and interactions. We also introduce world queries, which incorporate world knowledge into BEV features via causal attention in the Large Language Model, enabling contextual enrichment for understanding and generation tasks. We conduct comprehensive studies on nuScenes and OmniDrive-nuScenes datasets to validate the effectiveness of our method. HERMES achieves state-of-the-art performance, reducing generation error by 32.4% and improving understanding metrics such as CIDEr by 8.0%. The model and code will be publicly released at https://github.com/LMD0311/HERMES.

comment: Accepted by ICCV 2025. The code is available at https://github.com/LMD0311/HERMES

♻ ☆ PrAViC: Probabilistic Adaptation Framework for Real-Time Video Classification

Magdalena Trędowicz, Marcin Mazur, Szymon Janusz, Arkadiusz Lewicki, Jacek Tabor, Łukasz Struski

Video processing is generally divided into two main categories: processing of the entire video, which typically yields optimal classification outcomes, and real-time processing, where the objective is to make a decision as promptly as possible. Although the models dedicated to the processing of entire videos are typically well-defined and clearly presented in the literature, this is not the case for online processing, where a~plethora of hand-devised methods exist. To address this issue, we present PrAViC, a novel, unified, and theoretically-based adaptation framework for tackling the online classification problem in video data. The initial phase of our study is to establish a mathematical background for the classification of sequential data, with the potential to make a decision at an early stage. This allows us to construct a natural function that encourages the model to return a result much faster. The subsequent phase is to present a straightforward and readily implementable method for adapting offline models to the online setting using recurrent operations. Finally, PrAViC is evaluated by comparing it with existing state-of-the-art offline and online models and datasets. This enables the network to significantly reduce the time required to reach classification decisions while maintaining, or even enhancing, accuracy.

comment: The paper was accepted at ECAI 2025

♻ ☆ Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation

Minyue Dai, Ke Fan, Bin Ji, Haoran Xu, Haoyu Zhao, Junting Dong, Jingbo Wang, Bo Dai

Styled motion in-betweening is crucial for computer animation and gaming. However, existing methods typically encode motion styles by modeling whole-body motions, often overlooking the representation of individual body parts. This limitation reduces the flexibility of infilled motion, particularly in adjusting the motion styles of specific limbs independently. To overcome this challenge, we propose a novel framework that models motion styles at the body-part level, enhancing both the diversity and controllability of infilled motions. Our approach enables more nuanced and expressive animations by allowing precise modifications to individual limb motions while maintaining overall motion coherence. Leveraging phase-related insights, our framework employs periodic autoencoders to automatically extract the phase of each body part, capturing distinctive local style features. Additionally, we effectively decouple the motion source from synthesis control by integrating motion manifold learning and conditional generation techniques from both image and motion domains. This allows the motion source to generate high-quality motions across various styles, with extracted motion and style features readily available for controlled synthesis in subsequent tasks. Comprehensive evaluations demonstrate that our method achieves superior speed, robust generalization, and effective generation of extended motion sequences.

comment: 10 pages, 5 figures

♻ ☆ Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models IJCAI 2025

Andela Ilic, Jiaxi Jiang, Paul Streli, Xintong Liu, Christian Holz

Motion capture using sparse inertial sensors has shown great promise due to its portability and lack of occlusion issues compared to camera-based tracking. Existing approaches typically assume that IMU sensors are tightly attached to the human body. However, this assumption often does not hold in real-world scenarios. In this paper, we present Garment Inertial Poser (GaIP), a method for estimating full-body poses from sparse and loosely attached IMU sensors. We first simulate IMU recordings using an existing garment-aware human motion dataset. Our transformer-based diffusion models synthesize loose IMU data and estimate human poses from this challenging loose IMU data. We also demonstrate that incorporating garment-related parameters during training on loose IMU data effectively maintains expressiveness and enhances the ability to capture variations introduced by looser or tighter garments. Our experiments show that our diffusion methods trained on simulated and synthetic data outperform state-of-the-art inertial full-body pose estimators, both quantitatively and qualitatively, opening up a promising direction for future research on motion capture from such realistic sensor placements.

comment: Accepted by IJCAI 2025

♻ ☆ Towards Black-Box Membership Inference Attack for Diffusion Models

Jingwei Li, Jing Dong, Tianxing He, Jingzhao Zhang

Given the rising popularity of AI-generated art and the associated copyright concerns, identifying whether an artwork was used to train a diffusion model is an important research topic. The work approaches this problem from the membership inference attack (MIA) perspective. We first identify the limitation of applying existing MIA methods for proprietary diffusion models: the required access of internal U-nets. To address the above problem, we introduce a novel membership inference attack method that uses only the image-to-image variation API and operates without access to the model's internal U-net. Our method is based on the intuition that the model can more easily obtain an unbiased noise prediction estimate for images from the training set. By applying the API multiple times to the target image, averaging the outputs, and comparing the result to the original image, our approach can classify whether a sample was part of the training set. We validate our method using DDIM and Stable Diffusion setups and further extend both our approach and existing algorithms to the Diffusion Transformer architecture. Our experimental results consistently outperform previous methods.

♻ ☆ MultiFormer: A Multi-Person Pose Estimation System Based on CSI and Attention Mechanism

Yanyi Qu, Haoyang Ma, Wenhui Xiong

Human pose estimation based on Channel State Information (CSI) has emerged as a promising approach for non-intrusive and precise human activity monitoring, yet faces challenges including accurate multi-person pose recognition and effective CSI feature learning. This paper presents MultiFormer, a wireless sensing system that accurately estimates human pose through CSI. The proposed system adopts a Transformer based time-frequency dual-token feature extractor with multi-head self-attention. This feature extractor is able to model inter-subcarrier correlations and temporal dependencies of the CSI. The extracted CSI features and the pose probability heatmaps are then fused by Multi-Stage Feature Fusion Network (MSFN) to enforce the anatomical constraints. Extensive experiments conducted on on the public MM-Fi dataset and our self-collected dataset show that the MultiFormer achieves higher accuracy over state-of-the-art approaches, especially for high-mobility keypoints (wrists, elbows) that are particularly difficult for previous methods to accurately estimate.

♻ ☆ A Simple yet Powerful Instance-Aware Prompting Framework for Training-free Camouflaged Object Segmentation

Chao Yin, Jide Li, Xiaoqiang Li

Camouflaged Object Segmentation (COS) remains highly challenging due to the intrinsic visual similarity between target objects and their surroundings. While training-based COS methods achieve good performance, their performance degrades rapidly with increased annotation sparsity. To circumvent this limitation, recent studies have explored training-free COS methods, leveraging the Segment Anything Model (SAM) by automatically generating visual prompts from a single task-generic prompt (\textit{e.g.}, "\textit{camouflaged animal}") uniformly applied across all test images. However, these methods typically produce only semantic-level visual prompts, causing SAM to output coarse semantic masks and thus failing to handle scenarios with multiple discrete camouflaged instances effectively. To address this critical limitation, we propose a simple yet powerful \textbf{I}nstance-\textbf{A}ware \textbf{P}rompting \textbf{F}ramework (IAPF), the first training-free COS pipeline that explicitly converts a task-generic prompt into fine-grained instance masks. Specifically, the IAPF comprises three steps: (1) Text Prompt Generator, utilizing task-generic queries to prompt a Multimodal Large Language Model (MLLM) for generating image-specific foreground and background tags; (2) \textbf{Instance Mask Generator}, leveraging Grounding DINO to produce precise instance-level bounding box prompts, alongside the proposed Single-Foreground Multi-Background Prompting strategy to sample region-constrained point prompts within each box, enabling SAM to yield a candidate instance mask; (3) Self-consistency Instance Mask Voting, which selects the final COS prediction by identifying the candidate mask most consistent across multiple candidate instance masks. Extensive evaluations on standard COS benchmarks demonstrate that the proposed IAPF significantly surpasses existing state-of-the-art training-free COS methods.

comment: under review

♻ ☆ GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes

Seunghyeok Back, Joosoon Lee, Kangmin Kim, Heeseon Rho, Geonhyup Lee, Raeyoung Kang, Sangbeom Lee, Sangjun Noh, Youngjin Lee, Taeyeop Lee, Kyoobin Lee

Robust grasping in cluttered environments remains an open challenge in robotics. While benchmark datasets have significantly advanced deep learning methods, they mainly focus on simplistic scenes with light occlusion and insufficient diversity, limiting their applicability to practical scenarios. We present GraspClutter6D, a large-scale real-world grasping dataset featuring: (1) 1,000 highly cluttered scenes with dense arrangements (14.1 objects/scene, 62.6\% occlusion), (2) comprehensive coverage across 200 objects in 75 environment configurations (bins, shelves, and tables) captured using four RGB-D cameras from multiple viewpoints, and (3) rich annotations including 736K 6D object poses and 9.3B feasible robotic grasps for 52K RGB-D images. We benchmark state-of-the-art segmentation, object pose estimation, and grasp detection methods to provide key insights into challenges in cluttered environments. Additionally, we validate the dataset's effectiveness as a training resource, demonstrating that grasping networks trained on GraspClutter6D significantly outperform those trained on existing datasets in both simulation and real-world experiments. The dataset, toolkit, and annotation tools are publicly available on our project website: https://sites.google.com/view/graspclutter6d.

♻ ☆ HVL: Semi-Supervised Segmentation leveraging Hierarchical Vision-Language Synergy with Dynamic Text-Spatial Query Alignment

Numair Nadeem, Saeed Anwar, Muhammad Hamza Asad, Abdul Bais

In this paper, we address Semi-supervised Semantic Segmentation (SSS) under domain shift by leveraging domain-invariant semantic knowledge from text embeddings of Vision-Language Models (VLMs). We propose a unified Hierarchical Vision-Language framework (HVL) that integrates domain-invariant text embeddings as object queries in a transformer-based segmentation network to improve generalization and reduce misclassification under limited supervision. The mentioned textual queries are used for grouping pixels with shared semantics under SSS. HVL is designed to (1) generate textual queries that maximally encode domain-invariant semantics from VLM while capturing intra-class variations; (2) align these queries with spatial visual features to enhance their segmentation ability and improve the semantic clarity of visual features. We also introduce targeted regularization losses that maintain vision--language alignment throughout training to reinforce semantic understanding. HVL establishes a novel state-of-the-art by achieving a +9.3% improvement in mean Intersection over Union (mIoU) on COCO, utilizing 232 labelled images, +3.1% on Pascal VOC employing 92 labels, +4.8% on ADE20 using 316 labels, and +3.4% on Cityscapes with 100 labels, demonstrating superior performance with less than 1% supervision on four benchmark datasets. Our results show that language-guided segmentation bridges the label efficiency gap and enables new levels of fine-grained generalization.

♻ ☆ Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding

Dawei Huang, Qing Li, Chuan Yan, Zebang Cheng, Zihao Han, Yurong Huang, Xiang Li, Bin Li, Xiaohui Wang, Zheng Lian, Zhi-Qi Cheng, Xiaojiang Peng

Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Although recent Large Multimodal Models (LMMs) have exhibited significant progress in general vision-language (VL) tasks, their performance often deteriorates in emotion-specific scenarios, exhibiting catastrophic forgetting when fine-tuned on emotion-centric tasks. To overcome these limitations, we propose Emotion-Qwen, a unified multimodal framework designed to simultaneously enable robust emotion understanding and preserve general VL reasoning capabilities. Emotion-Qwen introduces a novel Hybrid Compressor based on a Mixture-of-Experts (MoE) architecture, dynamically routing inputs to optimally balance emotion-specific processing and general multimodal reasoning. We further propose a carefully structured three-stage pre-training pipeline, leveraging extensive general and emotion-focused datasets to strengthen multimodal representation robustness and model adaptability. Additionally, we develop the Video Emotion Reasoning (VER) dataset, a large-scale bilingual resource containing over 40K video clips annotated with detailed context-aware emotional descriptions, significantly facilitating research on fine-grained emotional reasoning. Extensive experiments confirm that Emotion-Qwen achieves state-of-the-art performance across multiple emotion recognition and reasoning benchmarks, while maintaining highly competitive results in general VL tasks.

♻ ☆ MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention

Qi Xie, Yongjia Ma, Donglin Di, Xuehao Gao, Xun Yang

Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To address these limitations, we propose MoCA, a novel Video Diffusion Model built on a Diffusion Transformer (DiT) backbone, incorporating a Mixture of Cross-Attention mechanism inspired by the Mixture-of-Experts paradigm. Our framework improves inter-frame identity consistency by embedding MoCA layers into each DiT block, where Hierarchical Temporal Pooling captures identity features over varying timescales, and Temporal-Aware Cross-Attention Experts dynamically model spatiotemporal relationships. We further incorporate a Latent Video Perceptual Loss to enhance identity coherence and fine-grained details across video frames. To train this model, we collect CelebIPVid, a dataset of 10,000 high-resolution videos from 1,000 diverse individuals, promoting cross-ethnicity generalization. Extensive experiments on CelebIPVid show that MoCA outperforms existing T2V methods by over 5% across Face similarity.

♻ ☆ DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes

Jiajun Jiang, Yiming Zhu, Zirui Wu, Jie Song

We introduce DualMap, an online open-vocabulary mapping system that enables robots to understand and navigate dynamically changing environments through natural language queries. Designed for efficient semantic mapping and adaptability to changing environments, DualMap meets the essential requirements for real-world robot navigation applications. Our proposed hybrid segmentation frontend and object-level status check eliminate the costly 3D object merging required by prior methods, enabling efficient online scene mapping. The dual-map representation combines a global abstract map for high-level candidate selection with a local concrete map for precise goal-reaching, effectively managing and updating dynamic changes in the environment. Through extensive experiments in both simulation and real-world scenarios, we demonstrate state-of-the-art performance in 3D open-vocabulary segmentation, efficient scene mapping, and online language-guided navigation.Project page: https://eku127.github.io/DualMap/

comment: 14 pages, 14 figures. Code: https://github.com/Eku127/DualMap Project page: https://eku127.github.io/DualMap/

♻ ☆ NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations

Zhenyu Tang, Chaoran Feng, Xinhua Cheng, Wangbo Yu, Junwu Zhang, Yuan Liu, Xiaoxiao Long, Wenping Wang, Li Yuan

3D Gaussian Splatting (3DGS) achieves impressive quality and rendering speed, but with millions of 3D Gaussians and significant storage and transmission costs. In this paper, we aim to develop a simple yet effective method called NeuralGS that compresses the original 3DGS into a compact representation. Our observation is that neural fields like NeRF can represent complex 3D scenes with Multi-Layer Perceptron (MLP) neural networks using only a few megabytes. Thus, NeuralGS effectively adopts the neural field representation to encode the attributes of 3D Gaussians with MLPs, only requiring a small storage size even for a large-scale scene. To achieve this, we adopt a clustering strategy and fit the Gaussians within each cluster using different tiny MLPs, based on importance scores of Gaussians as fitting weights. We experiment on multiple datasets, achieving a 91-times average model size reduction without harming the visual quality.

comment: Project page: https://pku-yuangroup.github.io/NeuralGS/

♻ ☆ Prompt-aligned Gradient for Prompt Tuning

Beier Zhu, Yulei Niu, Yucheng Han, Yue Wu, Hanwang Zhang

Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a zero-shot classifier by "prompt", e.g., the confidence score of an image being "[CLASS]" can be obtained by using the VLM provided similarity measure between the image and the prompt sentence "a photo of a [CLASS]". Therefore, prompt shows a great potential for fast adaptation of VLMs to downstream tasks if we fine-tune the prompt-based similarity measure. However, we find a common failure that improper fine-tuning may not only undermine the prompt's inherent prediction for the task-related classes, but also for other classes in the VLM vocabulary. Existing methods still address this problem by using traditional anti-overfitting techniques such as early stopping and data augmentation, which lack a principled solution specific to prompt. We present Prompt-aligned Gradient, dubbed ProGrad, to prevent prompt tuning from forgetting the the general knowledge learned from VLMs. In particular, ProGrad only updates the prompt whose gradient is aligned (or non-conflicting) to the "general direction", which is represented as the gradient of the KL loss of the pre-defined prompt prediction. Extensive experiments demonstrate the stronger few-shot generalization ability of ProGrad over state-of-the-art prompt tuning methods. Codes are available at https://github.com/BeierZhu/Prompt-align.

comment: ICCV2023

♻ ☆ Scaling Vision Mamba Across Resolutions via Fractal Traversal

Bo Li, Haoke Xiao, Lv Tang

Vision Mamba has recently emerged as a promising alternative to Transformer-based architectures, offering linear complexity in sequence length while maintaining strong modeling capacity. However, its adaptation to visual inputs is hindered by challenges in 2D-to-1D patch serialization and weak scalability across input resolutions. Existing serialization strategies such as raster scanning disrupt local spatial continuity and limit the model's ability to generalize across scales. In this paper, we propose FractalMamba++, a robust vision backbone that leverages fractal-based patch serialization via Hilbert curves to preserve spatial locality and enable seamless resolution adaptability. To address long-range dependency fading in high-resolution inputs, we further introduce a Cross-State Routing (CSR) mechanism that enhances global context propagation through selective state reuse. Additionally, we propose a Positional-Relation Capture (PRC) module to recover local adjacency disrupted by curve inflection points. Extensive experiments across diverse downstream tasks, including image classification, semantic segmentation and object detection, demonstrate that FractalMamba++ consistently outperforms previous Mamba-based backbones, with particularly notable gains under high-resolution settings.

♻ ☆ SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference ICML

Jintao Zhang, Chendong Xiang, Haofeng Huang, Jia Wei, Haocheng Xi, Jun Zhu, Jianfei Chen

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of corresponding computations. Many studies have utilized the sparse pattern to accelerate attention. However, most existing works focus on optimizing attention within specific models by exploiting certain sparse patterns of the attention map. A universal sparse attention that guarantees both the speedup and end-to-end performance of diverse models remains elusive. In this paper, we propose SpargeAttn, a universal sparse and quantized attention for any model. Our method uses a two-stage online filter: in the first stage, we rapidly and accurately predict the attention map, enabling the skip of some matrix multiplications in attention. In the second stage, we design an online softmax-aware filter that incurs no extra overhead and further skips some matrix multiplications. Experiments show that our method significantly accelerates diverse models, including language, image, and video generation, without sacrificing end-to-end metrics. The codes are available at https://github.com/thu-ml/SpargeAttn.

comment: @inproceedings{zhang2025spargeattn, title={Spargeattn: Accurate sparse attention accelerating any model inference}, author={Zhang, Jintao and Xiang, Chendong and Huang, Haofeng and Wei, Jia and Xi, Haocheng and Zhu, Jun and Chen, Jianfei}, booktitle={International Conference on Machine Learning (ICML)}, year={2025} }

2025-08-12

Sound 24

☆ Neutone SDK: An Open Source Framework for Neural Audio Processing

Christopher Mitcheltree, Bogdan Teleaga, Andrew Fyfe, Naotake Masuda, Matthias Schäfer, Alfie Bradic, Nao Tokui

Neural audio processing has unlocked novel methods of sound transformation and synthesis, yet integrating deep learning models into digital audio workstations (DAWs) remains challenging due to real-time / neural network inference constraints and the complexities of plugin development. In this paper, we introduce the Neutone SDK: an open source framework that streamlines the deployment of PyTorch-based neural audio models for both real-time and offline applications. By encapsulating common challenges such as variable buffer sizes, sample rate conversion, delay compensation, and control parameter handling within a unified, model-agnostic interface, our framework enables seamless interoperability between neural models and host plugins while allowing users to work entirely in Python. We provide a technical overview of the interfaces needed to accomplish this, as well as the corresponding SDK implementations. We also demonstrate the SDK's versatility across applications such as audio effect emulation, timbre transfer, and sample generation, as well as its adoption by researchers, educators, companies, and artists alike. The Neutone SDK is available at https://github.com/Neutone/neutone_sdk

comment: Accepted to AES International Conference on Artificial Intelligence and Machine Learning for Audio 2025

☆ Revealing the Role of Audio Channels in ASR Performance Degradation

Kuan-Tang Huang, Li-Wei Chen, Hung-Shin Lee, Berlin Chen, Hsin-Min Wang

Pre-trained automatic speech recognition (ASR) models have demonstrated strong performance on a variety of tasks. However, their performance can degrade substantially when the input audio comes from different recording channels. While previous studies have demonstrated this phenomenon, it is often attributed to the mismatch between training and testing corpora. This study argues that variations in speech characteristics caused by different recording channels can fundamentally harm ASR performance. To address this limitation, we propose a normalization technique designed to mitigate the impact of channel variation by aligning internal feature representations in the ASR model with those derived from a clean reference channel. This approach significantly improves ASR performance on previously unseen channels and languages, highlighting its ability to generalize across channel and language differences.

comment: Accepted to IEEE ASRU 2025

☆ DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models

Yuanyuan Wang, Dongchao Yang, Yiwen Shao, Hangting Chen, Jiankun Zhao, Zhiyong Wu, Helen Meng, Xixin Wu

☆ QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems

Chien-Chun Wang, Kuan-Tang Huang, Cheng-Yeh Yang, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen

Evaluating audio generation systems, including text-to-music (TTM), text-to-speech (TTS), and text-to-audio (TTA), remains challenging due to the subjective and multi-dimensional nature of human perception. Existing methods treat mean opinion score (MOS) prediction as a regression problem, but standard regression losses overlook the relativity of perceptual judgments. To address this limitation, we introduce QAMRO, a novel Quality-aware Adaptive Margin Ranking Optimization framework that seamlessly integrates regression objectives from different perspectives, aiming to highlight perceptual differences and prioritize accurate ratings. Our framework leverages pre-trained audio-text models such as CLAP and Audiobox-Aesthetics, and is trained exclusively on the official AudioMOS Challenge 2025 dataset. It demonstrates superior alignment with human evaluations across all dimensions, significantly outperforming robust baseline models.

comment: Accepted to IEEE ASRU 2025

☆ Listen through the Sound: Generative Speech Restoration Leveraging Acoustic Context Representation INTERSPEECH 2025

Soo-Whan Chung, Min-Seok Choi

This paper introduces a novel approach to speech restoration by integrating a context-related conditioning strategy. Specifically, we employ the diffusion-based generative restoration model, UNIVERSE++, as a backbone to evaluate the effectiveness of contextual representations. We incorporate acoustic context embeddings extracted from the CLAP model, which capture the environmental attributes of input audio. Additionally, we propose an Acoustic Context (ACX) representation that refines CLAP embeddings to better handle various distortion factors and their intensity in speech signals. Unlike content-based approaches that rely on linguistic and speaker attributes, ACX provides contextual information that enables the restoration model to distinguish and mitigate distortions better. Experimental results indicate that context-aware conditioning improves both restoration performance and its stability across diverse distortion conditions, reducing variability compared to content-based methods.

comment: Accepted to INTERSPEECH 2025

☆ LPGNet: A Lightweight Network with Parallel Attention and Gated Fusion for Multimodal Emotion Recognition

Zhining He, Yang Xiao

Emotion recognition in conversations (ERC) aims to predict the emotional state of each utterance by using multiple input types, such as text and audio. While Transformer-based models have shown strong performance in this task, they often face two major issues: high computational cost and heavy dependence on speaker information. These problems reduce their ability to generalize in real-world conversations. To solve these challenges, we propose LPGNet, a Lightweight network with Parallel attention and Gated fusion for multimodal ERC. The main part of LPGNet is the Lightweight Parallel Interaction Attention (LPIA) module. This module replaces traditional stacked Transformer layers with parallel dot-product attention, which can model both within-modality and between-modality relationships more efficiently. To improve emotional feature learning, LPGNet also uses a dual-gated fusion method. This method filters and combines features from different input types in a flexible and dynamic way. In addition, LPGNet removes speaker embeddings completely, which allows the model to work independently of speaker identity. Experiments on the IEMOCAP dataset show that LPGNet reaches over 87% accuracy and F1-score in 4-class emotion classification. It outperforms strong baseline models while using fewer parameters and showing better generalization across speakers.

comment: Under peering review

☆ Sound Signal Synthesis with Auxiliary Classifier GAN, COVID-19 cough as an example

Yahya Sherif Solayman Mohamed Saleh, Ahmed Mohammed Dabbous, Lama Alkhaled, Hum Yan Chai, Muhammad Ehsan Rana, Hamam Mokayed

One of the fastest-growing domains in AI is healthcare. Given its importance, it has been the interest of many researchers to deploy ML models into the ever-demanding healthcare domain to aid doctors and increase accessibility. Delivering reliable models, however, demands a sizable amount of data, and the recent COVID-19 pandemic served as a reminder of the rampant and scary nature of healthcare that makes training models difficult. To alleviate such scarcity, many published works attempted to synthesize radiological cough data to train better COVID-19 detection models on the respective radiological data. To accommodate the time sensitivity expected during a pandemic, this work focuses on detecting COVID-19 through coughs using synthetic data to improve the accuracy of the classifier. The work begins by training a CNN on a balanced subset of the Coughvid dataset, establishing a baseline classification test accuracy of 72%. The paper demonstrates how an Auxiliary Classification GAN (ACGAN) may be trained to conditionally generate novel synthetic Mel Spectrograms of both healthy and COVID-19 coughs. These coughs are used to augment the training dataset of the CNN classifier, allowing it to reach a new test accuracy of 75%. The work highlights the expected messiness and inconsistency in training and offers insights into detecting and handling such shortcomings.

☆ Transient Noise Removal via Diffusion-based Speech Inpainting

Mordehay Moradi, Sharon Gannot

In this paper, we present PGDI, a diffusion-based speech inpainting framework for restoring missing or severely corrupted speech segments. Unlike previous methods that struggle with speaker variability or long gap lengths, PGDI can accurately reconstruct gaps of up to one second in length while preserving speaker identity, prosody, and environmental factors such as reverberation. Central to this approach is classifier guidance, specifically phoneme-level guidance, which substantially improves reconstruction fidelity. PGDI operates in a speaker-independent manner and maintains robustness even when long segments are completely masked by strong transient noise, making it well-suited for real-world applications, such as fireworks, door slams, hammer strikes, and construction noise. Through extensive experiments across diverse speakers and gap lengths, we demonstrate PGDI's superior inpainting performance and its ability to handle challenging acoustic conditions. We consider both scenarios, with and without access to the transcript during inference, showing that while the availability of text further enhances performance, the model remains effective even in its absence. For audio samples, visit: https://mordehaym.github.io/PGDI/

comment: 23 pages, 3 figures, signal processing paper on speech inpainting

☆ Opening Musical Creativity? Embedded Ideologies in Generative-AI Music Systems

Liam Pram, Fabio Morreale

AI systems for music generation are increasingly common and easy to use, granting people without any musical background the ability to create music. Because of this, generative-AI has been marketed and celebrated as a means of democratizing music making. However, inclusivity often functions as marketable rhetoric rather than a genuine guiding principle in these industry settings. In this paper, we look at four generative-AI music making systems available to the public as of mid-2025 (AIVA, Stable Audio, Suno, and Udio) and track how they are rhetoricized by their developers, and received by users. Our aim is to investigate ideologies that are driving the early-stage development and adoption of generative-AI in music making, with a particular focus on democratization. A combination of autoethnography and digital ethnography is used to examine patterns and incongruities in rhetoric when positioned against product functionality. The results are then collated to develop a nuanced, contextual discussion. The shared ideology we map between producers and consumers is individualist, globalist, techno-liberal, and ethically evasive. It is a 'total ideology' which obfuscates individual responsibility, and through which the nature of music and musical practice is transfigured to suit generative outcomes.

comment: Extended version of the presentation at The First International Conference in AI Music Studies 2024

☆ SonicRadiation: A Hybrid Numerical Solution for Sound Radiation without Ghost Cells

Xutong Jin, Guoping Wang, Sheng Li

Interactive synthesis of physical sound effects is crucial in digital media production. Sound radiation simulation, a key component of physically based sound synthesis, has posed challenges in the context of complex object boundaries. Previous methods, such as ghost cell-based finite-difference time-domain (FDTD) wave solver, have struggled to address these challenges, leading to large errors and failures in complex boundaries because of the limitation of ghost cells. We present SonicRadiation, a hybrid numerical solution capable of handling complex and dynamic object boundaries in sound radiation simulation without relying on ghost cells. We derive a consistent formulation to connect the physical quantities on grid cells in FDTD with the boundary elements in the time-domain boundary element method (TDBEM). Hereby, we propose a boundary grid synchronization strategy to seamlessly integrate TDBEM with FDTD while maintaining high numerical accuracy. Our method holds both advantages from the accuracy of TDBEM for the near-field and the efficiency of FDTD for the far-field. Experimental results demonstrate the superiority of our method in sound radiation simulation over previous approaches in terms of accuracy and efficiency, particularly in complex scenes, further validating its effectiveness.

comment: 11 pages

☆ Multi-Target Backdoor Attacks Against Speaker Recognition

Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, Jesus Villalba Lopez, Najim Dehak, Patrick Cardinal

In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously, achieving success rates of up to 95.04%. To simulate more realistic attack conditions, we vary the signal-to-noise ratio between speech and trigger, demonstrating a trade-off between stealth and effectiveness. We further extend the attack to the speaker verification task by selecting the most similar training speaker - based on cosine similarity - as the target. The attack is most effective when target and enrolled speaker pairs are highly similar, reaching success rates of up to 90% in such cases.

comment: Accepted to IEEE Automatic Speech Recognition and Understanding Workshop 2025

☆ Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization ACL2025

Chaoqun Cui, Liangbin Huang, Shijing Wang, Zhe Tong, Zhaolong Huang, Xiao Zeng, Xiaofeng Liu

Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech technologies. Due to varying information densities across languages, target speech often mismatches the source speech duration, causing audio-video synchronization issues that significantly impact viewer experience. In this study, we approach duration alignment in LLM-based video dubbing machine translation as a preference optimization problem. We propose the Segment Supervised Preference Optimization (SSPO) method, which employs a segment-wise sampling strategy and fine-grained loss to mitigate duration mismatches between source and target lines. Experimental results demonstrate that SSPO achieves superior performance in duration alignment tasks.

comment: This paper is accepted by ACL2025 (Main)

☆ ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs

Eray Eren, Qingju Liu, Hyeongwoo Kim, Pablo Garrido, Abeer Alwan

Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks such as TTS. The ProMode encoder takes as input acoustic features and time-aligned textual content, both are partially masked, and obtains a fixed-length latent prosodic embedding. The decoder predicts acoustics in the masked region using both the encoded prosody input and unmasked textual content. Trained on the GigaSpeech dataset, we compare our method with state-of-the-art style encoders. For F0 and energy predictions, we show consistent improvements for our model at different levels of granularity. We also integrate these predicted prosodic features into a TTS system and conduct perceptual tests, which show higher prosody preference compared to the baselines, demonstrating the model's potential in tasks where prosody modeling is important.

comment: Interspeech 2025; demo page at https://promode8272.github.io/promode/index.html

☆ Selection of Layers from Self-supervised Learning Models for Predicting Mean-Opinion-Score of Speech

Xinyu Liang, Fredrik Cumlin, Victor Ungureanu, Chandan K. A. Reddy, Christian Schuldt, Saikat Chatterjee

Self-supervised learning (SSL) models like Wav2Vec2, HuBERT, and WavLM have been widely used in speech processing. These transformer-based models consist of multiple layers, each capturing different levels of representation. While prior studies explored their layer-wise representations for efficiency and performance, speech quality assessment (SQA) models predominantly rely on last-layer features, leaving intermediate layers underexamined. In this work, we systematically evaluate different layers of multiple SSL models for predicting mean-opinion-score (MOS). Features from each layer are fed into a lightweight regression network to assess effectiveness. Our experiments consistently show early-layers features outperform or match those from the last layer, leading to significant improvements over conventional approaches and state-of-the-art MOS prediction models. These findings highlight the advantages of early-layer selection, offering enhanced performance and reduced system complexity.

comment: Accepted at IEEE ASRU 2025

☆ Dynamic Synchronization and Resonance as a Universal Origin of 1/f Fluctuations -- Amplitude Modulation Across Music and Nature

Akika Nakamichi, Izumi Uesaka, Masahiro Morikawa

We propose a universal physical mechanism for the emergence of 1/f fluctuations, observed across a wide range of systems. In particular, we verify this on acoustic cases. The mechanism is based on amplitude modulation (AM) and demodulation (DM), where the 1/f spectral law arises not in the raw waveform but in its demodulated amplitude envelope. Two distinct yet complementary processes generate the required AM: (i) stochastic synchronization among oscillators, modeled via an extended Kuramoto framework that captures perpetual synchronization-desynchronization cycles, and (ii) frequency-selective resonance, modeled by spectral accumulation of eigenmodes in acoustic or structural environments. Numerical simulations demonstrate that both mechanisms, acting separately or in combination, robustly produce 1/f spectra over several decades when DM is applied, and that the classical Kuramoto critical point is not necessary for their emergence. We demonstrate the cross-domain relevance of this AM/DM framework through analyses of musical performances, seismic records, and astrophysical time series, revealing a common underlying structure. This work establishes demodulation as a general route to 1/f fluctuations, providing a simple and scalable explanation for its ubiquity in both natural and engineered systems. Keywords: 1/f fluctuation, amplitude modulation, synchronization, resonance, Kuramoto model, music, natural noise, demodulation

comment: 14 pages, 10 figures

☆ Music and Artificial Intelligence: Artistic Trends

Jordi Pons, Zack Zukowski, Julian D. Parker, CJ Carr, Josiah Taylor, Zach Evans

We study how musicians use artificial intelligence (AI) across formats like singles, albums, performances, installations, voices, ballets, operas, or soundtracks. We collect 337 music artworks and categorize them based on AI usage: AI composition, co-composition, sound design, lyrics generation, and translation. We find that AI is employed as a co-creative tool, as an artistic medium, and in live performances and installations. Innovative uses of AI include exploring uncanny aesthetics, multilingual and multigenre song releases, and new formats such as online installations. This research provides a comprehensive overview of current AI music practices, offering insights into emerging artistic trends and the challenges faced by AI musicians.

♻ ☆ Dopamine Audiobook: A Training-free MLLM Agent for Emotional and Immersive Audiobook Generation

Yan Rong, Shan Yang, Chenxing Li, Dong Yu, Li Liu

Audiobook generation aims to create rich, immersive listening experiences from multimodal inputs, but current approaches face three critical challenges: (1) the lack of synergistic generation of diverse audio types (e.g., speech, sound effects, and music) with precise temporal and semantic alignment; (2) the difficulty in conveying expressive, fine-grained emotions, which often results in machine-like vocal outputs; and (3) the absence of automated evaluation frameworks that align with human preferences for complex and diverse audio. To address these issues, we propose Dopamine Audiobook, a novel unified training-free multi-agent system, where a multimodal large language model (MLLM) serves two specialized roles (i.e., speech designer and audio designer) for emotional, human-like, and immersive audiobook generation and evaluation. Specifically, we firstly propose a flow-based, context-aware framework for diverse audio generation with word-level semantic and temporal alignment. To enhance expressiveness, we then design word-level paralinguistic augmentation, utterance-level prosody retrieval, and adaptive TTS model selection. Finally, for evaluation, we introduce a novel MLLM-based evaluation framework incorporating self-critique, perspective-taking, and psychological MagicEmo prompts to ensure human-aligned and self-aligned assessments. Experimental results demonstrate that our method achieves state-of-the-art (SOTA) performance on multiple metrics. Importantly, our evaluation framework shows better alignment with human preferences and transferability across audio tasks.

♻ ☆ TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree

Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan, Vitaly Lavrukhin, Boris Ginsburg

Recognizing specific key phrases is an essential task for contextualized Automatic Speech Recognition (ASR). However, most existing context-biasing approaches have limitations associated with the necessity of additional model training, significantly slow down the decoding process, or constrain the choice of the ASR system type. This paper proposes a universal ASR context-biasing framework that supports all major types: CTC, Transducers, and Attention Encoder-Decoder models. The framework is based on a GPU-accelerated word boosting tree, which enables it to be used in shallow fusion mode for greedy and beam search decoding without noticeable speed degradation, even with a vast number of key phrases (up to 20K items). The obtained results showed high efficiency of the proposed method, surpassing the considered open-source context-biasing approaches in accuracy and decoding speed. Our context-biasing framework is open-sourced as a part of the NeMo toolkit.

comment: Accepted to ASRU 2025

♻ ☆ 3DFacePolicy: Audio-Driven 3D Facial Animation Based on Action Control

Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita, Naoya Chiba, Yuki Uranishi

Audio-driven 3D facial animation has achieved significant progress in both research and applications. While recent baselines struggle to generate natural and continuous facial movements due to their frame-by-frame vertex generation approach, we propose 3DFacePolicy, a pioneer work that introduces a novel definition of vertex trajectory changes across consecutive frames through the concept of "action". By predicting action sequences for each vertex that encode frame-to-frame movements, we reformulate vertex generation approach into an action-based control paradigm. Specifically, we leverage a robotic control mechanism, diffusion policy, to predict action sequences conditioned on both audio and vertex states. Extensive experiments on VOCASET and BIWI datasets demonstrate that our approach significantly outperforms state-of-the-art methods and is particularly expert in dynamic, expressive and naturally smooth facial animations.

♻ ☆ Learning Marmoset Vocal Patterns with a Masked Autoencoder for Robust Call Segmentation, Classification, and Caller Identification

Bin Wu, Shinnosuke Takamichi, Sakriani Sakti, Satoshi Nakamura

The marmoset, a highly vocal primate, is a key model for studying social-communicative behavior. Unlike human speech, marmoset vocalizations are less structured, highly variable, and recorded in noisy, low-resource conditions. Learning marmoset communication requires joint call segmentation, classification, and caller identification -- challenging domain tasks. Previous CNNs handle local patterns but struggle with long-range temporal structure. We applied Transformers using self-attention for global dependencies. However, Transformers show overfitting and instability on small, noisy annotated datasets. To address this, we pretrain Transformers with MAE -- a self-supervised method reconstructing masked segments from hundreds of hours of unannotated marmoset recordings. The pretraining improved stability and generalization. Results show MAE-pretrained Transformers outperform CNNs, demonstrating modern self-supervised architectures effectively model low-resource non-human vocal communication.

comment: Accepted by ASRU 2025

♻ ☆ Marco-Voice Technical Report

Fengping Tian, Chenyang Lyu, Xuanfan Ni, Haoqin Sun, Qingjuan Li, Zhiqiang Qian, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo, Kaifu Zhang

comment: Technical Report. Our code and dataset are publicly available at https://github.com/AIDC-AI/Marco-Voice and https://huggingface.co/datasets/AIDC-AI/CSEMOTIONS respectively

♻ ☆ Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning

Shu Wu, Chenxing Li, Wenfu Wang, Hao Zhang, Hualei Wang, Meng Yu, Dong Yu

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning with rule-based rewards. However, the explicit reasoning process has yet to show significant benefits for audio question answering, and effectively leveraging deep reasoning remains an open challenge, with LALMs still falling short of human-level auditory-language reasoning. To address these limitations, we propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of LALMs, with a focus on improving adaptability, consistency, and effectiveness. Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task complexity dynamically. Furthermore, we incorporate an external reward model to evaluate the overall consistency and quality of the reasoning process, complemented by think-based rewards that help the model distinguish between valid and flawed reasoning paths during training. Experimental results demonstrate that our Audio-Thinker model outperforms existing reasoning-oriented LALMs across various benchmark tasks, exhibiting superior reasoning and generalization capabilities.

comment: preprint

♻ ☆ Gotta Hear Them All: Towards Sound Source Aware Audio Generation

Wei Guo, Heng Wang, Jianbo Ma, Weidong Cai

Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existing methods solely rely on the global scene and overlook details of local sounding objects (i.e., sound sources). To address this issue, we propose a Sound Source-Aware Audio (SS2A) generator. SS2A is able to locally perceive multimodal sound sources from a scene with visual detection and cross-modality translation. It then contrastively learns a Cross-Modal Sound Source (CMSS) Manifold to semantically disambiguate each source. Finally, we attentively mix their CMSS semantics into a rich audio representation, from which a pretrained audio generator outputs the sound. To model the CMSS manifold, we curate a novel single-sound-source visual-audio dataset VGGS3 from VGGSound. We also design a Sound Source Matching Score to clearly measure localized audio relevance. With the effectiveness of explicit sound source modeling, SS2A achieves state-of-the-art performance in extensive image-to-audio tasks. We also qualitatively demonstrate SS2A's ability to achieve intuitive synthesis control by compositing vision, text, and audio conditions. Furthermore, we show that our sound source modeling can achieve competitive video-to-audio performance with a straightforward temporal aggregation mechanism.

comment: 17 pages, 12 figures, source code available at https://github.com/wguo86/SSV2A

♻ ☆ VGGSounder: Audio-Visual Evaluations for Foundation Models

Daniil Zverev, Thaddäus Wiedemer, Ameya Prabhu, Matthias Bethge, Wieland Brendel, A. Sophia Koepke

The emergence of audio-visual foundation models underscores the importance of reliably assessing their multi-modal understanding. The VGGSound dataset is commonly used as a benchmark for evaluation audio-visual classification. However, our analysis identifies several limitations of VGGSound, including incomplete labelling, partially overlapping classes, and misaligned modalities. These lead to distorted evaluations of auditory and visual capabilities. To address these limitations, we introduce VGGSounder, a comprehensively re-annotated, multi-label test set that extends VGGSound and is specifically designed to evaluate audio-visual foundation models. VGGSounder features detailed modality annotations, enabling precise analyses of modality-specific performance. Furthermore, we reveal model limitations by analysing performance degradation when adding another input modality with our new modality confusion metric.

comment: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2025

Audio and Speech Processing 22

☆ Neutone SDK: An Open Source Framework for Neural Audio Processing

Christopher Mitcheltree, Bogdan Teleaga, Andrew Fyfe, Naotake Masuda, Matthias Schäfer, Alfie Bradic, Nao Tokui

comment: Accepted to AES International Conference on Artificial Intelligence and Machine Learning for Audio 2025

☆ Selection of Layers from Self-supervised Learning Models for Predicting Mean-Opinion-Score of Speech

Xinyu Liang, Fredrik Cumlin, Victor Ungureanu, Chandan K. A. Reddy, Christian Schuldt, Saikat Chatterjee

comment: Accepted at IEEE ASRU 2025

☆ DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models

Yuanyuan Wang, Dongchao Yang, Yiwen Shao, Hangting Chen, Jiankun Zhao, Zhiyong Wu, Helen Meng, Xixin Wu

☆ Listen through the Sound: Generative Speech Restoration Leveraging Acoustic Context Representation INTERSPEECH 2025

Soo-Whan Chung, Min-Seok Choi

comment: Accepted to INTERSPEECH 2025

☆ DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

Alexander Polok, Santosh Kesiraju, Karel Beneš, Bolaji Yusuf, Lukáš Burget, Jan Černocký

This paper presents a simple yet effective regularization for the internal language model induced by the decoder in encoder-decoder ASR models, thereby improving robustness and generalization in both in- and out-of-domain settings. The proposed method, Decoder-Centric Regularization in Encoder-Decoder (DeCRED), adds auxiliary classifiers to the decoder, enabling next token prediction via intermediate logits. Empirically, DeCRED reduces the mean internal LM BPE perplexity by 36.6% relative to 11 test sets. Furthermore, this translates into actual WER improvements over the baseline in 5 of 7 in-domain and 3 of 4 out-of-domain test sets, reducing macro WER from 6.4% to 6.3% and 18.2% to 16.2%, respectively. On TEDLIUM3, DeCRED achieves 7.0% WER, surpassing the baseline and encoder-centric InterCTC regularization by 0.6% and 0.5%, respectively. Finally, we compare DeCRED with OWSM v3.1 and Whisper-medium, showing competitive WERs despite training on much less data with fewer parameters.

comment: Accepted at IEEE ASRU 2025

☆ LPGNet: A Lightweight Network with Parallel Attention and Gated Fusion for Multimodal Emotion Recognition

Zhining He, Yang Xiao

comment: Under peering review

☆ EGGCodec: A Robust Neural Encodec Framework for EGG Reconstruction and F0 Extraction

Rui Feng, Yuang Chen, Yu Hu, Jun Du, Jiahong Yuan

This letter introduces EGGCodec, a robust neural Encodec framework engineered for electroglottography (EGG) signal reconstruction and F0 extraction. We propose a multi-scale frequency-domain loss function to capture the nuanced relationship between original and reconstructed EGG signals, complemented by a time-domain correlation loss to improve generalization and accuracy. Unlike conventional Encodec models that extract F0 directly from features, EGGCodec leverages reconstructed EGG signals, which more closely correspond to F0. By removing the conventional GAN discriminator, we streamline EGGCodec's training process without compromising efficiency, incurring only negligible performance degradation. Trained on a widely used EGG-inclusive dataset, extensive evaluations demonstrate that EGGCodec outperforms state-of-the-art F0 extraction schemes, reducing mean absolute error (MAE) from 14.14 Hz to 13.69 Hz, and improving voicing decision error (VDE) by 38.2\%. Moreover, extensive ablation experiments validate the contribution of each component of EGGCodec.

comment: 5 pages, 5 figures, to be appeared in IEEE Signal Processing Letters

☆ Transient Noise Removal via Diffusion-based Speech Inpainting

Mordehay Moradi, Sharon Gannot

comment: 23 pages, 3 figures, signal processing paper on speech inpainting

☆ MultiAiTutor: Child-Friendly Educational Multilingual Speech Generation Tutor with LLMs

Xiaoxue Gao, Huayun Zhang, Nancy F. Chen

comment: 5 figures

☆ Joint decoding method for controllable contextual speech recognition based on Speech LLM

Yangui Fang, Jing Peng, Yu Xi, Xu Li, Haoyu Li, Chengwei Zhang, Guohui Zhong, Kai Yu

Contextual speech recognition refers to the ability to identify preferences for specific content based on contextual information. Recently, leveraging the contextual understanding capabilities of Speech LLM to achieve contextual biasing by injecting contextual information through prompts have emerged as a research hotspot.However, the direct information injection method via prompts relies on the internal attention mechanism of the model, making it impossible to explicitly control the extent of information injection. To address this limitation, we propose a joint decoding method to control the contextual information. This approach enables explicit control over the injected contextual information and achieving superior recognition performance. Additionally, Our method can also be used for sensitive word suppression recognition.Furthermore, experimental results show that even Speech LLM not pre-trained on long contextual data can acquire long contextual capabilities through our method.

☆ ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs

Eray Eren, Qingju Liu, Hyeongwoo Kim, Pablo Garrido, Abeer Alwan

comment: Interspeech 2025; demo page at https://promode8272.github.io/promode/index.html

☆ Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative

Xi Xuan, Zimo Zhu, Wenxin Zhang, Yi-Cheng Lin, Tomi Kinnunen

Advances in speech synthesis intensify security threats, motivating real-time deepfake detection research. We investigate whether bidirectional Mamba can serve as a competitive alternative to Self-Attention in detecting synthetic speech. Our solution, Fake-Mamba, integrates an XLSR front-end with bidirectional Mamba to capture both local and global artifacts. Our core innovation introduces three efficient encoders: TransBiMamba, ConBiMamba, and PN-BiMamba. Leveraging XLSR's rich linguistic representations, PN-BiMamba can effectively capture the subtle cues of synthetic speech. Evaluated on ASVspoof 21 LA, 21 DF, and In-The-Wild benchmarks, Fake-Mamba achieves 0.97%, 1.74%, and 5.85% EER, respectively, representing substantial relative gains over SOTA models XLSR-Conformer and XLSR-Mamba. The framework maintains real-time inference across utterance lengths, demonstrating strong generalization and practical viability. The code is available at https://github.com/xuanxixi/Fake-Mamba.

comment: Accepted at IEEE ASRU 2025

☆ Objective Soups: Multilingual Multi-Task Modeling for Speech Processing

A F M Saif, Lisha Chen, Xiaodong Cui, Songtao Lu, Brian Kingsbury, Tianyi Chen

Training a single model for multilingual, multi-task speech processing (MSP) is severely hampered by conflicting objectives between tasks like speech recognition and translation. While multi-objective optimization (MOO) aims to align gradient updates, its effectiveness diminishes as the number of tasks grows, making it difficult to find a common descent direction. This raises a fundamental question: should highly conflicting objectives be optimized jointly or separated into a hierarchical structure? To address this question, this paper investigates three multi-objective MSP formulations, which we refer to as \textbf{objective soup recipes}. These formulations apply multi-objective optimization at different optimization levels to mitigate potential conflicts among all objectives. To ensure efficiency, we introduce a lightweight layer-selection mechanism that computes the conflict-avoiding gradient using only the most problematic layers, minimizing computational and memory overhead. Extensive experiments on CoVoST v2, LibriSpeech, and AISHELL-1 reveal that a bi-level recipe separating recognition and translation tasks consistently outperforms standard flat optimization. Our work demonstrates that hierarchical MOO is a more effective and scalable approach for building state-of-the-art MSP models. Our code has been released at https://github.com/afmsaif/Objective_Soups.

☆ Music and Artificial Intelligence: Artistic Trends

Jordi Pons, Zack Zukowski, Julian D. Parker, CJ Carr, Josiah Taylor, Zach Evans

♻ ☆ Dopamine Audiobook: A Training-free MLLM Agent for Emotional and Immersive Audiobook Generation

Yan Rong, Shan Yang, Chenxing Li, Dong Yu, Li Liu

♻ ☆ TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree

Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan, Vitaly Lavrukhin, Boris Ginsburg

comment: Accepted to ASRU 2025

♻ ☆ 3DFacePolicy: Audio-Driven 3D Facial Animation Based on Action Control

Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita, Naoya Chiba, Yuki Uranishi

♻ ☆ Learning Marmoset Vocal Patterns with a Masked Autoencoder for Robust Call Segmentation, Classification, and Caller Identification

Bin Wu, Shinnosuke Takamichi, Sakriani Sakti, Satoshi Nakamura

comment: Accepted by ASRU 2025

♻ ☆ Marco-Voice Technical Report

Fengping Tian, Chenyang Lyu, Xuanfan Ni, Haoqin Sun, Qingjuan Li, Zhiqiang Qian, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo, Kaifu Zhang

comment: Technical Report. Our code and dataset are publicly available at https://github.com/AIDC-AI/Marco-Voice and https://huggingface.co/datasets/AIDC-AI/CSEMOTIONS respectively

♻ ☆ Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning

Shu Wu, Chenxing Li, Wenfu Wang, Hao Zhang, Hualei Wang, Meng Yu, Dong Yu

comment: preprint

♻ ☆ Gotta Hear Them All: Towards Sound Source Aware Audio Generation

Wei Guo, Heng Wang, Jianbo Ma, Weidong Cai

comment: 17 pages, 12 figures, source code available at https://github.com/wguo86/SSV2A

♻ ☆ XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation

Tianlun Zuo, Jingbin Hu, Yuke Li, Xinfa Zhu, Hai Li, Ying Yan, Junhui Liu, Danming Xie, Lei Xie

Zero-shot emotion transfer in cross-lingual speech synthesis refers to generating speech in a target language, where the emotion is expressed based on reference speech from a different source language. However, this task remains challenging due to the scarcity of parallel multilingual emotional corpora, the presence of foreign accent artifacts, and the difficulty of separating emotion from language-specific prosodic features. In this paper, we propose XEmoRAG, a novel framework to enable zero-shot emotion transfer from Chinese to Thai using a large language model (LLM)-based model, without relying on parallel emotional data. XEmoRAG extracts language-agnostic emotional embeddings from Chinese speech and retrieves emotionally matched Thai utterances from a curated emotional database, enabling controllable emotion transfer without explicit emotion labels. Additionally, a flow-matching alignment module minimizes pitch and duration mismatches, ensuring natural prosody. It also blends Chinese timbre into the Thai synthesis, enhancing rhythmic accuracy and emotional expression, while preserving speaker characteristics and emotional consistency. Experimental results show that XEmoRAG synthesizes expressive and natural Thai speech using only Chinese reference audio, without requiring explicit emotion labels. These results highlight XEmoRAG's capability to achieve flexible and low-resource emotional transfer across languages. Our demo is available at https://tlzuo-lesley.github.io/Demo-page/ .

comment: Accepted by ASRU 2025

Computer Vision and Pattern Recognition 150

☆ HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis

Timo Teufel, Pulkit Gera, Xilong Zhou, Umar Iqbal, Pramod Rao, Jan Kautz, Vladislav Golyanik, Christian Theobalt

Simultaneous relighting and novel-view rendering of digital human representations is an important yet challenging task with numerous applications. Progress in this area has been significantly limited due to the lack of publicly available, high-quality datasets, especially for full-body human captures. To address this critical gap, we introduce the HumanOLAT dataset, the first publicly accessible large-scale dataset of multi-view One-Light-at-a-Time (OLAT) captures of full-body humans. The dataset includes HDR RGB frames under various illuminations, such as white light, environment maps, color gradients and fine-grained OLAT illuminations. Our evaluations of state-of-the-art relighting and novel-view synthesis methods underscore both the dataset's value and the significant challenges still present in modeling complex human-centric appearance and lighting interactions. We believe HumanOLAT will significantly facilitate future research, enabling rigorous benchmarking and advancements in both general and human-specific relighting and rendering techniques.

comment: TT and PG contributed equally; accepted at ICCV 2025; project page: https://vcai.mpi-inf.mpg.de/projects/HumanOLAT/

☆ Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

Ya Zou, Jingfeng Yao, Siyuan Yu, Shuai Zhang, Wenyu Liu, Xinggang Wang

There is a growing demand for deploying large generative AI models on mobile devices. For recent popular video generative models, however, the Variational AutoEncoder (VAE) represents one of the major computational bottlenecks. Both large parameter sizes and mismatched kernels cause out-of-memory errors or extremely slow inference on mobile devices. To address this, we propose a low-cost solution that efficiently transfers widely used video VAEs to mobile devices. (1) We analyze redundancy in existing VAE architectures and get empirical design insights. By integrating 3D depthwise separable convolutions into our model, we significantly reduce the number of parameters. (2) We observe that the upsampling techniques in mainstream video VAEs are poorly suited to mobile hardware and form the main bottleneck. In response, we propose a decoupled 3D pixel shuffle scheme that slashes end-to-end delay. Building upon these, we develop a universal mobile-oriented VAE decoder, Turbo-VAED. (3) We propose an efficient VAE decoder training method. Since only the decoder is used during deployment, we distill it to Turbo-VAED instead of retraining the full VAE, enabling fast mobile adaptation with minimal performance loss. To our knowledge, our method enables real-time 720p video VAE decoding on mobile devices for the first time. This approach is widely applicable to most video VAEs. When integrated into four representative models, with training cost as low as $95, it accelerates original VAEs by up to 84.5x at 720p resolution on GPUs, uses as low as 17.5% of original parameter count, and retains 96.9% of the original reconstruction quality. Compared to mobile-optimized VAEs, Turbo-VAED achieves a 2.9x speedup in FPS and better reconstruction quality on the iPhone 16 Pro. The code and models will soon be available at https://github.com/hustvl/Turbo-VAED.

☆ Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

Zixin Yin, Xili Dai, Ling-Hao Chen, Deyu Zhou, Jianan Wang, Duomin Wang, Gang Yu, Lionel M. Ni, Heung-Yeung Shum

Text-guided color editing in images and videos is a fundamental yet unsolved problem, requiring fine-grained manipulation of color attributes, including albedo, light source color, and ambient lighting, while preserving physical consistency in geometry, material properties, and light-matter interactions. Existing training-free methods offer broad applicability across editing tasks but struggle with precise color control and often introduce visual inconsistency in both edited and non-edited regions. In this work, we present ColorCtrl, a training-free color editing method that leverages the attention mechanisms of modern Multi-Modal Diffusion Transformers (MM-DiT). By disentangling structure and color through targeted manipulation of attention maps and value tokens, our method enables accurate and consistent color editing, along with word-level control of attribute intensity. Our method modifies only the intended regions specified by the prompt, leaving unrelated areas untouched. Extensive experiments on both SD3 and FLUX.1-dev demonstrate that ColorCtrl outperforms existing training-free approaches and achieves state-of-the-art performances in both edit quality and consistency. Furthermore, our method surpasses strong commercial models such as FLUX.1 Kontext Max and GPT-4o Image Generation in terms of consistency. When extended to video models like CogVideoX, our approach exhibits greater advantages, particularly in maintaining temporal coherence and editing stability. Finally, our method also generalizes to instruction-based editing diffusion models such as Step1X-Edit and FLUX.1 Kontext dev, further demonstrating its versatility.

☆ OpenCUA: Open Foundations for Computer-Use Agents

Xinyuan Wang, Bowen Wang, Dunjie Lu, Junlin Yang, Tianbao Xie, Junli Wang, Jiaqi Deng, Xiaole Guo, Yiheng Xu, Chen Henry Wu, Zhennan Shen, Zhuokai Li, Ryan Li, Xiaochuan Li, Junda Chen, Boyuan Zheng, Peihang Li, Fangyu Lei, Ruisheng Cao, Yeqiao Fu, Dongchan Shin, Martin Shin, Jiarui Hu, Yuyan Wang, Jixuan Chen, Yuxiao Ye, Danyang Zhang, Dikang Du, Hao Hu, Huarong Chen, Zaida Zhou, Yipu Wang, Heng Wang, Diyi Yang, Victor Zhong, Flood Sung, Y. Charles, Zhilin Yang, Tao Yu

☆ Deep Learning Models for Robust Facial Liveness Detection

Oleksandr Kuznetsov, Emanuele Frontoni, Luca Romeo, Riccardo Rosati, Andrea Maranesi, Alessandro Muscatello

In the rapidly evolving landscape of digital security, biometric authentication systems, particularly facial recognition, have emerged as integral components of various security protocols. However, the reliability of these systems is compromised by sophisticated spoofing attacks, where imposters gain unauthorized access by falsifying biometric traits. Current literature reveals a concerning gap: existing liveness detection methodologies - designed to counteract these breaches - fall short against advanced spoofing tactics employing deepfakes and other artificial intelligence-driven manipulations. This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques. By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision. Extensive evaluations were conducted across five diverse datasets, encompassing a wide range of attack vectors and environmental conditions. Results demonstrate substantial advancement over existing systems, with our best model (AttackNet V2.2) achieving 99.9% average accuracy when trained on combined data. Moreover, our research unveils critical insights into the behavioral patterns of impostor attacks, contributing to a more nuanced understanding of their evolving nature. The implications are profound: our models do not merely fortify the authentication processes but also instill confidence in biometric systems across various sectors reliant on secure access.

☆ Addressing Bias in VLMs for Glaucoma Detection Without Protected Attribute Supervision

Ahsan Habib Akash, Greg Murray, Annahita Amireskandari, Joel Palko, Carol Laxson, Binod Bhattarai, Prashnna Gyawali

Vision-Language Models (VLMs) have achieved remarkable success on multimodal tasks such as image-text retrieval and zero-shot classification, yet they can exhibit demographic biases even when explicit protected attributes are absent during training. In this work, we focus on automated glaucoma screening from retinal fundus images, a critical application given that glaucoma is a leading cause of irreversible blindness and disproportionately affects underserved populations. Building on a reweighting-based contrastive learning framework, we introduce an attribute-agnostic debiasing method that (i) infers proxy subgroups via unsupervised clustering of image-image embeddings, (ii) computes gradient-similarity weights between the CLIP-style multimodal loss and a SimCLR-style image-pair contrastive loss, and (iii) applies these weights in a joint, top-$k$ weighted objective to upweight underperforming clusters. This label-free approach adaptively targets the hardest examples, thereby reducing subgroup disparities. We evaluate our method on the Harvard FairVLMed glaucoma subset, reporting Equalized Odds Distance (EOD), Equalized Subgroup AUC (ES AUC), and Groupwise AUC to demonstrate equitable performance across inferred demographic subgroups.

comment: 3rd Workshop in Data Engineering in Medical Imaging (DEMI), MICCAI-2025 Workshop

☆ Efficient motion-based metrics for video frame interpolation

Conall Daly, Darren Ramsook, Anil Kokaram

Video frame interpolation (VFI) offers a way to generate intermediate frames between consecutive frames of a video sequence. Although the development of advanced frame interpolation algorithms has received increased attention in recent years, assessing the perceptual quality of interpolated content remains an ongoing area of research. In this paper, we investigate simple ways to process motion fields, with the purposes of using them as video quality metric for evaluating frame interpolation algorithms. We evaluate these quality metrics using the BVI-VFI dataset which contains perceptual scores measured for interpolated sequences. From our investigation we propose a motion metric based on measuring the divergence of motion fields. This metric correlates reasonably with these perceptual scores (PLCC=0.51) and is more computationally efficient (x2.7 speedup) compared to FloLPIPS (a well known motion-based metric). We then use our new proposed metrics to evaluate a range of state of the art frame interpolation metrics and find our metrics tend to favour more perceptual pleasing interpolated frames that may not score highly in terms of PSNR or SSIM.

comment: SPIE2025 - Applications of Digital Image Processing XLVIII accepted manuscript

☆ Scaling Learned Image Compression Models up to 1 Billion

Yuqi Li, Haotian Zhang, Li Li, Dong Liu, Feng Wu

Recent advances in large language models (LLMs) highlight a strong connection between intelligence and compression. Learned image compression, a fundamental task in modern data compression, has made significant progress in recent years. However, current models remain limited in scale, restricting their representation capacity, and how scaling model size influences compression performance remains unexplored. In this work, we present a pioneering study on scaling up learned image compression models and revealing the performance trends through scaling laws. Using the recent state-of-the-art HPCM model as baseline, we scale model parameters from 68.5 millions to 1 billion and fit power-law relations between test loss and key scaling variables, including model size and optimal training compute. The results reveal a scaling trend, enabling extrapolation to larger scale models. Experimental results demonstrate that the scaled-up HPCM-1B model achieves state-of-the-art rate-distortion performance. We hope this work inspires future exploration of large-scale compression models and deeper investigations into the connection between compression and intelligence.

comment: 11 pages, technical report

☆ A new dataset and comparison for multi-camera frame synthesis

Conall Daly, Anil Kokaram

Many methods exist for frame synthesis in image sequences but can be broadly categorised into frame interpolation and view synthesis techniques. Fundamentally, both frame interpolation and view synthesis tackle the same task, interpolating a frame given surrounding frames in time or space. However, most frame interpolation datasets focus on temporal aspects with single cameras moving through time and space, while view synthesis datasets are typically biased toward stereoscopic depth estimation use cases. This makes direct comparison between view synthesis and frame interpolation methods challenging. In this paper, we develop a novel multi-camera dataset using a custom-built dense linear camera array to enable fair comparison between these approaches. We evaluate classical and deep learning frame interpolators against a view synthesis method (3D Gaussian Splatting) for the task of view in-betweening. Our results reveal that deep learning methods do not significantly outperform classical methods on real image data, with 3D Gaussian Splatting actually underperforming frame interpolators by as much as 3.5 dB PSNR. However, in synthetic scenes, the situation reverses -- 3D Gaussian Splatting outperforms frame interpolation algorithms by almost 5 dB PSNR at a 95% confidence level.

comment: SPIE2025 - Applications of Digital Image Processing XLVIII accepted manuscript

☆ VertexRegen: Mesh Generation with Continuous Level of Detail

Xiang Zhang, Yawar Siddiqui, Armen Avetisyan, Chris Xie, Jakob Engel, Henry Howard-Jenkins

We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail.

comment: ICCV 2025. Project Page: https://vertexregen.github.io/

☆ VLM-3D:End-to-End Vision-Language Models for Open-World 3D Perception

Fuhao Chang, Shuxin Li, Yabei Li, Lei He

Open-set perception in complex traffic environments poses a critical challenge for autonomous driving systems, particularly in identifying previously unseen object categories, which is vital for ensuring safety. Visual Language Models (VLMs), with their rich world knowledge and strong semantic reasoning capabilities, offer new possibilities for addressing this task. However, existing approaches typically leverage VLMs to extract visual features and couple them with traditional object detectors, resulting in multi-stage error propagation that hinders perception accuracy. To overcome this limitation, we propose VLM-3D, the first end-to-end framework that enables VLMs to perform 3D geometric perception in autonomous driving scenarios. VLM-3D incorporates Low-Rank Adaptation (LoRA) to efficiently adapt VLMs to driving tasks with minimal computational overhead, and introduces a joint semantic-geometric loss design: token-level semantic loss is applied during early training to ensure stable convergence, while 3D IoU loss is introduced in later stages to refine the accuracy of 3D bounding box predictions. Evaluations on the nuScenes dataset demonstrate that the proposed joint semantic-geometric loss in VLM-3D leads to a 12.8% improvement in perception accuracy, fully validating the effectiveness and advancement of our method.

☆ ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive Thresholds

Shanle Yao, Ghazal Alinezhad Noghre, Armin Danesh Pazho, Hamed Tabkhi

Video Anomaly Detection (VAD) can play a key role in spotting unusual activities in video footage. VAD is difficult to use in real-world settings due to the dynamic nature of human actions, environmental variations, and domain shifts. Traditional evaluation metrics often prove inadequate for such scenarios, as they rely on static assumptions and fall short of identifying a threshold that distinguishes normal from anomalous behavior in dynamic settings. To address this, we introduce an active learning framework tailored for VAD, designed for adapting to the ever-changing real-world conditions. Our approach leverages active learning to continuously select the most informative data points for labeling, thereby enhancing model adaptability. A critical innovation is the incorporation of a human-in-the-loop mechanism, which enables the identification of actual normal and anomalous instances from pseudo-labeling results generated by AI. This collected data allows the framework to define an adaptive threshold tailored to different environments, ensuring that the system remains effective as the definition of 'normal' shifts across various settings. Implemented within a lab-based framework that simulates real-world conditions, our approach allows rigorous testing and refinement of VAD algorithms with a new metric. Experimental results show that our method achieves an EBI (Error Balance Index) of 68.91 for Q3 in real-world simulated scenarios, demonstrating its practical effectiveness and significantly enhancing the applicability of VAD in dynamic environments.

☆ Per-Query Visual Concept Learning

Ori Malca, Dvir Samuel, Gal Chechik

Visual concept learning, also known as Text-to-image personalization, is the process of teaching new concepts to a pretrained model. This has numerous applications from product placement to entertainment and personalized design. Here we show that many existing methods can be substantially augmented by adding a personalization step that is (1) specific to the prompt and noise seed, and (2) using two loss terms based on the self- and cross- attention, capturing the identity of the personalized concept. Specifically, we leverage PDM features - previously designed to capture identity - and show how they can be used to improve personalized semantic similarity. We evaluate the benefit that our method gains on top of six different personalization methods, and several base text-to-image models (both UNet- and DiT-based). We find significant improvements even over previous per-query personalization methods.

comment: Project page is at https://per-query-visual-concept-learning.github.io/

☆ Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding

Maxim A. Patratskiy, Alexey K. Kovalev, Aleksandr I. Panov

Vision-Language-Action models have demonstrated remarkable capabilities in predicting agent movements within virtual environments and real-world scenarios based on visual observations and textual instructions. Although recent research has focused on enhancing spatial and temporal understanding independently, this paper presents a novel approach that integrates both aspects through visual prompting. We introduce a method that projects visual traces of key points from observations onto depth maps, enabling models to capture both spatial and temporal information simultaneously. The experiments in SimplerEnv show that the mean number of tasks successfully solved increased for 4% compared to SpatialVLA and 19% compared to TraceVLA. Furthermore, we show that this enhancement can be achieved with minimal training data, making it particularly valuable for real-world applications where data collection is challenging. The project page is available at https://ampiromax.github.io/ST-VLA.

☆ When Deepfakes Look Real: Detecting AI-Generated Faces with Unlabeled Data due to Annotation Challenges

Zhiqiang Yang, Renshuai Tao, Xiaolong Zheng, Guodong Yang, Chunjie Zhang

Existing deepfake detection methods heavily depend on labeled training data. However, as AI-generated content becomes increasingly realistic, even \textbf{human annotators struggle to distinguish} between deepfakes and authentic images. This makes the labeling process both time-consuming and less reliable. Specifically, there is a growing demand for approaches that can effectively utilize large-scale unlabeled data from online social networks. Unlike typical unsupervised learning tasks, where categories are distinct, AI-generated faces closely mimic real image distributions and share strong similarities, causing performance drop in conventional strategies. In this paper, we introduce the Dual-Path Guidance Network (DPGNet), to tackle two key challenges: (1) bridging the domain gap between faces from different generation models, and (2) utilizing unlabeled image samples. The method features two core modules: text-guided cross-domain alignment, which uses learnable prompts to unify visual and textual embeddings into a domain-invariant feature space, and curriculum-driven pseudo label generation, which dynamically exploit more informative unlabeled samples. To prevent catastrophic forgetting, we also facilitate bridging between domains via cross-domain knowledge distillation. Extensive experiments on \textbf{11 popular datasets}, show that DPGNet outperforms SoTA approaches by \textbf{6.3\%}, highlighting its effectiveness in leveraging unlabeled data to address the annotation challenges posed by the increasing realism of deepfakes.

comment: 10pages,5figures

☆ Uncertainty-aware Cross-training for Semi-supervised Medical Image Segmentation

Kaiwen Huang, Tao Zhou, Huazhu Fu, Yizhe Zhang, Yi Zhou, Xiao-Jun Wu

Semi-supervised learning has gained considerable popularity in medical image segmentation tasks due to its capability to reduce reliance on expert-examined annotations. Several mean-teacher (MT) based semi-supervised methods utilize consistency regularization to effectively leverage valuable information from unlabeled data. However, these methods often heavily rely on the student model and overlook the potential impact of cognitive biases within the model. Furthermore, some methods employ co-training using pseudo-labels derived from different inputs, yet generating high-confidence pseudo-labels from perturbed inputs during training remains a significant challenge. In this paper, we propose an Uncertainty-aware Cross-training framework for semi-supervised medical image Segmentation (UC-Seg). Our UC-Seg framework incorporates two distinct subnets to effectively explore and leverage the correlation between them, thereby mitigating cognitive biases within the model. Specifically, we present a Cross-subnet Consistency Preservation (CCP) strategy to enhance feature representation capability and ensure feature consistency across the two subnets. This strategy enables each subnet to correct its own biases and learn shared semantics from both labeled and unlabeled data. Additionally, we propose an Uncertainty-aware Pseudo-label Generation (UPG) component that leverages segmentation results and corresponding uncertainty maps from both subnets to generate high-confidence pseudo-labels. We extensively evaluate the proposed UC-Seg on various medical image segmentation tasks involving different modality images, such as MRI, CT, ultrasound, colonoscopy, and so on. The results demonstrate that our method achieves superior segmentation accuracy and generalization performance compared to other state-of-the-art semi-supervised methods. Our code will be released at https://github.com/taozh2017/UCSeg.

comment: 14 pages, 10 figures

☆ Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement

Luyang Cao, Han Xu, Jian Zhang, Lei Qi, Jiayi Ma, Yinghuan Shi, Yang Gao

In low-light image enhancement, Retinex-based deep learning methods have garnered significant attention due to their exceptional interpretability. These methods decompose images into mutually independent illumination and reflectance components, allows each component to be enhanced separately. In fact, achieving perfect decomposition of illumination and reflectance components proves to be quite challenging, with some residuals still existing after decomposition. In this paper, we formally name these residuals as inter-component residuals (ICR), which has been largely underestimated by previous methods. In our investigation, ICR not only affects the accuracy of the decomposition but also causes enhanced components to deviate from the ideal outcome, ultimately reducing the final synthesized image quality. To address this issue, we propose a novel Inter-correction Retinex model (IRetinex) to alleviate ICR during the decomposition and enhancement stage. In the decomposition stage, we leverage inter-component residual reduction module to reduce the feature similarity between illumination and reflectance components. In the enhancement stage, we utilize the feature similarity between the two components to detect and mitigate the impact of ICR within each enhancement unit. Extensive experiments on three low-light benchmark datasets demonstrated that by reducing ICR, our method outperforms state-of-the-art approaches both qualitatively and quantitatively.

comment: This article has been accepted by ACMMM 2025

☆ UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale

Yuhao Wang, Wei Xi

Convolutional neural networks (ConvNets) with large effective receptive field (ERF), still in their early stages, have demonstrated promising effectiveness while constrained by high parameters and FLOPs costs and disrupted asymptotically Gaussian distribution (AGD) of ERF. This paper proposes an alternative paradigm: rather than merely employing extremely large ERF, it is more effective and efficient to expand the ERF while maintaining AGD of ERF by proper combination of smaller kernels, such as $7\times{7}$, $9\times{9}$, $11\times{11}$. This paper introduces a Three-layer Receptive Field Aggregator and designs a Layer Operator as the fundamental operator from the perspective of receptive field. The ERF can be expanded to the level of existing large-kernel ConvNets through the stack of proposed modules while maintaining AGD of ERF. Using these designs, we propose a universal model for ConvNet of any scale, termed UniConvNet. Extensive experiments on ImageNet-1K, COCO2017, and ADE20K demonstrate that UniConvNet outperforms state-of-the-art CNNs and ViTs across various vision recognition tasks for both lightweight and large-scale models with comparable throughput. Surprisingly, UniConvNet-T achieves $84.2\%$ ImageNet top-1 accuracy with $30M$ parameters and $5.1G$ FLOPs. UniConvNet-XL also shows competitive scalability to big data and large models, acquiring $88.4\%$ top-1 accuracy on ImageNet. Code and models are publicly available at https://github.com/ai-paperwithcode/UniConvNet.

comment: ICCV 2025

☆ Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation

Zan Wang, Jingze Zhang, Yixin Chen, Baoxiong Jia, Wei Liang, Siyuan Huang

Despite significant advancements in human motion generation, current motion representations, typically formulated as discrete frame sequences, still face two critical limitations: (i) they fail to capture motion from a multi-scale perspective, limiting the capability in complex patterns modeling; (ii) they lack compositional flexibility, which is crucial for model's generalization in diverse generation tasks. To address these challenges, we introduce MSQ, a novel quantization method that compresses the motion sequence into multi-scale discrete tokens across spatial and temporal dimensions. MSQ employs distinct encoders to capture body parts at varying spatial granularities and temporally interpolates the encoded features into multiple scales before quantizing them into discrete tokens. Building on this representation, we establish a generative mask modeling model to effectively support motion editing, motion control, and conditional motion generation. Through quantitative and qualitative analysis, we show that our quantization method enables the seamless composition of motion tokens without requiring specialized design or re-training. Furthermore, extensive evaluations demonstrate that our approach outperforms existing baseline methods on various benchmarks.

comment: 18 pages

☆ KFFocus: Highlighting Keyframes for Enhanced Video Understanding

Ming Nie, Chunwei Wang, Hang Xu, Li Zhang

Recently, with the emergence of large language models, multimodal LLMs have demonstrated exceptional capabilities in image and video modalities. Despite advancements in video comprehension, the substantial computational demands of long video sequences lead current video LLMs (Vid-LLMs) to employ compression strategies at both the inter-frame level (e.g., uniform sampling of video frames) and intra-frame level (e.g., condensing all visual tokens of each frame into a limited number). However, this approach often neglects the uneven temporal distribution of critical information across frames, risking the omission of keyframes that contain essential temporal and semantic details. To tackle these challenges, we propose KFFocus, a method designed to efficiently compress video tokens and emphasize the informative context present within video frames. We substitute uniform sampling with a refined approach inspired by classic video compression principles to identify and capture keyframes based on their temporal redundancy. By assigning varying condensation ratios to frames based on their contextual relevance, KFFocus efficiently reduces token redundancy while preserving informative content details. Additionally, we introduce a spatiotemporal modeling module that encodes both the temporal relationships between video frames and the spatial structure within each frame, thus providing Vid-LLMs with a nuanced understanding of spatial-temporal dynamics. Extensive experiments on widely recognized video understanding benchmarks, especially long video scenarios, demonstrate that KFFocus significantly outperforms existing methods, achieving substantial computational efficiency and enhanced accuracy.

☆ ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation

Ding Xia, Naoto Inoue, Qianru Qiu, Kotaro Kikuchi

Colors play a crucial role in the design of vector graphic documents by enhancing visual appeal, facilitating communication, improving usability, and ensuring accessibility. In this context, color recommendation involves suggesting appropriate colors to complete or refine a design when one or more colors are missing or require alteration. Traditional methods often struggled with these challenges due to the complex nature of color design and the limited data availability. In this study, we explored the use of pretrained Large Language Models (LLMs) and their commonsense reasoning capabilities for color recommendation, raising the question: Can pretrained LLMs serve as superior designers for color recommendation tasks? To investigate this, we developed a robust, rigorously validated pipeline, ColorGPT, that was built by systematically testing multiple color representations and applying effective prompt engineering techniques. Our approach primarily targeted color palette completion by recommending colors based on a set of given colors and accompanying context. Moreover, our method can be extended to full palette generation, producing an entire color palette corresponding to a provided textual description. Experimental results demonstrated that our LLM-based pipeline outperformed existing methods in terms of color suggestion accuracy and the distribution of colors in the color palette completion task. For the full palette generation task, our approach also yielded improvements in color diversity and similarity compared to current techniques.

comment: Accepted to ICDAR2025

☆ TaoCache: Structure-Maintained Video Generation Acceleration

Zhentao Fan, Zongzuo Wang, Weiwei Zhang

Existing cache-based acceleration methods for video diffusion models primarily skip early or mid denoising steps, which often leads to structural discrepancies relative to full-timestep generation and can hinder instruction following and character consistency. We present TaoCache, a training-free, plug-and-play caching strategy that, instead of residual-based caching, adopts a fixed-point perspective to predict the model's noise output and is specifically effective in late denoising stages. By calibrating cosine similarities and norm ratios of consecutive noise deltas, TaoCache preserves high-resolution structure while enabling aggressive skipping. The approach is orthogonal to complementary accelerations such as Pyramid Attention Broadcast (PAB) and TeaCache, and it integrates seamlessly into DiT-based frameworks. Across Latte-1, OpenSora-Plan v110, and Wan2.1, TaoCache attains substantially higher visual quality (LPIPS, SSIM, PSNR) than prior caching methods under the same speedups.

☆ Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering

Elman Ghazaei, Erchan Aptoula

The Earth's surface is constantly changing, and detecting these changes provides valuable insights that benefit various aspects of human society. While traditional change detection methods have been employed to detect changes from bi-temporal images, these approaches typically require expert knowledge for accurate interpretation. To enable broader and more flexible access to change information by non-expert users, the task of Change Detection Visual Question Answering (CDVQA) has been introduced. However, existing CDVQA methods have been developed under the assumption that training and testing datasets share similar distributions. This assumption does not hold in real-world applications, where domain shifts often occur. In this paper, the CDVQA task is revisited with a focus on addressing domain shift. To this end, a new multi-modal and multi-domain dataset, BrightVQA, is introduced to facilitate domain generalization research in CDVQA. Furthermore, a novel state space model, termed Text-Conditioned State Space Model (TCSSM), is proposed. The TCSSM framework is designed to leverage both bi-temporal imagery and geo-disaster-related textual information in an unified manner to extract domain-invariant features across domains. Input-dependent parameters existing in TCSSM are dynamically predicted by using both bi-temporal images and geo-disaster-related description, thereby facilitating the alignment between bi-temporal visual data and the associated textual descriptions. Extensive experiments are conducted to evaluate the proposed method against state-of-the-art models, and superior performance is consistently demonstrated. The code and dataset will be made publicly available upon acceptance at https://github.com/Elman295/TCSSM.

☆ Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation

Ao Ma, Jiasong Feng, Ke Cao, Jing Wang, Yun Wang, Quanwei Zhang, Zhanjie Zhang

Storytelling tasks involving generating consistent subjects have gained significant attention recently. However, existing methods, whether training-free or training-based, continue to face challenges in maintaining subject consistency due to the lack of fine-grained guidance and inter-frame interaction. Additionally, the scarcity of high-quality data in this field makes it difficult to precisely control storytelling tasks, including the subject's position, appearance, clothing, expression, and posture, thereby hindering further advancements. In this paper, we demonstrate that layout conditions, such as the subject's position and detailed attributes, effectively facilitate fine-grained interactions between frames. This not only strengthens the consistency of the generated frame sequence but also allows for precise control over the subject's position, appearance, and other key details. Building on this, we introduce an advanced storytelling task: Layout-Togglable Storytelling, which enables precise subject control by incorporating layout conditions. To address the lack of high-quality datasets with layout annotations for this task, we develop Lay2Story-1M, which contains over 1 million 720p and higher-resolution images, processed from approximately 11,300 hours of cartoon videos. Building on Lay2Story-1M, we create Lay2Story-Bench, a benchmark with 3,000 prompts designed to evaluate the performance of different methods on this task. Furthermore, we propose Lay2Story, a robust framework based on the Diffusion Transformers (DiTs) architecture for Layout-Togglable Storytelling tasks. Through both qualitative and quantitative experiments, we find that our method outperforms the previous state-of-the-art (SOTA) techniques, achieving the best results in terms of consistency, semantic correlation, and aesthetic quality.

comment: Accepted by ICCV 2025

☆ UniSTFormer: Unified Spatio-Temporal Lightweight Transformer for Efficient Skeleton-Based Action Recognition

Wenhan Wu, Zhishuai Guo, Chen Chen, Aidong Lu

Skeleton-based action recognition (SAR) has achieved impressive progress with transformer architectures. However, existing methods often rely on complex module compositions and heavy designs, leading to increased parameter counts, high computational costs, and limited scalability. In this paper, we propose a unified spatio-temporal lightweight transformer framework that integrates spatial and temporal modeling within a single attention module, eliminating the need for separate temporal modeling blocks. This approach reduces redundant computations while preserving temporal awareness within the spatial modeling process. Furthermore, we introduce a simplified multi-scale pooling fusion module that combines local and global pooling pathways to enhance the model's ability to capture fine-grained local movements and overarching global motion patterns. Extensive experiments on benchmark datasets demonstrate that our lightweight model achieves a superior balance between accuracy and efficiency, reducing parameter complexity by over 58% and lowering computational cost by over 60% compared to state-of-the-art transformer-based baselines, while maintaining competitive recognition performance.

☆ MADPromptS: Unlocking Zero-Shot Morphing Attack Detection with Multiple Prompt Aggregation

Eduarda Caldeira, Fadi Boutros, Naser Damer

Face Morphing Attack Detection (MAD) is a critical challenge in face recognition security, where attackers can fool systems by interpolating the identity information of two or more individuals into a single face image, resulting in samples that can be verified as belonging to multiple identities by face recognition systems. While multimodal foundation models (FMs) like CLIP offer strong zero-shot capabilities by jointly modeling images and text, most prior works on FMs for biometric recognition have relied on fine-tuning for specific downstream tasks, neglecting their potential for direct, generalizable deployment. This work explores a pure zero-shot approach to MAD by leveraging CLIP without any additional training or fine-tuning, focusing instead on the design and aggregation of multiple textual prompts per class. By aggregating the embeddings of diverse prompts, we better align the model's internal representations with the MAD task, capturing richer and more varied cues indicative of bona-fide or attack samples. Our results show that prompt aggregation substantially improves zero-shot detection performance, demonstrating the effectiveness of exploiting foundation models' built-in multimodal knowledge through efficient prompt engineering.

comment: Accepted at ACM Multimedia Workshops

☆ Accelerated Volumetric Compression without Hierarchies: A Fourier Feature Based Implicit Neural Representation Approach

Leona Žůrková, Petr Strakoš, Michal Kravčenko, Tomáš Brzobohatý, Lubomír Říha

Volumetric data compression is critical in fields like medical imaging, scientific simulation, and entertainment. We introduce a structure-free neural compression method combining Fourierfeature encoding with selective voxel sampling, yielding compact volumetric representations and faster convergence. Our dynamic voxel selection uses morphological dilation to prioritize active regions, reducing redundant computation without any hierarchical metadata. In the experiment, sparse training reduced training time by 63.7 % (from 30 to 11 minutes) with only minor quality loss: PSNR dropped 0.59 dB (from 32.60 to 32.01) and SSIM by 0.008 (from 0.948 to 0.940). The resulting neural representation, stored solely as network weights, achieves a compression rate of 14 and eliminates traditional data-loading overhead. This connects coordinate-based neural representation with efficient volumetric compression, offering a scalable, structure-free solution for practical applications.

comment: 2 pages, accepted for the VIS IEEE 2025 poster

☆ Shape Completion and Real-Time Visualization in Robotic Ultrasound Spine Acquisitions

Miruna-Alexandra Gafencu, Reem Shaban, Yordanka Velikova, Mohammad Farid Azampour, Nassir Navab

Ultrasound (US) imaging is increasingly used in spinal procedures due to its real-time, radiation-free capabilities; however, its effectiveness is hindered by shadowing artifacts that obscure deeper tissue structures. Traditional approaches, such as CT-to-US registration, incorporate anatomical information from preoperative CT scans to guide interventions, but they are limited by complex registration requirements, differences in spine curvature, and the need for recent CT imaging. Recent shape completion methods can offer an alternative by reconstructing spinal structures in US data, while being pretrained on large set of publicly available CT scans. However, these approaches are typically offline and have limited reproducibility. In this work, we introduce a novel integrated system that combines robotic ultrasound with real-time shape completion to enhance spinal visualization. Our robotic platform autonomously acquires US sweeps of the lumbar spine, extracts vertebral surfaces from ultrasound, and reconstructs the complete anatomy using a deep learning-based shape completion network. This framework provides interactive, real-time visualization with the capability to autonomously repeat scans and can enable navigation to target locations. This can contribute to better consistency, reproducibility, and understanding of the underlying anatomy. We validate our approach through quantitative experiments assessing shape completion accuracy and evaluations of multiple spine acquisition protocols on a phantom setup. Additionally, we present qualitative results of the visualization on a volunteer scan.

☆ A Pseudo Global Fusion Paradigm-Based Cross-View Network for LiDAR-Based Place Recognition

Jintao Cheng, Jiehao Luo, Xieyuanli Chen, Jin Wu, Rui Fan, Xiaoyu Tang, Wei Zhang

LiDAR-based Place Recognition (LPR) remains a critical task in Embodied Artificial Intelligence (AI) and Autonomous Driving, primarily addressing localization challenges in GPS-denied environments and supporting loop closure detection. Existing approaches reduce place recognition to a Euclidean distance-based metric learning task, neglecting the feature space's intrinsic structures and intra-class variances. Such Euclidean-centric formulation inherently limits the model's capacity to capture nonlinear data distributions, leading to suboptimal performance in complex environments and temporal-varying scenarios. To address these challenges, we propose a novel cross-view network based on an innovative fusion paradigm. Our framework introduces a pseudo-global information guidance mechanism that coordinates multi-modal branches to perform feature learning within a unified semantic space. Concurrently, we propose a Manifold Adaptation and Pairwise Variance-Locality Learning Metric that constructs a Symmetric Positive Definite (SPD) matrix to compute Mahalanobis distance, superseding traditional Euclidean distance metrics. This geometric formulation enables the model to accurately characterize intrinsic data distributions and capture complex inter-class dependencies within the feature space. Experimental results demonstrate that the proposed algorithm achieves competitive performance, particularly excelling in complex environmental conditions.

☆ Automatic and standardized surgical reporting for central nervous system tumors

David Bouget, Mathilde Gajda Faanes, Asgeir Store Jakola, Frederik Barkhof, Hilko Ardon, Lorenzo Bello, Mitchel S. Berger, Shawn L. Hervey-Jumper, Julia Furtner, Albert J. S. Idema, Barbara Kiesel, Georg Widhalm, Rishi Nandoe Tewarie, Emmanuel Mandonnet, Pierre A. Robe, Michiel Wagemakers, Timothy R. Smith, Philip C. De Witt Hamer, Ole solheim, Ingerid Reinertsen

Magnetic resonance (MR) imaging is essential for evaluating central nervous system (CNS) tumors, guiding surgical planning, treatment decisions, and assessing postoperative outcomes and complication risks. While recent work has advanced automated tumor segmentation and report generation, most efforts have focused on preoperative data, with limited attention to postoperative imaging analysis. This study introduces a comprehensive pipeline for standardized postsurtical reporting in CNS tumors. Using the Attention U-Net architecture, segmentation models were trained for the preoperative (non-enhancing) tumor core, postoperative contrast-enhancing residual tumor, and resection cavity. Additionally, MR sequence classification and tumor type identification for contrast-enhancing lesions were explored using the DenseNet architecture. The models were integrated into a reporting pipeline, following the RANO 2.0 guidelines. Training was conducted on multicentric datasets comprising 2000 to 7000 patients, using a 5-fold cross-validation. Evaluation included patient-, voxel-, and object-wise metrics, with benchmarking against the latest BraTS challenge results. The segmentation models achieved average voxel-wise Dice scores of 87%, 66%, 70%, and 77% for the tumor core, non-enhancing tumor core, contrast-enhancing residual tumor, and resection cavity, respectively. Classification models reached 99.5% balanced accuracy in MR sequence classification and 80% in tumor type classification. The pipeline presented in this study enables robust, automated segmentation, MR sequence classification, and standardized report generation aligned with RANO 2.0 guidelines, enhancing postoperative evaluation and clinical decision-making. The proposed models and methods were integrated into Raidionics, open-source software platform for CNS tumor analysis, now including a dedicated module for postsurgical analysis.

comment: 16 pages, 6 figures, 9 tables

☆ Masked Clustering Prediction for Unsupervised Point Cloud Pre-training

Bin Ren, Xiaoshui Huang, Mengyuan Liu, Hong Liu, Fabio Poiesi, Nicu Sebe, Guofeng Mei

Vision transformers (ViTs) have recently been widely applied to 3D point cloud understanding, with masked autoencoding as the predominant pre-training paradigm. However, the challenge of learning dense and informative semantic features from point clouds via standard ViTs remains underexplored. We propose MaskClu, a novel unsupervised pre-training method for ViTs on 3D point clouds that integrates masked point modeling with clustering-based learning. MaskClu is designed to reconstruct both cluster assignments and cluster centers from masked point clouds, thus encouraging the model to capture dense semantic information. Additionally, we introduce a global contrastive learning mechanism that enhances instance-level feature learning by contrasting different masked views of the same point cloud. By jointly optimizing these complementary objectives, i.e., dense semantic reconstruction, and instance-level contrastive learning. MaskClu enables ViTs to learn richer and more semantically meaningful representations from 3D point clouds. We validate the effectiveness of our method via multiple 3D tasks, including part segmentation, semantic segmentation, object detection, and classification, where MaskClu sets new competitive results. The code and models will be released at:https://github.com/Amazingren/maskclu.

comment: 3D point cloud pretraining method. 8 pages in the main manuscript

☆ A Robust Epipolar-Domain Regularization Algorithm for Light Field Depth Estimation

Noor Islam S. Mohammad

Robust depth estimation in light field imaging remains a critical challenge for pattern recognition applications such as augmented reality, biomedical imaging, and scene reconstruction. While existing approaches often rely heavily on deep convolutional neural networks, they tend to incur high computational costs and struggle in noisy real-world environments. This paper proposes a novel lightweight depth estimation pipeline that integrates light field-based disparity information with a directed random walk refinement algorithm. Unlike traditional CNN-based methods, our approach enhances depth map consistency without requiring extensive training or large-scale datasets. The proposed method was evaluated on the 4D Light Field Benchmark dataset and a diverse set of real-world images. Experimental results indicate that while performance slightly declines under uncontrolled conditions, the algorithm consistently maintains low computational complexity and competitive accuracy compared to state-of-the-art deep learning models. These findings highlight the potential of our method as a robust and efficient alternative for depth estimation and segmentation in light field imaging. The work provides insights into practical algorithm design for light field-based pattern recognition and opens new directions for integrating probabilistic graph models with depth sensing frameworks.

☆ Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos

Chaoyi Wang, Yifan Yang, Jun Pei, Lijie Xia, Jianpo Liu, Xiaobing Yuan, Xinhan Di

Creating realistic, fully animatable whole-body avatars from a single portrait is challenging due to limitations in capturing subtle expressions, body movements, and dynamic backgrounds. Current evaluation datasets and metrics fall short in addressing these complexities. To bridge this gap, we introduce the Whole-Body Benchmark Dataset (WB-DH), an open-source, multi-modal benchmark designed for evaluating whole-body animatable avatar generation. Key features include: (1) detailed multi-modal annotations for fine-grained guidance, (2) a versatile evaluation framework, and (3) public access to the dataset and tools at https://github.com/deepreasonings/WholeBodyBenchmark.

comment: This paper has been accepted by ICCV 2025 Workshop MMFM4

☆ GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments

Lin Zeng, Boming Zhao, Jiarui Hu, Xujie Shen, Ziqiang Dang, Hujun Bao, Zhaopeng Cui

Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-intensive, requiring extensive model retraining, or fail to capture detailed types of changes over time. In this paper, we present GaussianUpdate, a novel approach that combines 3D Gaussian representation with continual learning to address these challenges. Our method effectively updates the Gaussian radiance fields with current data while preserving information from past scenes. Unlike existing methods, GaussianUpdate explicitly models different types of changes through a novel multi-stage update strategy. Additionally, we introduce a visibility-aware continual learning approach with generative replay, enabling self-aware updating without the need to store images. The experiments on the benchmark dataset demonstrate our method achieves superior and real-time rendering with the capability of visualizing changes over different times

comment: Accepted to ICCV 2025

☆ Frequency-Assisted Adaptive Sharpening Scheme Considering Bitrate and Quality Tradeoff

Yingxue Pang, Shijie Zhao, Haiqiang Wang, Gen Zhan, Junlin Li, Li Zhang

Sharpening is a widely adopted technique to improve video quality, which can effectively emphasize textures and alleviate blurring. However, increasing the sharpening level comes with a higher video bitrate, resulting in degraded Quality of Service (QoS). Furthermore, the video quality does not necessarily improve with increasing sharpening levels, leading to issues such as over-sharpening. Clearly, it is essential to figure out how to boost video quality with a proper sharpening level while also controlling bandwidth costs effectively. This paper thus proposes a novel Frequency-assisted Sharpening level Prediction model (FreqSP). We first label each video with the sharpening level correlating to the optimal bitrate and quality tradeoff as ground truth. Then taking uncompressed source videos as inputs, the proposed FreqSP leverages intricate CNN features and high-frequency components to estimate the optimal sharpening level. Extensive experiments demonstrate the effectiveness of our method.

☆ Adaptive High-Frequency Preprocessing for Video Coding

Yingxue Pang, Shijie Zhao, Junlin Li, Li Zhang

High-frequency components are crucial for maintaining video clarity and realism, but they also significantly impact coding bitrate, resulting in increased bandwidth and storage costs. This paper presents an end-to-end learning-based framework for adaptive high-frequency preprocessing to enhance subjective quality and save bitrate in video coding. The framework employs the Frequency-attentive Feature pyramid Prediction Network (FFPN) to predict the optimal high-frequency preprocessing strategy, guiding subsequent filtering operators to achieve the optimal tradeoff between bitrate and quality after compression. For training FFPN, we pseudo-label each training video with the optimal strategy, determined by comparing the rate-distortion (RD) performance across different preprocessing types and strengths. Distortion is measured using the latest quality assessment metric. Comprehensive evaluations on multiple datasets demonstrate the visually appealing enhancement capabilities and bitrate savings achieved by our framework.

☆ DiffPhysCam: Differentiable Physics-Based Camera Simulation for Inverse Rendering and Embodied AI

Bo-Hsun Chen, Nevindu M. Batagoda, Dan Negrut

We introduce DiffPhysCam, a differentiable camera simulator designed to support robotics and embodied AI applications by enabling gradient-based optimization in visual perception pipelines. Generating synthetic images that closely mimic those from real cameras is essential for training visual models and enabling end-to-end visuomotor learning. Moreover, differentiable rendering allows inverse reconstruction of real-world scenes as digital twins, facilitating simulation-based robotics training. However, existing virtual cameras offer limited control over intrinsic settings, poorly capture optical artifacts, and lack tunable calibration parameters -- hindering sim-to-real transfer. DiffPhysCam addresses these limitations through a multi-stage pipeline that provides fine-grained control over camera settings, models key optical effects such as defocus blur, and supports calibration with real-world data. It enables both forward rendering for image synthesis and inverse rendering for 3D scene reconstruction, including mesh and material texture optimization. We show that DiffPhysCam enhances robotic perception performance in synthetic image tasks. As an illustrative example, we create a digital twin of a real-world scene using inverse rendering, simulate it in a multi-physics environment, and demonstrate navigation of an autonomous ground vehicle using images generated by DiffPhysCam.

comment: 19 pages, 17 figures, and 4 tables

☆ Silicon Minds versus Human Hearts: The Wisdom of Crowds Beats the Wisdom of AI in Emotion Recognition

Mustafa Akben, Vinayaka Gude, Haya Ajjan

The ability to discern subtle emotional cues is fundamental to human social intelligence. As artificial intelligence (AI) becomes increasingly common, AI's ability to recognize and respond to human emotions is crucial for effective human-AI interactions. In particular, whether such systems can match or surpass human experts remains to be seen. However, the emotional intelligence of AI, particularly multimodal large language models (MLLMs), remains largely unexplored. This study evaluates the emotion recognition abilities of MLLMs using the Reading the Mind in the Eyes Test (RMET) and its multiracial counterpart (MRMET), and compares their performance against human participants. Results show that, on average, MLLMs outperform humans in accurately identifying emotions across both tests. This trend persists even when comparing performance across low, medium, and expert-level performing groups. Yet when we aggregate independent human decisions to simulate collective intelligence, human groups significantly surpass the performance of aggregated MLLM predictions, highlighting the wisdom of the crowd. Moreover, a collaborative approach (augmented intelligence) that combines human and MLLM predictions achieves greater accuracy than either humans or MLLMs alone. These results suggest that while MLLMs exhibit strong emotion recognition at the individual level, the collective intelligence of humans and the synergistic potential of human-AI collaboration offer the most promising path toward effective emotional AI. We discuss the implications of these findings for the development of emotionally intelligent AI systems and future research directions.

☆ A Parametric Bi-Directional Curvature-Based Framework for Image Artifact Classification and Quantification

Diego Frias

This work presents a novel framework for No-Reference Image Quality Assessment (NR-IQA) founded on the analysis of directional image curvature. Within this framework, we define a measure of Anisotropic Texture Richness (ATR), which is computed at the pixel level using two tunable thresholds -- one permissive and one restrictive -- that quantify orthogonal texture suppression. When its parameters are optimized for a specific artifact, the resulting ATR score serves as a high-performance quality metric, achieving Spearman correlations with human perception of approximately -0.93 for Gaussian blur and -0.95 for white noise on the LIVE dataset. The primary contribution is a two-stage system that leverages the differential response of ATR to various distortions. First, the system utilizes the signature from two specialist ATR configurations to classify the primary artifact type (blur vs. noise) with over 97% accuracy. Second, following classification, it employs a dedicated regression model mapping the relevant ATR score to a quality rating to quantify the degradation. On a combined dataset, the complete system predicts human scores with a coefficient of determination (R2) of 0.892 and a Root Mean Square Error (RMSE) of 5.17 DMOS points. This error corresponds to just 7.4% of the dataset's total quality range, demonstrating high predictive accuracy. This establishes our framework as a robust, dual-purpose tool for the classification and subsequent quantification of image degradation.

☆ 3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs

Noor Ahmed, Cameron Braunstein, Steffen Eger, Eddy Ilg

Recent Multi-Modal Large Language Models (MLLMs) have demonstrated strong capabilities in learning joint representations from text and images. However, their spatial reasoning remains limited. We introduce 3DFroMLLM, a novel framework that enables the generation of 3D object prototypes directly from MLLMs, including geometry and part labels. Our pipeline is agentic, comprising a designer, coder, and visual inspector operating in a refinement loop. Notably, our approach requires no additional training data or detailed user instructions. Building on prior work in 2D generation, we demonstrate that rendered images produced by our framework can be effectively used for image classification pretraining tasks and outperforms previous methods by 15%. As a compelling real-world use case, we show that the generated prototypes can be leveraged to improve fine-grained vision-language models by using the rendered, part-labeled prototypes to fine-tune CLIP for part segmentation and achieving a 55% accuracy improvement without relying on any additional human-labeled data.

☆ TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models

Yuqi Peng, Lingtao Zheng, Yufeng Yang, Yi Huang, Mingfu Yan, Jianzhuang Liu, Shifeng Chen

Personalized text-to-image generation aims to synthesize novel images of a specific subject or style using only a few reference images. Recent methods based on Low-Rank Adaptation (LoRA) enable efficient single-concept customization by injecting lightweight, concept-specific adapters into pre-trained diffusion models. However, combining multiple LoRA modules for multi-concept generation often leads to identity missing and visual feature leakage. In this work, we identify two key issues behind these failures: (1) token-wise interference among different LoRA modules, and (2) spatial misalignment between the attention map of a rare token and its corresponding concept-specific region. To address these issues, we propose Token-Aware LoRA (TARA), which introduces a token mask to explicitly constrain each module to focus on its associated rare token to avoid interference, and a training objective that encourages the spatial attention of a rare token to align with its concept region. Our method enables training-free multi-concept composition by directly injecting multiple independently trained TARA modules at inference time. Experimental results demonstrate that TARA enables efficient multi-concept inference and effectively preserving the visual identity of each concept by avoiding mutual interference between LoRA modules. The code and models are available at https://github.com/YuqiPeng77/TARA.

☆ Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

Shi-Chen Zhang, Yunheng Li, Yu-Huan Wu, Qibin Hou, Ming-Ming Cheng

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference through lightweight designs, we reveal their inherent limitation: misalignment between class representations and image features caused by a per-pixel classification paradigm. With experimental analysis, we find that this paradigm results in a highly challenging assumption for efficient scenarios: Image pixel features should not vary for the same category in different images. To address this dilemma, we propose a coupled dual-branch offset learning paradigm that explicitly learns feature and class offsets to dynamically refine both class representations and spatial image features. Based on the proposed paradigm, we construct an efficient semantic segmentation network, OffSeg. Notably, the offset learning paradigm can be adopted to existing methods with no additional architectural changes. Extensive experiments on four datasets, including ADE20K, Cityscapes, COCO-Stuff-164K, and Pascal Context, demonstrate consistent improvements with negligible parameters. For instance, on the ADE20K dataset, our proposed offset learning paradigm improves SegFormer-B0, SegNeXt-T, and Mask2Former-Tiny by 2.7%, 1.9%, and 2.6% mIoU, respectively, with only 0.1-0.2M additional parameters required.

comment: Accepted at ICCV 2025. Project page: https://github.com/HVision-NKU/OffSeg

☆ Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space

Luis S. Luevano, Pavel Korshunov, Sebastien Marcel

Face aging or de-aging with generative AI has gained significant attention for its applications in such fields like forensics, security, and media. However, most state of the art methods rely on conditional Generative Adversarial Networks (GANs), Diffusion-based models, or Visual Language Models (VLMs) to age or de-age faces based on predefined age categories and conditioning via loss functions, fine-tuning, or text prompts. The reliance on such conditioning leads to complex training requirements, increased data needs, and challenges in generating consistent results. Additionally, identity preservation is rarely taken into accountor evaluated on a single face recognition system without any control or guarantees on whether identity would be preserved in a generated aged/de-aged face. In this paper, we propose to synthesize aged and de-aged faces via editing latent space of StyleGAN2 using a simple support vector modeling of aging/de-aging direction and several feature selection approaches. By using two state-of-the-art face recognition systems, we empirically find the identity preserving subspace within the StyleGAN2 latent space, so that an apparent age of a given face can changed while preserving the identity. We then propose a simple yet practical formula for estimating the limits on aging/de-aging parameters that ensures identity preservation for a given input face. Using our method and estimated parameters we have generated a public dataset of synthetic faces at different ages that can be used for benchmarking cross-age face recognition, age assurance systems, or systems for detection of synthetic images. Our code and dataset are available at the project page https://www.idiap.ch/paper/agesynth/

comment: Accepted for publication in IEEE International Joint Conference on Biometrics (IJCB), 2025

☆ MonoPartNeRF:Human Reconstruction from Monocular Video via Part-Based Neural Radiance Fields

Yao Lu, Jiawei Li, Ming Jiang

In recent years, Neural Radiance Fields (NeRF) have achieved remarkable progress in dynamic human reconstruction and rendering. Part-based rendering paradigms, guided by human segmentation, allow for flexible parameter allocation based on structural complexity, thereby enhancing representational efficiency. However, existing methods still struggle with complex pose variations, often producing unnatural transitions at part boundaries and failing to reconstruct occluded regions accurately in monocular settings. We propose MonoPartNeRF, a novel framework for monocular dynamic human rendering that ensures smooth transitions and robust occlusion recovery. First, we build a bidirectional deformation model that combines rigid and non-rigid transformations to establish a continuous, reversible mapping between observation and canonical spaces. Sampling points are projected into a parameterized surface-time space (u, v, t) to better capture non-rigid motion. A consistency loss further suppresses deformation-induced artifacts and discontinuities. We introduce a part-based pose embedding mechanism that decomposes global pose vectors into local joint embeddings based on body regions. This is combined with keyframe pose retrieval and interpolation, along three orthogonal directions, to guide pose-aware feature sampling. A learnable appearance code is integrated via attention to model dynamic texture changes effectively. Experiments on the ZJU-MoCap and MonoCap datasets demonstrate that our method significantly outperforms prior approaches under complex pose and occlusion conditions, achieving superior joint alignment, texture fidelity, and structural continuity.

☆ Region-Adaptive Video Sharpening via Rate-Perception Optimization

Yingxue Pang, Shijie Zhao, Mengxi Guo, Junlin Li, Li Zhang

Sharpening is a widely adopted video enhancement technique. However, uniform sharpening intensity ignores texture variations, degrading video quality. Sharpening also increases bitrate, and there's a lack of techniques to optimally allocate these additional bits across diverse regions. Thus, this paper proposes RPO-AdaSharp, an end-to-end region-adaptive video sharpening model for both perceptual enhancement and bitrate savings. We use the coding tree unit (CTU) partition mask as prior information to guide and constrain the allocation of increased bits. Experiments on benchmarks demonstrate the effectiveness of the proposed model qualitatively and quantitatively.

☆ DiffPose-Animal: A Language-Conditioned Diffusion Framework for Animal Pose Estimation

Tianyu Xiong, Dayi Tan, Wei Tian

Animal pose estimation is a fundamental task in computer vision, with growing importance in ecological monitoring, behavioral analysis, and intelligent livestock management. Compared to human pose estimation, animal pose estimation is more challenging due to high interspecies morphological diversity, complex body structures, and limited annotated data. In this work, we introduce DiffPose-Animal, a novel diffusion-based framework for top-down animal pose estimation. Unlike traditional heatmap regression methods, DiffPose-Animal reformulates pose estimation as a denoising process under the generative framework of diffusion models. To enhance semantic guidance during keypoint generation, we leverage large language models (LLMs) to extract both global anatomical priors and local keypoint-wise semantics based on species-specific prompts. These textual priors are encoded and fused with image features via cross-attention modules to provide biologically meaningful constraints throughout the denoising process. Additionally, a diffusion-based keypoint decoder is designed to progressively refine pose predictions, improving robustness to occlusion and annotation sparsity. Extensive experiments on public animal pose datasets demonstrate the effectiveness and generalization capability of our method, especially under challenging scenarios with diverse species, cluttered backgrounds, and incomplete keypoints.

comment: 13pages,2figures

☆ SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)

Trong-Thuan Nguyen, Viet-Tham Huynh, Quang-Thuc Nguyen, Hoang-Phuc Nguyen, Long Le Bao, Thai Hoang Minh, Minh Nguyen Anh, Thang Nguyen Tien, Phat Nguyen Thuan, Huy Nguyen Phong, Bao Huynh Thai, Vinh-Tiep Nguyen, Duc-Vu Nguyen, Phu-Hoa Pham, Minh-Huy Le-Hoang, Nguyen-Khang Le, Minh-Chinh Nguyen, Minh-Quan Ho, Ngoc-Long Tran, Hien-Long Le-Hoang, Man-Khoi Tran, Anh-Duong Tran, Kim Nguyen, Quan Nguyen Hung, Dat Phan Thanh, Hoang Tran Van, Tien Huynh Viet, Nhan Nguyen Viet Thien, Dinh-Khoi Vo, Van-Loc Nguyen, Trung-Nghia Le, Tam V. Nguyen, Minh-Triet Tran

Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addition, ROOMELSA includes over 1,600 apartment scenes, nearly 5,200 rooms, and more than 44,000 targeted queries. Empirically, while coarse object retrieval is largely solved, only one top-performing model consistently ranked the correct match first across nearly all test cases. Notably, a lightweight CLIP-based model also performed well, although it struggled with subtle variations in materials, part structures, and contextual cues, resulting in occasional errors. These findings highlight the importance of tightly integrating visual and language understanding. By bridging the gap between scene-level grounding and fine-grained 3D retrieval, ROOMELSA establishes a new benchmark for advancing robust, real-world 3D recognition systems.

☆ Bridging the Gap: A Framework for Real-World Video Deepfake Detection via Social Network Compression Emulation

Andrea Montibeller, Dasara Shullani, Daniele Baracchi, Alessandro Piva, Giulia Boato

The growing presence of AI-generated videos on social networks poses new challenges for deepfake detection, as detectors trained under controlled conditions often fail to generalize to real-world scenarios. A key factor behind this gap is the aggressive, proprietary compression applied by platforms like YouTube and Facebook, which launder low-level forensic cues. However, replicating these transformations at scale is difficult due to API limitations and data-sharing constraints. For these reasons, we propose a first framework that emulates the video sharing pipelines of social networks by estimating compression and resizing parameters from a small set of uploaded videos. These parameters enable a local emulator capable of reproducing platform-specific artifacts on large datasets without direct API access. Experiments on FaceForensics++ videos shared via social networks demonstrate that our emulated data closely matches the degradation patterns of real uploads. Furthermore, detectors fine-tuned on emulated videos achieve comparable performance to those trained on actual shared media. Our approach offers a scalable and practical solution for bridging the gap between lab-based training and real-world deployment of deepfake detectors, particularly in the underexplored domain of compressed video content.

☆ Exploring Palette based Color Guidance in Diffusion Models ACM MM 2025

Qianru Qiu, Jiafeng Mao, Xueting Wang

With the advent of diffusion models, Text-to-Image (T2I) generation has seen substantial advancements. Current T2I models allow users to specify object colors using linguistic color names, and some methods aim to personalize color-object association through prompt learning. However, existing models struggle to provide comprehensive control over the color schemes of an entire image, especially for background elements and less prominent objects not explicitly mentioned in prompts. This paper proposes a novel approach to enhance color scheme control by integrating color palettes as a separate guidance mechanism alongside prompt instructions. We investigate the effectiveness of palette guidance by exploring various palette representation methods within a diffusion-based image colorization framework. To facilitate this exploration, we construct specialized palette-text-image datasets and conduct extensive quantitative and qualitative analyses. Our results demonstrate that incorporating palette guidance significantly improves the model's ability to generate images with desired color schemes, enabling a more controlled and refined colorization process.

comment: Accepted to ACM MM 2025

☆ Adaptive Confidence-Wise Loss for Improved Lens Structure Segmentation in AS-OCT

Zunjie Xiao, Xiao Wu, Tianhang Liu, Lingxi Hu, Yinling Zhang, Xiaoqing Zhang, Risa Higashita, Jiang Liu

Precise lens structure segmentation is essential for the design of intraocular lenses (IOLs) in cataract surgery. Existing deep segmentation networks typically weight all pixels equally under cross-entropy (CE) loss, overlooking the fact that sub-regions of lens structures are inhomogeneous (e.g., some regions perform better than others) and that boundary regions often suffer from poor segmentation calibration at the pixel level. Clinically, experts annotate different sub-regions of lens structures with varying confidence levels, considering factors such as sub-region proportions, ambiguous boundaries, and lens structure shapes. Motivated by this observation, we propose an Adaptive Confidence-Wise (ACW) loss to group each lens structure sub-region into different confidence sub-regions via a confidence threshold from the unique region aspect, aiming to exploit the potential of expert annotation confidence prior. Specifically, ACW clusters each target region into low-confidence and high-confidence groups and then applies a region-weighted loss to reweigh each confidence group. Moreover, we design an adaptive confidence threshold optimization algorithm to adjust the confidence threshold of ACW dynamically. Additionally, to better quantify the miscalibration errors in boundary region segmentation, we propose a new metric, termed Boundary Expected Calibration Error (BECE). Extensive experiments on a clinical lens structure AS-OCT dataset and other multi-structure datasets demonstrate that our ACW significantly outperforms competitive segmentation loss methods across different deep segmentation networks (e.g., MedSAM). Notably, our method surpasses CE with 6.13% IoU gain, 4.33% DSC increase, and 4.79% BECE reduction in lens structure segmentation under U-Net. The code of this paper is available at https://github.com/XiaoLing12138/Adaptive-Confidence-Wise-Loss.

☆ SafeFix: Targeted Model Repair via Controlled Image Generation

Ouyang Xu, Baoming Zhang, Ruiyu Mao, Yunhui Guo

Deep learning models for visual recognition often exhibit systematic errors due to underrepresented semantic subpopulations. Although existing debugging frameworks can pinpoint these failures by identifying key failure attributes, repairing the model effectively remains difficult. Current solutions often rely on manually designed prompts to generate synthetic training images -- an approach prone to distribution shift and semantic errors. To overcome these challenges, we introduce a model repair module that builds on an interpretable failure attribution pipeline. Our approach uses a conditional text-to-image model to generate semantically faithful and targeted images for failure cases. To preserve the quality and relevance of the generated samples, we further employ a large vision-language model (LVLM) to filter the outputs, enforcing alignment with the original data distribution and maintaining semantic consistency. By retraining vision models with this rare-case-augmented synthetic dataset, we significantly reduce errors associated with rare cases. Our experiments demonstrate that this targeted repair strategy improves model robustness without introducing new bugs. Code is available at https://github.com/oxu2/SafeFix

☆ Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos

Qi Zheng, Li-Heng Chen, Chenlong He, Neil Berkbeck, Yilin Wang, Balu Adsumilli, Alan C. Bovik, Yibo Fan, Zhengzhong Tu

Although there have been notable advancements in video compression technologies in recent years, banding artifacts remain a serious issue affecting the quality of compressed videos, particularly on smooth regions of high-definition videos. Noticeable banding artifacts can severely impact the perceptual quality of videos viewed on a high-end HDTV or high-resolution screen. Hence, there is a pressing need for a systematic investigation of the banding video quality assessment problem for advanced video codecs. Given that the existing publicly available datasets for studying banding artifacts are limited to still picture data only, which cannot account for temporal banding dynamics, we have created a first-of-a-kind open video dataset, dubbed LIVE-YT-Banding, which consists of 160 videos generated by four different compression parameters using the AV1 video codec. A total of 7,200 subjective opinions are collected from a cohort of 45 human subjects. To demonstrate the value of this new resources, we tested and compared a variety of models that detect banding occurrences, and measure their impact on perceived quality. Among these, we introduce an effective and efficient new no-reference (NR) video quality evaluator which we call CBAND. CBAND leverages the properties of the learned statistics of natural images expressed in the embeddings of deep neural networks. Our experimental results show that the perceptual banding prediction performance of CBAND significantly exceeds that of previous state-of-the-art models, and is also orders of magnitude faster. Moreover, CBAND can be employed as a differentiable loss function to optimize video debanding models. The LIVE-YT-Banding database, code, and pre-trained model are all publically available at https://github.com/uniqzheng/CBAND.

☆ ROD: RGB-Only Fast and Efficient Off-road Freespace Detection

Tong Sun, Hongliang Ye, Jilin Mei, Liang Chen, Fangzhou Zhao, Leiqiang Zong, Yu Hu

Off-road freespace detection is more challenging than on-road scenarios because of the blurred boundaries of traversable areas. Previous state-of-the-art (SOTA) methods employ multi-modal fusion of RGB images and LiDAR data. However, due to the significant increase in inference time when calculating surface normal maps from LiDAR data, multi-modal methods are not suitable for real-time applications, particularly in real-world scenarios where higher FPS is required compared to slow navigation. This paper presents a novel RGB-only approach for off-road freespace detection, named ROD, eliminating the reliance on LiDAR data and its computational demands. Specifically, we utilize a pre-trained Vision Transformer (ViT) to extract rich features from RGB images. Additionally, we design a lightweight yet efficient decoder, which together improve both precision and inference speed. ROD establishes a new SOTA on ORFD and RELLIS-3D datasets, as well as an inference speed of 50 FPS, significantly outperforming prior models.

☆ STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision

Chen Li, Han Zhang, Zhantao Yang, Fangyi Chen, Zihan Wang, Anudeepsekhar Bolimera, Marios Savvides

Vision-language models (VLMs) have made significant strides in reasoning, yet they often struggle with complex multimodal tasks and tend to generate overly verbose outputs. A key limitation is their reliance on chain-of-thought (CoT) reasoning, despite many tasks benefiting from alternative topologies like trees or graphs. To address this, we introduce STELAR-Vision, a training framework for topology-aware reasoning. At its core is TopoAug, a synthetic data pipeline that enriches training with diverse topological structures. Using supervised fine-tuning and reinforcement learning, we post-train Qwen2VL models with both accuracy and efficiency in mind. Additionally, we propose Frugal Learning, which reduces output length with minimal accuracy loss. On MATH-V and VLM-S2H, STELAR-Vision improves accuracy by 9.7% over its base model and surpasses the larger Qwen2VL-72B-Instruct by 7.3%. On five out-of-distribution benchmarks, it outperforms Phi-4-Multimodal-Instruct by up to 28.4% and LLaMA-3.2-11B-Vision-Instruct by up to 13.2%, demonstrating strong generalization. Compared to Chain-Only training, our approach achieves 4.3% higher overall accuracy on in-distribution datasets and consistently outperforms across all OOD benchmarks. We have released datasets, and code will be available.

☆ PADReg: Physics-Aware Deformable Registration Guided by Contact Force for Ultrasound Sequences

Yimeng Geng, Mingyang Zhao, Fan Xu, Guanglin Cao, Gaofeng Meng, Hongbin Liu

Ultrasound deformable registration estimates spatial transformations between pairs of deformed ultrasound images, which is crucial for capturing biomechanical properties and enhancing diagnostic accuracy in diseases such as thyroid nodules and breast cancer. However, ultrasound deformable registration remains highly challenging, especially under large deformation. The inherently low contrast, heavy noise and ambiguous tissue boundaries in ultrasound images severely hinder reliable feature extraction and correspondence matching. Existing methods often suffer from poor anatomical alignment and lack physical interpretability. To address the problem, we propose PADReg, a physics-aware deformable registration framework guided by contact force. PADReg leverages synchronized contact force measured by robotic ultrasound systems as a physical prior to constrain the registration. Specifically, instead of directly predicting deformation fields, we first construct a pixel-wise stiffness map utilizing the multi-modal information from contact force and ultrasound images. The stiffness map is then combined with force data to estimate a dense deformation field, through a lightweight physics-aware module inspired by Hooke's law. This design enables PADReg to achieve physically plausible registration with better anatomical alignment than previous methods relying solely on image similarity. Experiments on in-vivo datasets demonstrate that it attains a HD95 of 12.90, which is 21.34\% better than state-of-the-art methods. The source code is available at https://github.com/evelynskip/PADReg.

comment: This work has been submitted to the IEEE for possible publication

☆ MMIF-AMIN: Adaptive Loss-Driven Multi-Scale Invertible Dense Network for Multimodal Medical Image Fusion

Tao Luo, Weihua Xu

Multimodal medical image fusion (MMIF) aims to integrate images from different modalities to produce a comprehensive image that enhances medical diagnosis by accurately depicting organ structures, tissue textures, and metabolic information. Capturing both the unique and complementary information across multiple modalities simultaneously is a key research challenge in MMIF. To address this challenge, this paper proposes a novel image fusion method, MMIF-AMIN, which features a new architecture that can effectively extract these unique and complementary features. Specifically, an Invertible Dense Network (IDN) is employed for lossless feature extraction from individual modalities. To extract complementary information between modalities, a Multi-scale Complementary Feature Extraction Module (MCFEM) is designed, which incorporates a hybrid attention mechanism, convolutional layers of varying sizes, and Transformers. An adaptive loss function is introduced to guide model learning, addressing the limitations of traditional manually-designed loss functions and enhancing the depth of data mining. Extensive experiments demonstrate that MMIF-AMIN outperforms nine state-of-the-art MMIF methods, delivering superior results in both quantitative and qualitative analyses. Ablation experiments confirm the effectiveness of each component of the proposed method. Additionally, extending MMIF-AMIN to other image fusion tasks also achieves promising performance.

comment: 10 pages, 6 figures,conference

☆ Multi-level Collaborative Distillation Meets Global Workspace Model: A Unified Framework for OCIL

Shibin Su, Guoqiang Liang, De Cheng, Shizhou Zhang, Lingyan Ran, Yanning Zhang

Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams and samples of the data streams can be seen only once, making it more suitable for real-world scenarios compared to offline learning. However, OCIL faces two key challenges: maintaining model stability under strict memory constraints and ensuring adaptability to new tasks. Under stricter memory constraints, current replay-based methods are less effective. While ensemble methods improve adaptability (plasticity), they often struggle with stability. To overcome these challenges, we propose a novel approach that enhances ensemble learning through a Global Workspace Model (GWM)-a shared, implicit memory that guides the learning of multiple student models. The GWM is formed by fusing the parameters of all students within each training batch, capturing the historical learning trajectory and serving as a dynamic anchor for knowledge consolidation. This fused model is then redistributed periodically to the students to stabilize learning and promote cross-task consistency. In addition, we introduce a multi-level collaborative distillation mechanism. This approach enforces peer-to-peer consistency among students and preserves historical knowledge by aligning each student with the GWM. As a result, student models remain adaptable to new tasks while maintaining previously learned knowledge, striking a better balance between stability and plasticity. Extensive experiments on three standard OCIL benchmarks show that our method delivers significant performance improvement for several OCIL models across various memory budgets.

comment: 12 pages, 7 figures

☆ Learning Generalizable and Efficient Image Watermarking via Hierarchical Two-Stage Optimization

Ke Liu, Xuanhan Wang, Qilong Zhang, Lianli Gao, Jingkuan Song

Deep image watermarking, which refers to enable imperceptible watermark embedding and reliable extraction in cover images, has shown to be effective for copyright protection of image assets. However, existing methods face limitations in simultaneously satisfying three essential criteria for generalizable watermarking: 1) invisibility (imperceptible hide of watermarks), 2) robustness (reliable watermark recovery under diverse conditions), and 3) broad applicability (low latency in watermarking process). To address these limitations, we propose a Hierarchical Watermark Learning (HiWL), a two-stage optimization that enable a watermarking model to simultaneously achieve three criteria. In the first stage, distribution alignment learning is designed to establish a common latent space with two constraints: 1) visual consistency between watermarked and non-watermarked images, and 2) information invariance across watermark latent representations. In this way, multi-modal inputs including watermark message (binary codes) and cover images (RGB pixels) can be well represented, ensuring the invisibility of watermarks and robustness in watermarking process thereby. The second stage employs generalized watermark representation learning to establish a disentanglement policy for separating watermarks from image content in RGB space. In particular, it strongly penalizes substantial fluctuations in separated RGB watermarks corresponding to identical messages. Consequently, HiWL effectively learns generalizable latent-space watermark representations while maintaining broad applicability. Extensive experiments demonstrate the effectiveness of proposed method. In particular, it achieves 7.6\% higher accuracy in watermark extraction than existing methods, while maintaining extremely low latency (100K images processed in 8s).

☆ Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation

Xin Wang, Yin Guo, Jiamin Xia, Kaiyu Zhang, Niranjan Balu, Mahmud Mossa-Basha, Linda Shapiro, Chun Yuan

☆ AME: Aligned Manifold Entropy for Robust Vision-Language Distillation

Guiming Cao, Yuming Ou

Knowledge distillation is a long-established technique for knowledge transfer, and has regained attention in the context of the recent emergence of large vision-language models (VLMs). However, vision-language knowledge distillation often requires sufficient training data to achieve robust generalization on amples with ambiguous or boundary-adjacent representations, which are associated with high predictive uncertainty. Critically, collecting such large-scale, task-specific data for training is often impractical in real-world scenarios. To address this major challenge arising from the entanglement of uncertainty and cross-modal feature representation, we propose Aligned Manifold Entropy for Robust Vision-Language Distillation (AME), aiming to achieve robust generalization under real-world conditions. AME applies entropy minimization over a reconfigured shared manifold, where multi-modal data (i.e., image and text) are bridged through a pair of projection functions, conducive to structural compression for cross-modal feature representations. This enables robust knowledge distillation under low-data regimes, while requiring no architectural modifications to the backbone. As a result, it can serve as a plug-and-play module compatible with a wide range of vision-language distillation frameworks. Notably, our theoretical analysis reveals that integrating knowledge distillation with entropy minimization over the shared manifold leads to a tighter generalization error bound. Extensive experiments across diverse distillation architectures and training settings demonstrate that AME consistently facilitates robust knowledge distillation, resulting in superior generalization performance across a wide spectrum of downstream tasks.

☆ Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation

Jiahua Dong, Hui Yin, Wenqi Liang, Hanbin Zhao, Henghui Ding, Nicu Sebe, Salman Khan, Fahad Shahbaz Khan

Video instance segmentation (VIS) has gained significant attention for its capability in tracking and segmenting object instances across video frames. However, most of the existing VIS approaches unrealistically assume that the categories of object instances remain fixed over time. Moreover, they experience catastrophic forgetting of old classes when required to continuously learn object instances belonging to new categories. To resolve these challenges, we develop a novel Hierarchical Visual Prompt Learning (HVPL) model that overcomes catastrophic forgetting of previous categories from both frame-level and video-level perspectives. Specifically, to mitigate forgetting at the frame level, we devise a task-specific frame prompt and an orthogonal gradient correction (OGC) module. The OGC module helps the frame prompt encode task-specific global instance information for new classes in each individual frame by projecting its gradients onto the orthogonal feature space of old classes. Furthermore, to address forgetting at the video level, we design a task-specific video prompt and a video context decoder. This decoder first embeds structural inter-class relationships across frames into the frame prompt features, and then propagates task-specific global video contexts from the frame prompt features to the video prompt. Through rigorous comparisons, our HVPL model proves to be more effective than baseline approaches. The code is available at https://github.com/JiahuaDong/HVPL.

comment: Accepted to ICCV2025

☆ Neural Artistic Style and Color Transfer Using Deep Learning

Justin London

Neural artistic style transfers and blends the content and style representation of one image with the style of another. This enables artists to create unique innovative visuals and enhances artistic expression in various fields including art, design, and film. Color transfer algorithms are an important in digital image processing by adjusting the color information in a target image based on the colors in the source image. Color transfer enhances images and videos in film and photography, and can aid in image correction. We introduce a methodology that combines neural artistic style with color transfer. The method uses the Kullback-Leibler (KL) divergence to quantitatively evaluate color and luminance histogram matching algorithms including Reinhard global color transfer, iteration distribution transfer (IDT), IDT with regrain, Cholesky, and PCA between the original and neural artistic style transferred image using deep learning. We estimate the color channel kernel densities. Various experiments are performed to evaluate the KL of these algorithms and their color histograms for style to content transfer.

☆ SelfHVD: Self-Supervised Handheld Video Deblurring for Mobile Phones

Honglei Xu, Zhilu Zhang, Junjie Fan, Xiaohe Wu, Wangmeng Zuo

Shooting video with a handheld mobile phone, the most common photographic device, often results in blurry frames due to shaking hands and other instability factors. Although previous video deblurring methods have achieved impressive progress, they still struggle to perform satisfactorily on real-world handheld video due to the blur domain gap between training and testing data. To address the issue, we propose a self-supervised method for handheld video deblurring, which is driven by sharp clues in the video. First, to train the deblurring model, we extract the sharp clues from the video and take them as misalignment labels of neighboring blurry frames. Second, to improve the model's ability, we propose a novel Self-Enhanced Video Deblurring (SEVD) method to create higher-quality paired video data. Third, we propose a Self-Constrained Spatial Consistency Maintenance (SCSCM) method to regularize the model, preventing position shifts between the output and input frames. Moreover, we construct a synthetic and a real-world handheld video dataset for handheld video deblurring. Extensive experiments on these two and other common real-world datasets demonstrate that our method significantly outperforms existing self-supervised ones. The code and datasets are publicly available at https://github.com/cshonglei/SelfHVD.

☆ Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization

Jihwan Park, Taehoon song, Sanghyeok Lee, Miso Choi, Hyunwoo J. Kim

☆ Yan: Foundational Interactive Video Generation

Yan Team

☆ QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection

Yuxiao Wang, Wolin Liang, Yu Lei, Weiying Xue, Nan Zhuang, Qi Liu

Human-Object Interaction (HOI) detection aims to localize human-object pairs and recognize their interactions in images. Although DETR-based methods have recently emerged as the mainstream framework for HOI detection, they still suffer from a key limitation: Randomly initialized queries lack explicit semantics, leading to suboptimal detection performance. To address this challenge, we propose QueryCraft, a novel plug-and-play HOI detection framework that incorporates semantic priors and guided feature learning through transformer-based query initialization. Central to our approach is \textbf{ACTOR} (\textbf{A}ction-aware \textbf{C}ross-modal \textbf{T}ransf\textbf{OR}mer), a cross-modal Transformer encoder that jointly attends to visual regions and textual prompts to extract action-relevant features. Rather than merely aligning modalities, ACTOR leverages language-guided attention to infer interaction semantics and produce semantically meaningful query representations. To further enhance object-level query quality, we introduce a \textbf{P}erceptual \textbf{D}istilled \textbf{Q}uery \textbf{D}ecoder (\textbf{PDQD}), which distills object category awareness from a pre-trained detector to serve as object query initiation. This dual-branch query initialization enables the model to generate more interpretable and effective queries for HOI detection. Extensive experiments on HICO-Det and V-COCO benchmarks demonstrate that our method achieves state-of-the-art performance and strong generalization. Code will be released upon publication.

☆ DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding

Wenwen Yu, Zhibo Yang, Yuliang Liu, Xiang Bai

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in document understanding. However, their reasoning processes remain largely black-box, making it difficult to ensure reliability and trustworthiness, especially in high-stakes domains such as legal, financial, and medical document analysis. Existing methods use fixed Chain-of-Thought (CoT) reasoning with supervised fine-tuning (SFT) but suffer from catastrophic forgetting, poor adaptability, and limited generalization across domain tasks. In this paper, we propose DocThinker, a rule-based Reinforcement Learning (RL) framework for dynamic inference-time reasoning. Instead of relying on static CoT templates, DocThinker autonomously refines reasoning strategies via policy learning, generating explainable intermediate results, including structured reasoning processes, rephrased questions, regions of interest (RoI) supporting the answer, and the final answer. By integrating multi-objective rule-based rewards and KL-constrained optimization, our method mitigates catastrophic forgetting and enhances both adaptability and transparency. Extensive experiments on multiple benchmarks demonstrate that DocThinker significantly improves generalization while producing more explainable and human-understandable reasoning steps. Our findings highlight RL as a powerful alternative for enhancing explainability and adaptability in MLLM-based document understanding. Code will be available at https://github.com/wenwenyu/DocThinker.

comment: ICCV 2025

☆ RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space

Jingyun Liang, Jingkai Zhou, Shikai Li, Chenjie Cao, Lei Sun, Yichen Qian, Weihua Chen, Fan Wang

Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory and action patterns. In this paper, we propose a decomposed human motion control and video generation framework that explicitly decouples motion from appearance, subject from background, and action from trajectory, enabling flexible mix-and-match composition of these elements. Concretely, we first build a ground-aware 3D world coordinate system and perform motion editing directly in the 3D space. Trajectory control is implemented by unprojecting edited 2D trajectories into 3D with focal-length calibration and coordinate transformation, followed by speed alignment and orientation adjustment; actions are supplied by a motion bank or generated via text-to-motion methods. Then, based on modern text-to-video diffusion transformer models, we inject the subject as tokens for full attention, concatenate the background along the channel dimension, and add motion (trajectory and action) control signals by addition. Such a design opens up the possibility for us to generate realistic videos of anyone doing anything anywhere. Extensive experiments on benchmark datasets and real-world cases demonstrate that our method achieves state-of-the-art performance on both element-wise controllability and overall video quality.

comment: Project page: https://jingyunliang.github.io/RealisMotion

☆ Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation

Chenruo Liu, Hongjun Liu, Zeyu Lai, Yiqiu Shen, Chen Zhao, Qi Lei

To enhance group robustness to spurious correlations, prior work often relies on auxiliary annotations for groups or spurious features and assumes identical sets of groups across source and target domains. These two requirements are both unnatural and impractical in real-world settings. To overcome these limitations, we propose a method that leverages the semantic structure inherent in class labels--specifically, superclass information--to naturally reduce reliance on spurious features. Our model employs gradient-based attention guided by a pre-trained vision-language model to disentangle superclass-relevant and irrelevant features. Then, by promoting the use of all superclass-relevant features for prediction, our approach achieves robustness to more complex spurious correlations without the need to annotate any source samples. Experiments across diverse datasets demonstrate that our method significantly outperforms baselines in domain generalization tasks, with clear improvements in both quantitative metrics and qualitative visualizations.

☆ Think as Cardiac Sonographers: Marrying SAM with Left Ventricular Indicators Measurements According to Clinical Guidelines

Tuo Liu, Qinghan Yang, Yu Zhang, Rongjun Ge, Yang Chen, Guangquan Zhou

Left ventricular (LV) indicator measurements following clinical echocardiog-raphy guidelines are important for diagnosing cardiovascular disease. Alt-hough existing algorithms have explored automated LV quantification, they can struggle to capture generic visual representations due to the normally small training datasets. Therefore, it is necessary to introduce vision founda-tional models (VFM) with abundant knowledge. However, VFMs represented by the segment anything model (SAM) are usually suitable for segmentation but incapable of identifying key anatomical points, which are critical in LV indicator measurements. In this paper, we propose a novel framework named AutoSAME, combining the powerful visual understanding of SAM with seg-mentation and landmark localization tasks simultaneously. Consequently, the framework mimics the operation of cardiac sonographers, achieving LV indi-cator measurements consistent with clinical guidelines. We further present fil-tered cross-branch attention (FCBA) in AutoSAME, which leverages relatively comprehensive features in the segmentation to enhance the heatmap regression (HR) of key points from the frequency domain perspective, optimizing the vis-ual representation learned by the latter. Moreover, we propose spatial-guided prompt alignment (SGPA) to automatically generate prompt embeddings guid-ed by spatial properties of LV, thereby improving the accuracy of dense pre-dictions by prior spatial knowledge. The extensive experiments on an echocar-diography dataset demonstrate the efficiency of each design and the superiori-ty of our AutoSAME in LV segmentation, landmark localization, and indicator measurements. The code will be available at https://github.com/QC-LIU-1997/AutoSAME.

☆ Unlocking the Potential of Diffusion Priors in Blind Face Restoration

Yunqi Miao, Zhiyu Qu, Mingqi Gao, Changrui Chen, Jifei Song, Jungong Han, Jiankang Deng

Although diffusion prior is rising as a powerful solution for blind face restoration (BFR), the inherent gap between the vanilla diffusion model and BFR settings hinders its seamless adaptation. The gap mainly stems from the discrepancy between 1) high-quality (HQ) and low-quality (LQ) images and 2) synthesized and real-world images. The vanilla diffusion model is trained on images with no or less degradations, whereas BFR handles moderately to severely degraded images. Additionally, LQ images used for training are synthesized by a naive degradation model with limited degradation patterns, which fails to simulate complex and unknown degradations in real-world scenarios. In this work, we use a unified network FLIPNET that switches between two modes to resolve specific gaps. In Restoration mode, the model gradually integrates BFR-oriented features and face embeddings from LQ images to achieve authentic and faithful face restoration. In Degradation mode, the model synthesizes real-world like degraded images based on the knowledge learned from real-world degradation datasets. Extensive evaluations on benchmark datasets show that our model 1) outperforms previous diffusion prior based BFR methods in terms of authenticity and fidelity, and 2) outperforms the naive degradation model in modeling the real-world degradations.

☆ Boosting Generic Semi-Supervised Medical Image Segmentation via Diverse Teaching and Label Propagation

Wei Li, Pengcheng Zhou, Linye Ma, Wenyi Zhao, Huihua Yang

Both limited annotation and domain shift are significant challenges frequently encountered in medical image segmentation, leading to derivative scenarios like semi-supervised medical (SSMIS), semi-supervised medical domain generalization (Semi-MDG) and unsupervised medical domain adaptation (UMDA). Conventional methods are generally tailored to specific tasks in isolation, the error accumulation hinders the effective utilization of unlabeled data and limits further improvements, resulting in suboptimal performance when these issues occur. In this paper, we aim to develop a generic framework that masters all three tasks. We found that the key to solving the problem lies in how to generate reliable pseudo labels for the unlabeled data in the presence of domain shift with labeled data and increasing the diversity of the model. To tackle this issue, we employ a Diverse Teaching and Label Propagation Network (DTLP-Net) to boosting the Generic Semi-Supervised Medical Image Segmentation. Our DTLP-Net involves a single student model and two diverse teacher models, which can generate reliable pseudo-labels for the student model. The first teacher model decouple the training process with labeled and unlabeled data, The second teacher is momentum-updated periodically, thus generating reliable yet divers pseudo-labels. To fully utilize the information within the data, we adopt inter-sample and intra-sample data augmentation to learn the global and local knowledge. In addition, to further capture the voxel-level correlations, we propose label propagation to enhance the model robust. We evaluate our proposed framework on five benchmark datasets for SSMIS, UMDA, and Semi-MDG tasks. The results showcase notable improvements compared to state-of-the-art methods across all five settings, indicating the potential of our framework to tackle more challenging SSL scenarios.

☆ Calibration Attention: Instance-wise Temperature Scaling for Vision Transformers

Wenhao Liang, Wei Emma Zhang, Lin Yue, Miao Xu, Olaf Maennel, Weitong Chen

Probability calibration is critical when Vision Transformers are deployed in risk-sensitive applications. The standard fix, post-hoc temperature scaling, uses a single global scalar and requires a held-out validation set. We introduce Calibration Attention (CalAttn), a drop-in module that learns an adaptive, per-instance temperature directly from the ViT's CLS token. Across CIFAR-10/100, MNIST, Tiny-ImageNet, and ImageNet-1K, CalAttn reduces calibration error by up to 4x on ViT-224, DeiT, and Swin, while adding under 0.1 percent additional parameters. The learned temperatures cluster tightly around 1.0, in contrast to the large global values used by standard temperature scaling. CalAttn is simple, efficient, and architecture-agnostic, and yields more trustworthy probabilities without sacrificing accuracy. Code: [https://github.com/EagleAdelaide/CalibrationAttention-CalAttn-](https://github.com/EagleAdelaide/CalibrationAttention-CalAttn-)

comment: UnderReview

☆ Hybrid Long and Short Range Flows for Point Cloud Filtering

Dasith de Silva Edirimuni, Xuequan Lu, Ajmal Saeed Mian, Lei Wei, Gang Li, Scott Schaefer, Ying He

Point cloud capture processes are error-prone and introduce noisy artifacts that necessitate filtering/denoising. Recent filtering methods often suffer from point clustering or noise retaining issues. In this paper, we propose Hybrid Point Cloud Filtering ($\textbf{HybridPF}$) that considers both short-range and long-range filtering trajectories when removing noise. It is well established that short range scores, given by $\nabla_{x}\log p(x_t)$, may provide the necessary displacements to move noisy points to the underlying clean surface. By contrast, long range velocity flows approximate constant displacements directed from a high noise variant patch $x_0$ towards the corresponding clean surface $x_1$. Here, noisy patches $x_t$ are viewed as intermediate states between the high noise variant and the clean patches. Our intuition is that long range information from velocity flow models can guide the short range scores to align more closely with the clean points. In turn, score models generally provide a quicker convergence to the clean surface. Specifically, we devise two parallel modules, the ShortModule and LongModule, each consisting of an Encoder-Decoder pair to respectively account for short-range scores and long-range flows. We find that short-range scores, guided by long-range features, yield filtered point clouds with good point distributions and convergence near the clean surface. We design a joint loss function to simultaneously train the ShortModule and LongModule, in an end-to-end manner. Finally, we identify a key weakness in current displacement based methods, limitations on the decoder architecture, and propose a dynamic graph convolutional decoder to improve the inference process. Comprehensive experiments demonstrate that our HybridPF achieves state-of-the-art results while enabling faster inference speed.

☆ Training Kindai OCR with parallel textline images and self-attention feature distance-based loss

Anh Le, Asanobu Kitamoto

Kindai documents, written in modern Japanese from the late 19th to early 20th century, hold significant historical value for researchers studying societal structures, daily life, and environmental conditions of that period. However, transcribing these documents remains a labor-intensive and time-consuming task, resulting in limited annotated data for training optical character recognition (OCR) systems. This research addresses this challenge of data scarcity by leveraging parallel textline images - pairs of original Kindai text and their counterparts in contemporary Japanese fonts - to augment training datasets. We introduce a distance-based objective function that minimizes the gap between self-attention features of the parallel image pairs. Specifically, we explore Euclidean distance and Maximum Mean Discrepancy (MMD) as domain adaptation metrics. Experimental results demonstrate that our method reduces the character error rate (CER) by 2.23% and 3.94% over a Transformer-based OCR baseline when using Euclidean distance and MMD, respectively. Furthermore, our approach improves the discriminative quality of self-attention representations, leading to more effective OCR performance for historical documents.

♻ ☆ ViStoryBench: Comprehensive Benchmark Suite for Story Visualization

Cailin Zhuang, Ailin Huang, Wei Cheng, Jingwei Wu, Yaoqi Hu, Jiaqi Liao, Hongyuan Wang, Xinyao Liao, Weiwei Cai, Hengyuan Xu, Xuanyang Zhang, Xianfang Zeng, Zhewei Huang, Gang Yu, Chi Zhang

Story visualization aims to generate coherent image sequences that faithfully depict a narrative and align with character references. Despite progress in generative models, existing benchmarks are narrow in scope, often limited to short prompts, no character reference, or single-image cases, and fall short of real-world storytelling complexity. This hinders a nuanced understanding of model capabilities and limitations. We present ViStoryBench, a comprehensive benchmark designed to evaluate story visualization models across diverse narrative structures, visual styles, and character settings. The benchmark features richly annotated multi-shot scripts derived from curated stories spanning literature, film, and folklore. Large language models assist in story summarization and script generation, with all outputs verified by humans to ensure coherence and fidelity. Character references are carefully curated to maintain intra-story consistency across varying artistic styles. To enable thorough evaluation, ViStoryBench introduces a set of automated metrics that assess character consistency, style similarity, prompt adherence, aesthetic quality, and generation artifacts such as copy-paste behavior. These metrics are validated through human studies, and used to benchmark a broad range of open-source and commercial models. ViStoryBench offers a high-fidelity, multi-dimensional evaluation suite that facilitates systematic analysis and fosters future progress in visual storytelling.

comment: 33 Pages, Project Page: https://vistorybench.github.io/, Code: https://github.com/vistorybench/vistorybench

♻ ☆ CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics

Shravan Nayak, Mehar Bhatia, Xiaofeng Zhang, Verena Rieser, Lisa Anne Hendricks, Sjoerd van Steenkiste, Yash Goyal, Karolina Stańczak, Aishwarya Agrawal

The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurately represent diverse cultural contexts -- where missed cues can stereotype communities and undermine usability. In this work, we present the first study to systematically quantify the alignment of T2I models and evaluation metrics with respect to both explicit (stated) as well as implicit (unstated, implied by the prompt's cultural context) cultural expectations. To this end, we introduce CulturalFrames, a novel benchmark designed for rigorous human evaluation of cultural representation in visual generations. Spanning 10 countries and 5 socio-cultural domains, CulturalFrames comprises 983 prompts, 3637 corresponding images generated by 4 state-of-the-art T2I models, and over 10k detailed human annotations. We find that across models and countries, cultural expectations are missed an average of 44% of the time. Among these failures, explicit expectations are missed at a surprisingly high average rate of 68%, while implicit expectation failures are also significant, averaging 49%. Furthermore, we show that existing T2I evaluation metrics correlate poorly with human judgments of cultural alignment, irrespective of their internal reasoning. Collectively, our findings expose critical gaps, provide a concrete testbed, and outline actionable directions for developing culturally informed T2I models and metrics that improve global usability.

♻ ☆ Euclid Quick Data Release (Q1). Active galactic nuclei identification using diffusion-based inpainting of Euclid VIS images

Euclid Collaboration, G. Stevens, S. Fotopoulou, M. N. Bremer, T. Matamoro Zatarain, K. Jahnke, B. Margalef-Bentabol, M. Huertas-Company, M. J. Smith, M. Walmsley, M. Salvato, M. Mezcua, A. Paulino-Afonso, M. Siudek, M. Talia, F. Ricci, W. Roster, N. Aghanim, B. Altieri, S. Andreon, H. Aussel, C. Baccigalupi, M. Baldi, S. Bardelli, P. Battaglia, A. Biviano, A. Bonchi, E. Branchini, M. Brescia, J. Brinchmann, S. Camera, G. Cañas-Herrera, V. Capobianco, C. Carbone, J. Carretero, M. Castellano, G. Castignani, S. Cavuoti, K. C. Chambers, A. Cimatti, C. Colodro-Conde, G. Congedo, C. J. Conselice, L. Conversi, Y. Copin, A. Costille, F. Courbin, H. M. Courtois, M. Cropper, A. Da Silva, H. Degaudenzi, G. De Lucia, C. Dolding, H. Dole, M. Douspis, F. Dubath, X. Dupac, S. Dusini, S. Escoffier, M. Farina, S. Ferriol, K. George, C. Giocoli, B. R. Granett, A. Grazian, F. Grupp, S. V. H. Haugan, I. M. Hook, F. Hormuth, A. Hornstrup, P. Hudelot, M. Jhabvala, E. Keihänen, S. Kermiche, A. Kiessling, M. Kilbinger, B. Kubik, M. Kümmel, H. Kurki-Suonio, Q. Le Boulc'h, A. M. C. Le Brun, D. Le Mignant, P. B. Lilje, V. Lindholm, I. Lloro, G. Mainetti, D. Maino, E. Maiorano, O. Marggraf, M. Martinelli, N. Martinet, F. Marulli, R. Massey, S. Maurogordato, H. J. McCracken, E. Medinaceli, S. Mei, M. Melchior, M. Meneghetti, E. Merlin, G. Meylan, A. Mora, M. Moresco, L. Moscardini, R. Nakajima, C. Neissner, S. -M. Niemi, C. Padilla, S. Paltani, F. Pasian, K. Pedersen, W. J. Percival, V. Pettorino, G. Polenta, M. Poncet, L. A. Popa, L. Pozzetti, F. Raison, R. Rebolo, A. Renzi, J. Rhodes, G. Riccio, E. Romelli, M. Roncarelli, R. Saglia, A. G. Sánchez, D. Sapone, J. A. Schewtschenko, M. Schirmer, P. Schneider, T. Schrabback, A. Secroun, S. Serrano, P. Simon, C. Sirignano, G. Sirri, J. Skottfelt, L. Stanco, J. Steinwagner, P. Tallada-Crespí, A. N. Taylor, I. Tereno, S. Toft, R. Toledo-Moreo, F. Torradeflot, I. Tutusaus, L. Valenziano, J. Valiviita, T. Vassallo, G. Verdoes Kleijn, A. Veropalumbo, Y. Wang, J. Weller, A. Zacchei, G. Zamorani, F. M. Zerbi, I. A. Zinchenko, E. Zucca, V. Allevato, M. Ballardini, M. Bolzonella, E. Bozzo, C. Burigana, R. Cabanac, A. Cappi, J. A. Escartin Vigo, L. Gabarra, W. G. Hartley, J. Martín-Fleitas, S. Matthew, R. B. Metcalf, A. Pezzotta, M. Pöntinen, I. Risso, V. Scottez, M. Sereno, M. Tenti, M. Wiesmann, Y. Akrami, S. Alvi, I. T. Andika, S. Anselmi, M. Archidiacono, F. Atrio-Barandela, D. Bertacca, M. Bethermin, L. Bisigello, A. Blanchard, L. Blot, S. Borgani, M. L. Brown, S. Bruton, A. Calabro, F. Caro, T. Castro, F. Cogato, S. Davini, G. Desprez, A. Díaz-Sánchez, J. J. Diaz, S. Di Domizio, J. M. Diego, P. -A. Duc, A. Enia, Y. Fang, A. G. Ferrari, A. Finoguenov, A. Fontana, A. Franco, J. García-Bellido, T. Gasparetto, V. Gautard, E. Gaztanaga, F. Giacomini, F. Gianotti, M. Guidi, C. M. Gutierrez, A. Hall, S. Hemmati, H. Hildebrandt, J. Hjorth, J. J. E. Kajava, Y. Kang, V. Kansal, D. Karagiannis, C. C. Kirkpatrick, S. Kruk, L. Legrand, M. Lembo, F. Lepori, G. Leroy, J. Lesgourgues, L. Leuzzi, T. I. Liaudat, J. Macias-Perez, M. Magliocchetti, F. Mannucci, R. Maoli, C. J. A. P. Martins, L. Maurin, M. Miluzio, P. Monaco, G. Morgante, K. Naidoo, A. Navarro-Alsina, F. Passalacqua, K. Paterson, L. Patrizii, A. Pisani, D. Potter, S. Quai, M. Radovich, P. -F. Rocci, G. Rodighiero, S. Sacquegna, M. Sahlén, D. B. Sanders, E. Sarpa, A. Schneider, M. Schultheis, D. Sciotti, E. Sellentin, F. Shankar, L. C. Smith, K. Tanidis, G. Testera, R. Teyssier, S. Tosi, A. Troja, M. Tucci, C. Valieri, D. Vergani, G. Verza, N. A. Walton

Light emission from galaxies exhibit diverse brightness profiles, influenced by factors such as galaxy type, structural features and interactions with other galaxies. Elliptical galaxies feature more uniform light distributions, while spiral and irregular galaxies have complex, varied light profiles due to their structural heterogeneity and star-forming activity. In addition, galaxies with an active galactic nucleus (AGN) feature intense, concentrated emission from gas accretion around supermassive black holes, superimposed on regular galactic light, while quasi-stellar objects (QSO) are the extreme case of the AGN emission dominating the galaxy. The challenge of identifying AGN and QSO has been discussed many times in the literature, often requiring multi-wavelength observations. This paper introduces a novel approach to identify AGN and QSO from a single image. Diffusion models have been recently developed in the machine-learning literature to generate realistic-looking images of everyday objects. Utilising the spatial resolving power of the Euclid VIS images, we created a diffusion model trained on one million sources, without using any source pre-selection or labels. The model learns to reconstruct light distributions of normal galaxies, since the population is dominated by them. We condition the prediction of the central light distribution by masking the central few pixels of each source and reconstruct the light according to the diffusion model. We further use this prediction to identify sources that deviate from this profile by examining the reconstruction error of the few central pixels regenerated in each source's core. Our approach, solely using VIS imaging, features high completeness compared to traditional methods of AGN and QSO selection, including optical, near-infrared, mid-infrared, and X-rays.

comment: Paper submitted as part of the A&A Special Issue `Euclid Quick Data Release (Q1)', 34 pages, 26 figures

♻ ☆ Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions

Li Siyao, Yao Feng, Omid Taheri, Chen Change Loy, Michael J. Black

While current general-purpose 3D human models (e.g., SMPL-X) efficiently represent accurate human shape and pose, they lacks the ability to physically interact with the environment due to the kinematic nature. As a result, kinematic-based interaction models often suffer from issues such as interpenetration and unrealistic object dynamics. To address this limitation, we introduce a novel approach that embeds SMPL-X into a tangible entity capable of dynamic physical interactions with its surroundings. Specifically, we propose a "half-physics" mechanism that transforms 3D kinematic motion into a physics simulation. Our approach maintains kinematic control over inherent SMPL-X poses while ensuring physically plausible interactions with scenes and objects, effectively eliminating penetration and unrealistic object dynamics. Unlike reinforcement learning-based methods, which demand extensive and complex training, our half-physics method is learning-free and generalizes to any body shape and motion; meanwhile, it operates in real time. Moreover, it preserves the fidelity of the original kinematic motion while seamlessly integrating physical interactions

♻ ☆ Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?

Yang Yao, Lingyu Li, Jiaxin Song, Chiyu Chen, Zhenqi He, Yixu Wang, Xin Wang, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang

As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.

♻ ☆ MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing

Langyu Wang, Bingke Zhu, Yingying Chen, Yiyuan Zhang, Ming Tang, Jinqiao Wang

The weakly-supervised audio-visual video parsing (AVVP) aims to predict all modality-specific events and locate their temporal boundaries. Despite significant progress, due to the limitations of the weakly-supervised and the deficiencies of the model architecture, existing methods are lacking in simultaneously improving both the segment-level prediction and the event-level prediction. In this work, we propose a audio-visual Mamba network with pseudo labeling aUGmentation (MUG) for emphasising the uniqueness of each segment and excluding the noise interference from the alternate modalities. Specifically, we annotate some of the pseudo-labels based on previous work. Using unimodal pseudo-labels, we perform cross-modal random combinations to generate new data, which can enhance the model's ability to parse various segment-level event combinations. For feature processing and interaction, we employ a audio-visual mamba network. The AV-Mamba enhances the ability to perceive different segments and excludes additional modal noise while sharing similar modal information. Our extensive experiments demonstrate that MUG improves state-of-the-art results on LLP dataset in all metrics (e.g,, gains of 2.1% and 1.2% in terms of visual Segment-level and audio Segment-level metrics). Our code is available at https://github.com/WangLY136/MUG.

comment: Accpted by ICCV 2025

♻ ☆ LM-MCVT: A Lightweight Multi-modal Multi-view Convolutional-Vision Transformer Approach for 3D Object Recognition

Songsong Xiong, Hamidreza Kasaei

♻ ☆ Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning

Haoran Chen, Ping Wang, Zihan Zhou, Xu Zhang, Zuxuan Wu, Yu-Gang Jiang

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with many approaches building upon the framework that maintains a pool of learnable prompts. Although effective, these methods introduce substantial computational overhead, primarily due to prompt pool querying and increased input sequence lengths from prompt concatenation. In this work, we present a novel prompt-based approach that addresses this limitation. Our method trains a single set of shared prompts across all tasks and, rather than concatenating prompts to the input, directly modifies the CLS token's attention computation by adding the prompts to it. This simple and lightweight design not only significantly reduces computational complexity-both in terms of inference costs and the number of trainable parameters-but also eliminates the need to optimize prompt lengths for different downstream tasks, offering a more efficient yet powerful solution for rehearsal-free class-incremental learning. Extensive experiments across a diverse range of CIL benchmarks demonstrate the effectiveness of our approach, highlighting its potential to establish a new prompt-based CIL paradigm. Furthermore, experiments on general recognition benchmarks beyond the CIL setting also show strong performance, positioning our method as a promising candidate for a general parameter-efficient fine-tuning approach.

♻ ☆ OE3DIS: Open-Ended 3D Point Cloud Instance Segmentation

Phuc D. A. Nguyen, Minh Luu, Anh Tran, Cuong Pham, Khoi Nguyen

Open-Vocab 3D Instance Segmentation methods (OV-3DIS) have recently demonstrated their ability to generalize to unseen objects. However, these methods still depend on predefined class names during testing, restricting the autonomy of agents. To mitigate this constraint, we propose a novel problem termed Open-Ended 3D Instance Segmentation (OE-3DIS), which eliminates the necessity for predefined class names during testing. Moreover, we contribute a comprehensive set of strong baselines, derived from OV-3DIS approaches and leveraging 2D Multimodal Large Language Models. To assess the performance of our OE-3DIS system, we introduce a novel Open-Ended score, evaluating both the semantic and geometric quality of predicted masks and their associated class names, alongside the standard AP score. Our approach demonstrates significant performance improvements over the baselines on the ScanNet200 and ScanNet++ datasets. Remarkably, our method surpasses the performance of Open3DIS, the current state-of-the-art method in OV-3DIS, even in the absence of ground-truth object class names.

comment: Accepted at ICCVW'25 - OpenSUN3D: 5th Workshop on Open-World 3D Scene Understanding with Foundation Models

♻ ☆ Un-EVIMO: Unsupervised Event-Based Independent Motion Segmentation

Ziyun Wang, Jinyuan Guo, Kostas Daniilidis

Event cameras are a novel type of biologically inspired vision sensor known for their high temporal resolution, high dynamic range, and low power consumption. Because of these properties, they are well-suited for processing fast motions that require rapid reactions. Although event cameras have recently shown competitive performance in unsupervised optical flow estimation, performance in detecting independently moving objects (IMOs) is lacking behind, although event-based methods would be suited for this task based on their low latency and HDR properties. Previous approaches to event-based IMO segmentation have been heavily dependent on labeled data. However, biological vision systems have developed the ability to avoid moving objects through daily tasks without being given explicit labels. In this work, we propose the first event framework that generates IMO pseudo-labels using geometric constraints. Due to its unsupervised nature, our method can handle an arbitrary number of not predetermined objects and is easily scalable to datasets where expensive IMO labels are not readily available. We evaluate our approach on the EVIMO dataset and show that it performs competitively with supervised methods, both quantitatively and qualitatively.

♻ ☆ 3D Human Mesh Estimation from Single View RGBD

Ozhan Suat, Bedirhan Uguz, Batuhan Karagoz, Muhammed Can Keles, Emre Akbas

Despite significant progress in 3D human mesh estimation from RGB images; RGBD cameras, offering additional depth data, remain underutilized. In this paper, we present a method for accurate 3D human mesh estimation from a single RGBD view, leveraging the affordability and widespread adoption of RGBD cameras for real-world applications. A fully supervised approach for this problem, requires a dataset with RGBD image and 3D mesh label pairs. However, collecting such a dataset is costly and challenging, hence, existing datasets are small, and limited in pose and shape diversity. To overcome this data scarcity, we leverage existing Motion Capture (MoCap) datasets. We first obtain complete 3D meshes from the body models found in MoCap datasets, and create partial, single-view versions of them by projection to a virtual camera. This simulates the depth data provided by an RGBD camera from a single viewpoint. Then, we train a masked autoencoder to complete the partial, single-view mesh. During inference, our method, which we name as M$^3$ for ``Masked Mesh Modeling'', matches the depth values coming from the sensor to vertices of a template human mesh, which creates a partial, single-view mesh. We effectively recover parts of the 3D human body mesh model that are not visible, resulting in a full body mesh. M$^3$ achieves 16.8 mm and 22.0 mm per-vertex-error (PVE) on the SURREAL and CAPE datasets, respectively; outperforming existing methods that use full-body point clouds as input. We obtain a competitive 70.9 PVE on the BEHAVE dataset, outperforming a recently published RGB based method by 18.4 mm, highlighting the usefulness of depth data. Code will be released.

♻ ☆ From Lab to Field: Real-World Evaluation of an AI-Driven Smart Video Solution to Enhance Community Safety

Shanle Yao, Babak Rahimi Ardabili, Armin Danesh Pazho, Ghazal Alinezhad Noghre, Christopher Neff, Lauren Bourque, Hamed Tabkhi

This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera networks, leveraging recent advancements in AI for easy adoption. Prioritizing privacy and ethical standards, pose based data is used for downstream AI tasks such as anomaly detection. Cloud-based infrastructure and mobile app are deployed, enabling real-time alerts within communities. The SVS employs innovative data representation and visualization techniques, such as the Occupancy Indicator, Statistical Anomaly Detection, Bird's Eye View, and Heatmaps, to understand pedestrian behaviors and enhance public safety. Evaluation of the SVS demonstrates its capacity to convert complex computer vision outputs into actionable insights for stakeholders, community partners, law enforcement, urban planners, and social scientists. This article presents a comprehensive real-world deployment and evaluation of the SVS, implemented in a community college environment across 16 cameras. The system integrates AI-driven visual processing, supported by statistical analysis, database management, cloud communication, and user notifications. Additionally, the article evaluates the end-to-end latency from the moment an AI algorithm detects anomalous behavior in real-time at the camera level to the time stakeholders receive a notification. The results demonstrate the system's robustness, effectively managing 16 CCTV cameras with a consistent throughput of 16.5 frames per second (FPS) over a 21-hour period and an average end-to-end latency of 26.76 seconds between anomaly detection and alert issuance.

♻ ☆ TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation

Victor Shea-Jay Huang, Le Zhuo, Yi Xin, Zhaokai Wang, Fu-Yun Wang, Yuchi Wang, Renrui Zhang, Peng Gao, Hongsheng Li

Diffusion Transformers (DiTs) are a powerful yet underexplored class of generative models compared to U-Net-based diffusion architectures. We propose TIDE-Temporal-aware sparse autoencoders for Interpretable Diffusion transformErs-a framework designed to extract sparse, interpretable activation features across timesteps in DiTs. TIDE effectively captures temporally-varying representations and reveals that DiTs naturally learn hierarchical semantics (e.g., 3D structure, object class, and fine-grained concepts) during large-scale pretraining. Experiments show that TIDE enhances interpretability and controllability while maintaining reasonable generation quality, enabling applications such as safe image editing and style transfer.

♻ ☆ SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

Zeyi Sun, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, Jiaqi Wang

Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software, particularly in scenarios lacking human annotations. To address this challenge, we propose SEAgent, an agentic self-evolving framework enabling CUAs to autonomously evolve through interactions with unfamiliar software. Specifically, SEAgent empowers computer-use agents to autonomously master novel software environments via experiential learning, where agents explore new software, learn through iterative trial-and-error, and progressively tackle auto-generated tasks organized from simple to complex. To achieve this goal, we design a World State Model for step-wise trajectory assessment, along with a Curriculum Generator that generates increasingly diverse and challenging tasks. The agent's policy is updated through experiential learning, comprised of adversarial imitation of failure actions and Group Relative Policy Optimization (GRPO) on successful ones. Furthermore, we introduce a specialist-to-generalist training strategy that integrates individual experiential insights from specialist agents, facilitating the development of a stronger generalist CUA capable of continuous autonomous evolution. This unified agent ultimately achieves performance surpassing ensembles of individual specialist agents on their specialized software. We validate the effectiveness of SEAgent across five novel software environments within OS-World. Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA, i.e., UI-TARS.

comment: Code at https://github.com/SunzeY/SEAgent

♻ ☆ HiMat: DiT-based Ultra-High Resolution SVBRDF Generation

Zixiong Wang, Jian Yang, Yiwei Hu, Milos Hasan, Beibei Wang

Creating highly detailed SVBRDFs is essential for 3D content creation. The rise of high-resolution text-to-image generative models, based on diffusion transformers (DiT), suggests an opportunity to finetune them for this task. However, retargeting the models to produce multiple aligned SVBRDF maps instead of just RGB images, while achieving high efficiency and ensuring consistency across different maps, remains a challenge. In this paper, we introduce HiMat: a memory- and computation-efficient diffusion-based framework capable of generating native 4K-resolution SVBRDFs. A key challenge we address is maintaining consistency across different maps in a lightweight manner, without relying on training new VAEs or significantly altering the DiT backbone (which would damage its prior capabilities). To tackle this, we introduce the CrossStitch module, a lightweight convolutional module that captures inter-map dependencies through localized operations. Its weights are initialized such that the DiT backbone operation is unchanged before finetuning starts. HiMat enables generation with strong structural coherence and high-frequency details. Results with a large set of text prompts demonstrate the effectiveness of our approach for 4K SVBRDF generation. Further experiments suggest generalization to tasks such as intrinsic decomposition.

♻ ☆ GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving

Jian Wang, Chaokang Jiang, Haitao Xu

Diffusion-based models are redefining the state-of-the-art in end-to-end autonomous driving, yet their performance is increasingly hampered by a reliance on transformer-based fusion. These architectures face fundamental limitations: quadratic computational complexity restricts the use of high-resolution features, and a lack of spatial priors prevents them from effectively modeling the inherent structure of Bird's Eye View (BEV) representations. This paper introduces GMF-Drive (Gated Mamba Fusion for Driving), an end-to-end framework that overcomes these challenges through two principled innovations. First, we supersede the information-limited histogram-based LiDAR representation with a geometrically-augmented pillar format encoding shape descriptors and statistical features, preserving critical 3D geometric details. Second, we propose a novel hierarchical gated mamba fusion (GM-Fusion) architecture that substitutes an expensive transformer with a highly efficient, spatially-aware state-space model (SSM). Our core BEV-SSM leverages directional sequencing and adaptive fusion mechanisms to capture long-range dependencies with linear complexity, while explicitly respecting the unique spatial properties of the driving scene. Extensive experiments on the challenging NAVSIM benchmark demonstrate that GMF-Drive achieves a new state-of-the-art performance, significantly outperforming DiffusionDrive. Comprehensive ablation studies validate the efficacy of each component, demonstrating that task-specific SSMs can surpass a general-purpose transformer in both performance and efficiency for autonomous driving.

comment: 7 pages, 4 figures

♻ ☆ Understanding Dynamic Scenes in Ego Centric 4D Point Clouds

Junsheng Huang, Shengyu Hao, Bocheng Hu, Gaoang Wang

Understanding dynamic 4D scenes from an egocentric perspective-modeling changes in 3D spatial structure over time-is crucial for human-machine interaction, autonomous navigation, and embodied intelligence. While existing egocentric datasets contain dynamic scenes, they lack unified 4D annotations and task-driven evaluation protocols for fine-grained spatio-temporal reasoning, especially on motion of objects and human, together with their interactions. To address this gap, we introduce EgoDynamic4D, a novel QA benchmark on highly dynamic scenes, comprising RGB-D video, camera poses, globally unique instance masks, and 4D bounding boxes. We construct 927K QA pairs accompanied by explicit Chain-of-Thought (CoT), enabling verifiable, step-by-step spatio-temporal reasoning. We design 12 dynamic QA tasks covering agent motion, human-object interaction, trajectory prediction, relation understanding, and temporal-causal reasoning, with fine-grained, multidimensional metrics. To tackle these tasks, we propose an end-to-end spatio-temporal reasoning framework that unifies dynamic and static scene information, using instance-aware feature encoding, time and camera encoding, and spatially adaptive down-sampling to compress large 4D scenes into token sequences manageable by LLMs. Experiments on EgoDynamic4D show that our method consistently outperforms baselines, validating the effectiveness of multimodal temporal modeling for egocentric dynamic scene understanding.

♻ ☆ Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation

Qiao Yu, Xianzhi Li, Yuan Tang, Xu Han, Long Hu, Yixue Hao, Min Chen

Generating 3D meshes from a single image is an important but ill-posed task. Existing methods mainly adopt 2D multiview diffusion models to generate intermediate multiview images, and use the Large Reconstruction Model (LRM) to create the final meshes. However, the multiview images exhibit local inconsistencies, and the meshes often lack fidelity to the input image or look blurry. We propose Fancy123, featuring two enhancement modules and an unprojection operation to address the above three issues, respectively. The appearance enhancement module deforms the 2D multiview images to realign misaligned pixels for better multiview consistency. The fidelity enhancement module deforms the 3D mesh to match the input image. The unprojection of the input image and deformed multiview images onto LRM's generated mesh ensures high clarity, discarding LRM's predicted blurry-looking mesh colors. Extensive qualitative and quantitative experiments verify Fancy123's SoTA performance with significant improvement. Also, the two enhancement modules are plug-and-play and work at inference time, allowing seamless integration into various existing single-image-to-3D methods. Code at: https://github.com/YuQiao0303/Fancy123

comment: CVPR2025

♻ ☆ OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions

Maxim Popov, Regina Kurkova, Mikhail Iumanov, Jaafar Mahmoud, Sergey Kolyubin

Open Semantic Mapping (OSM) is a key technology in robotic perception, combining semantic segmentation and SLAM techniques. This paper introduces a dynamically configurable and highly automated LLM/LVLM-powered pipeline for evaluating OSM solutions called OSMa-Bench (Open Semantic Mapping Benchmark). The study focuses on evaluating state-of-the-art semantic mapping algorithms under varying indoor lighting conditions, a critical challenge in indoor environments. We introduce a novel dataset with simulated RGB-D sequences and ground truth 3D reconstructions, facilitating the rigorous analysis of mapping performance across different lighting conditions. Through experiments on leading models such as ConceptGraphs, BBQ and OpenScene, we evaluate the semantic fidelity of object recognition and segmentation. Additionally, we introduce a Scene Graph evaluation method to analyze the ability of models to interpret semantic structure. The results provide insights into the robustness of these models, forming future research directions for developing resilient and adaptable robotic systems. Project page is available at https://be2rlab.github.io/OSMa-Bench/.

comment: Project page: https://be2rlab.github.io/OSMa-Bench/

♻ ☆ LayLens: Improving Deepfake Understanding through Simplified Explanations

Abhijeet Narang, Parul Gupta, Liuyijia Su, Abhinav Dhall

This demonstration paper presents $\mathbf{LayLens}$, a tool aimed to make deepfake understanding easier for users of all educational backgrounds. While prior works often rely on outputs containing technical jargon, LayLens bridges the gap between model reasoning and human understanding through a three-stage pipeline: (1) explainable deepfake detection using a state-of-the-art forgery localization model, (2) natural language simplification of technical explanations using a vision-language model, and (3) visual reconstruction of a plausible original image via guided image editing. The interface presents both technical and layperson-friendly explanations in addition to a side-by-side comparison of the uploaded and reconstructed images. A user study with 15 participants shows that simplified explanations significantly improve clarity and reduce cognitive load, with most users expressing increased confidence in identifying deepfakes. LayLens offers a step toward transparent, trustworthy, and user-centric deepfake forensics.

comment: Accepted to ACM ICMI 2025 Demos

♻ ☆ SCB-Dataset: A Dataset for Detecting Student and Teacher Classroom Behavior

Fan Yang

Using deep learning methods to detect the classroom behaviors of both students and teachers is an effective way to automatically analyze classroom performance and enhance teaching effectiveness. Then, there is still a scarcity of publicly available high-quality datasets on student-teacher behaviors. We constructed SCB-Dataset a comprehensive dataset of student and teacher classroom behaviors covering 19 classes. SCB-Dataset is divided into two types: Object Detection and Image Classification. The Object Detection part includes 13,330 images and 122,977 labels, and the Image Classification part includes 21,019 images. We conducted benchmark tests on SCB-Dataset using YOLO series algorithms and Large vision-language model. We believe that SCB-Dataset can provide a solid foundation for future applications of artificial intelligence in education. Code:https://github.com/Whiffe/SCB-dataset

♻ ☆ 3DFacePolicy: Audio-Driven 3D Facial Animation Based on Action Control

Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita, Naoya Chiba, Yuki Uranishi

♻ ☆ Learning to Harmonize Cross-vendor X-ray Images by Non-linear Image Dynamics Correction

Yucheng Lu, Shunxin Wang, Dovile Juodelyte, Veronika Cheplygina

In this paper, we explore how conventional image enhancement can improve model robustness in medical image analysis. By applying commonly used normalization methods to images from various vendors and studying their influence on model generalization in transfer learning, we show that the nonlinear characteristics of domain-specific image dynamics cannot be addressed by simple linear transforms. To tackle this issue, we reformulate the image harmonization task as an exposure correction problem and propose a method termed Global Deep Curve Estimation (GDCE) to reduce domain-specific exposure mismatch. GDCE performs enhancement via a pre-defined polynomial function and is trained with a "domain discriminator", aiming to improve model transparency in downstream tasks compared to existing black-box methods.

♻ ☆ How Does Bilateral Ear Symmetry Affect Deep Ear Features?

Kagan Ozturk, Deeksha Arun, Kevin W. Bowyer, Patrick Flynn

Ear recognition has gained attention as a reliable biometric technique due to the distinctive characteristics of human ears. With the increasing availability of large-scale datasets, convolutional neural networks (CNNs) have been widely adopted to learn features directly from raw ear images, outperforming traditional hand-crafted methods. However, the effect of bilateral ear symmetry on the features learned by CNNs has received little attention in recent studies. In this paper, we investigate how bilateral ear symmetry influences the effectiveness of CNN-based ear recognition. To this end, we first develop an ear side classifier to automatically categorize ear images as either left or right. We then explore the impact of incorporating this side information during both training and test. Cross-dataset evaluations are conducted on five datasets. Our results suggest that treating left and right ears separately during training and testing can lead to notable performance improvements. Furthermore, our ablation studies on alignment strategies, input sizes, and various hyperparameter settings provide practical insights into training CNN-based ear recognition systems on large-scale datasets to achieve higher verification rates.

♻ ☆ See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question Answering

Junjie Wang, Yunhan Tang, Yijie Wang, Zhihao Yuan, Huan Wang, Yangfan He, Bin Li

comment: Paper withdrawn by authors. A critical bug in our data processing script (process_data.py, line 152) caused an incorrect indexing operation, leading to systematic data omission. This error invalidates the performance benchmarks in Table 2 and the conclusions, leaving the paper's central claim unsupported. We apologize to the research community for this error

♻ ☆ Multiple Stochastic Prompt Tuning for Few-shot Adaptation under Extreme Domain Shift

Debarshi Brahma, Soma Biswas

Foundation Vision-Language Models (VLMs) like CLIP exhibit strong generalization capabilities due to large-scale pretraining on diverse image-text pairs. However, their performance often degrades when applied to target datasets with significant distribution shifts in both visual appearance and class semantics. Recent few-shot learning approaches adapt CLIP to downstream tasks using limited labeled data via adapter or prompt tuning, but are not specifically designed to handle such extreme domain shifts. Conversely, some works addressing cross-domain few-shot learning consider such domain-shifted scenarios but operate in an episodic setting with only a few classes per episode, limiting their applicability to real-world deployment, where all classes must be handled simultaneously. To address this gap, we propose a novel framework, MIST (Multiple Stochastic Prompt Tuning), for efficiently adapting CLIP to datasets with extreme distribution shifts using only a few labeled examples, in scenarios involving all classes at once. Specifically, we introduce multiple learnable prompts per class to effectively capture diverse modes in visual representations arising from distribution shifts. To further enhance generalization, these prompts are modeled as learnable Gaussian distributions, enabling efficient exploration of the prompt parameter space and reducing overfitting caused by limited supervision. Extensive experiments and comparisons with state-of-the-art methods demonstrate the effectiveness of the proposed framework.

♻ ☆ PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloud

Qiao Yu, Xianzhi Li, Yuan Tang, Xu Han, Jinfeng Xu, Long Hu, Min Chen

Faithfully reconstructing textured meshes is crucial for many applications. Compared to text or image modalities, leveraging 3D colored point clouds as input (colored-PC-to-mesh) offers inherent advantages in comprehensively and precisely replicating the target object's 360{\deg} characteristics. While most existing colored-PC-to-mesh methods suffer from blurry textures or require hard-to-acquire 3D training data, we propose PointDreamer, a novel framework that harnesses 2D diffusion prior for superior texture quality. Crucially, unlike prior 2D-diffusion-for-3D works driven by text or image inputs, PointDreamer successfully adapts 2D diffusion models to 3D point cloud data by a novel project-inpaint-unproject pipeline. Specifically, it first projects the point cloud into sparse 2D images and then performs diffusion-based inpainting. After that, diverging from most existing 3D reconstruction or generation approaches that predict texture in 3D/UV space thus often yielding blurry texture, PointDreamer achieves high-quality texture by directly unprojecting the inpainted 2D images to the 3D mesh. Furthermore, we identify for the first time a typical kind of unprojection artifact appearing in occlusion borders, which is common in other multiview-image-to-3D pipelines but less-explored. To address this, we propose a novel solution named the Non-Border-First (NBF) unprojection strategy. Extensive qualitative and quantitative experiments on various synthetic and real-scanned datasets demonstrate that PointDreamer, though zero-shot, exhibits SoTA performance (30% improvement on LPIPS score from 0.118 to 0.068), and is robust to noisy, sparse, or even incomplete input data. Code at: https://github.com/YuQiao0303/PointDreamer.

♻ ☆ Cut2Next: Generating Next Shot via In-Context Tuning

Jingwen He, Hongbo Liu, Jiajun Li, Ziqi Huang, Yu Qiao, Wanli Ouyang, Ziwei Liu

Effective multi-shot generation demands purposeful, film-like transitions and strict cinematic continuity. Current methods, however, often prioritize basic visual consistency, neglecting crucial editing patterns (e.g., shot/reverse shot, cutaways) that drive narrative flow for compelling storytelling. This yields outputs that may be visually coherent but lack narrative sophistication and true cinematic integrity. To bridge this, we introduce Next Shot Generation (NSG): synthesizing a subsequent, high-quality shot that critically conforms to professional editing patterns while upholding rigorous cinematic continuity. Our framework, Cut2Next, leverages a Diffusion Transformer (DiT). It employs in-context tuning guided by a novel Hierarchical Multi-Prompting strategy. This strategy uses Relational Prompts to define overall context and inter-shot editing styles. Individual Prompts then specify per-shot content and cinematographic attributes. Together, these guide Cut2Next to generate cinematically appropriate next shots. Architectural innovations, Context-Aware Condition Injection (CACI) and Hierarchical Attention Mask (HAM), further integrate these diverse signals without introducing new parameters. We construct RawCuts (large-scale) and CuratedCuts (refined) datasets, both with hierarchical prompts, and introduce CutBench for evaluation. Experiments show Cut2Next excels in visual consistency and text fidelity. Crucially, user studies reveal a strong preference for Cut2Next, particularly for its adherence to intended editing patterns and overall cinematic continuity, validating its ability to generate high-quality, narratively expressive, and cinematically coherent subsequent shots.

♻ ☆ UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI

Fangwei Zhong, Kui Wu, Churan Wang, Hao Chen, Hai Ci, Zhoujun Li, Yizhou Wang

We introduce UnrealZoo, a collection of over 100 photo-realistic 3D virtual worlds built on Unreal Engine, designed to reflect the complexity and variability of open-world environments. We also provide a rich variety of playable entities, including humans, animals, robots, and vehicles for embodied AI research. We extend UnrealCV with optimized APIs and tools for data collection, environment augmentation, distributed training, and benchmarking. These improvements achieve significant improvements in the efficiency of rendering and communication, enabling advanced applications such as multi-agent interactions. Our experimental evaluation across visual navigation and tracking tasks reveals two key insights: 1) environmental diversity provides substantial benefits for developing generalizable reinforcement learning (RL) agents, and 2) current embodied agents face persistent challenges in open-world scenarios, including navigation in unstructured terrain, adaptation to unseen morphologies, and managing latency in the close-loop control systems for interacting in highly dynamic objects. UnrealZoo thus serves as both a comprehensive testing ground and a pathway toward developing more capable embodied AI systems for real-world deployment.

comment: ICCV 2025 (Highlight), Project page: http://unrealzoo.site/

♻ ☆ PAD-F: Prior-Aware Debiasing Framework for Long-Tailed X-ray Prohibited Item Detection

Haoyu Wang, Renshuai Tao, Wei Wang, Yunchao Wei

Detecting prohibited items in X-ray security imagery is a challenging yet crucial task. With the rapid advancement of deep learning, object detection algorithms have been widely applied in this area. However, the distribution of object classes in real-world prohibited item detection scenarios often exhibits a distinct long-tailed distribution. Due to the unique principles of X-ray imaging, conventional methods for long-tailed object detection are often ineffective in this domain. To tackle these challenges, we introduce the Prior-Aware Debiasing Framework (PAD-F), a novel approach that employs a two-pronged strategy leveraging both material and co-occurrence priors. At the data level, our Explicit Material-Aware Augmentation (EMAA) component generates numerous challenging training samples for tail classes. It achieves this through a placement strategy guided by material-specific absorption rates and a gradient-based Poisson blending technique. At the feature level, the Implicit Co-occurrence Aggregator (ICA) acts as a plug-in module that enhances features for ambiguous objects by implicitly learning and aggregating statistical co-occurrence relationships within the image. Extensive experiments on the HiXray and PIDray datasets demonstrate that PAD-F significantly boosts the performance of multiple popular detectors. It achieves an absolute improvement of up to +17.2% in AP50 for tail classes and comprehensively outperforms existing state-of-the-art methods. Our work provides an effective and versatile solution to the critical problem of long-tailed detection in X-ray security.

comment: 9 pages, 5 figures

♻ ☆ Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction

Xudong Cai, Shuo Wang, Peng Wang, Yongcai Wang, Zhaoxin Fan, Wanting Li, Tianbao Zhang, Jianrong Tao, Yeying Jin, Deying Li

Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but they fundamentally suffer from a Memory Demand Dilemma: The memory representation faces an inherent conflict between the long-term stability required for static structures and the rapid, high-fidelity detail retention needed for dynamic motion. This conflict forces existing methods into a compromise, leading to either geometric drift in static structures or blurred, inaccurate reconstructions of dynamic objects. To address this dilemma, we propose Mem4D, a novel framework that decouples the modeling of static geometry and dynamic motion. Guided by this insight, we design a dual-memory architecture: 1) The Transient Dynamics Memory (TDM) focuses on capturing high-frequency motion details from recent frames, enabling accurate and fine-grained modeling of dynamic content; 2) The Persistent Structure Memory (PSM) compresses and preserves long-term spatial information, ensuring global consistency and drift-free reconstruction for static elements. By alternating queries to these specialized memories, Mem4D simultaneously maintains static geometry with global consistency and reconstructs dynamic elements with high fidelity. Experiments on challenging benchmarks demonstrate that our method achieves state-of-the-art or competitive performance while maintaining high efficiency. Codes will be publicly available.

♻ ☆ Efficient Annotation of Medieval Charters

Anguelos Nicolaou, Daniel Luger, Franziska Decker, Nicolas Renet, Vincent Christlein, Georg Vogeler

Diplomatics, the analysis of medieval charters, is a major field of research in which paleography is applied. Annotating data, if performed by laymen, needs validation and correction by experts. In this paper, we propose an effective and efficient annotation approach for charter segmentation, essentially reducing it to object detection. This approach allows for a much more efficient use of the paleographer's time and produces results that can compete and even outperform pixel-level segmentation in some use cases. Further experiments shed light on how to design a class ontology in order to make the best use of annotators' time and effort. Exploiting the presence of calibration cards in the image, we further annotate the data with the physical length in pixels and train regression neural networks to predict it from image patches.

♻ ☆ Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics

Nikolai Röhrich, Alwin Hoffmann, Richard Nordsieck, Emilio Zarbali, Alireza Javanmardi

While transformers have surpassed convolutional neural networks (CNNs) in various computer vision tasks, microelectronics defect detection still largely relies on CNNs. We hypothesize that this gap is due to the fact that a) transformers have an increased need for data and b) (labelled) image generation procedures for microelectronics are costly, and data is therefore sparse. Whereas in other domains, pre-training on large natural image datasets can mitigate this problem, in microelectronics transfer learning is hindered due to the dissimilarity of domain data and natural images. We address this challenge through self pre-training, where models are pre-trained directly on the target dataset, rather than another dataset. We propose a resource-efficient vision transformer (ViT) pre-training framework for defect detection in microelectronics based on masked autoencoders (MAE). We perform pre-training and defect detection using a dataset of less than 10,000 scanning acoustic microscopy (SAM) images. Our experimental results show that our approach leads to substantial performance gains compared to a) supervised ViT, b) ViT pre-trained on natural image datasets, and c) state-of-the-art CNN-based defect detection models used in microelectronics. Additionally, interpretability analysis reveals that our self pre-trained models attend to defect-relevant features such as cracks in the solder material, while baseline models often attend to spurious patterns. This shows that our approach yields defect-specific feature representations, resulting in more interpretable and generalizable transformer models for this data-sparse domain.

comment: 16 pages, 5 figures

♻ ☆ HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition

Suhan Woo, Seongwon Lee, Jinwoo Jang, Euntai Kim

When applying Visual Place Recognition (VPR) to real-world mobile robots and similar applications, perspective-to-equirectangular (P2E) formulation naturally emerges as a suitable approach to accommodate diverse query images captured from various viewpoints. In this paper, we introduce HypeVPR, a novel hierarchical embedding framework in hyperbolic space, designed to address the unique challenges of P2E VPR. The key idea behind HypeVPR is that visual environments captured by panoramic views exhibit inherent hierarchical structures. To leverage this property, we employ hyperbolic space to represent hierarchical feature relationships and preserve distance properties within the feature space. To achieve this, we propose a hierarchical feature aggregation mechanism that organizes local-to-global feature representations within hyperbolic space. Additionally, HypeVPR adopts an efficient coarse-to-fine search strategy to enable flexible control over accuracy-efficiency trade-offs and ensure robust matching even between descriptors from different image types. This approach allows HypeVPR to outperform existing methods while significantly accelerating retrieval and reducing database storage requirements. The code and models will be released at https://github.com/suhan-woo/HypeVPR.git.

♻ ☆ Context-based Motion Retrieval using Open Vocabulary Methods for Autonomous Driving

Stefan Englmeier, Max A. Büttner, Katharina Winter, Fabian B. Flohr

Autonomous driving systems must operate reliably in safety-critical scenarios, particularly those involving unusual or complex behavior by Vulnerable Road Users (VRUs). Identifying these edge cases in driving datasets is essential for robust evaluation and generalization, but retrieving such rare human behavior scenarios within the long tail of large-scale datasets is challenging. To support targeted evaluation of autonomous driving systems in diverse, human-centered scenarios, we propose a novel context-aware motion retrieval framework. Our method combines Skinned Multi-Person Linear (SMPL)-based motion sequences and corresponding video frames before encoding them into a shared multimodal embedding space aligned with natural language. Our approach enables the scalable retrieval of human behavior and their context through text queries. This work also introduces our dataset WayMoCo, an extension of the Waymo Open Dataset. It contains automatically labeled motion and scene context descriptions derived from generated pseudo-ground-truth SMPL sequences and corresponding image data. Our approach outperforms state-of-the-art models by up to 27.5% accuracy in motion-context retrieval, when evaluated on the WayMoCo dataset.

comment: Project page: https://iv.ee.hm.edu/contextmotionclip/; This work has been submitted to the IEEE for possible publication

♻ ☆ Style transfer between Microscopy and Magnetic Resonance Imaging via Generative Adversarial Network in small sample size settings

Monika Pytlarz, Adrian Onicas, Alessandro Crimi

Cross-modal augmentation of Magnetic Resonance Imaging (MRI) and microscopic imaging based on the same tissue samples is promising because it can allow histopathological analysis in the absence of an underlying invasive biopsy procedure. Here, we tested a method for generating microscopic histological images from MRI scans of the human corpus callosum using conditional generative adversarial network (cGAN) architecture. To our knowledge, this is the first multimodal translation of the brain MRI to histological volumetric representation of the same sample. The technique was assessed by training paired image translation models taking sets of images from MRI scans and microscopy. The use of cGAN for this purpose is challenging because microscopy images are large in size and typically have low sample availability. The current work demonstrates that the framework reliably synthesizes histology images from MRI scans of corpus callosum, emphasizing the network's ability to train on high resolution histologies paired with relatively lower-resolution MRI scans. With the ultimate goal of avoiding biopsies, the proposed tool can be used for educational purposes.

comment: 2023 IEEE International Conference on Image Processing (ICIP)

♻ ☆ When Imitation Learning Outperforms Reinforcement Learning in Surgical Action Planning

Maxence Boels, Harry Robertshaw, Thomas C Booth, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin

Surgical action planning requires predicting future instrument-verb-target triplets for real-time assistance. While teleoperated robotic surgery provides natural expert demonstrations for imitation learning (IL), reinforcement learning (RL) could potentially discover superior strategies through exploration. We present the first comprehensive comparison of IL versus RL for surgical action planning on CholecT50. Our Dual-task Autoregressive Imitation Learning (DARIL) baseline achieves 34.6% action triplet recognition mAP and 33.6% next frame prediction mAP with smooth planning degradation to 29.2% at 10-second horizons. We evaluated three RL variants: world model-based RL, direct video RL, and inverse RL enhancement. Surprisingly, all RL approaches underperformed DARIL i.e. world model RL dropped to 3.1% mAP at 10s while direct video RL achieved only 15.9%. Our analysis reveals that distribution matching on expert-annotated test sets systematically favors IL over potentially valid RL policies that differ from training demonstrations. This challenges assumptions about RL superiority in sequential decision making and provides crucial insights for surgical AI development.

comment: Paper accepted at the MICCAI2025 workshop proceedings on COLlaborative Intelligence and Autonomy in Image-guided Surgery (COLAS)

♻ ☆ Multi-Keypoint Affordance Representation for Functional Dexterous Grasping

Fan Yang, Dongsheng Luo, Wenrui Chen, Jiacheng Lin, Junjie Cai, Kailun Yang, Zhiyong Li, Yaonan Wang

Functional dexterous grasping requires precise hand-object interaction, going beyond simple gripping. Existing affordance-based methods primarily predict coarse interaction regions and cannot directly constrain the grasping posture, leading to a disconnection between visual perception and manipulation. To address this issue, we propose a multi-keypoint affordance representation for functional dexterous grasping, which directly encodes task-driven grasp configurations by localizing functional contact points. Our method introduces Contact-guided Multi-Keypoint Affordance (CMKA), leveraging human grasping experience images for weak supervision combined with Large Vision Models for fine affordance feature extraction, achieving generalization while avoiding manual keypoint annotations. Additionally, we present a Keypoint-based Grasp matrix Transformation (KGT) method, ensuring spatial consistency between hand keypoints and object contact points, thus providing a direct link between visual perception and dexterous grasping actions. Experiments on public real-world FAH datasets, IsaacGym simulation, and challenging robotic tasks demonstrate that our method significantly improves affordance localization accuracy, grasp consistency, and generalization to unseen tools and tasks, bridging the gap between visual affordance learning and dexterous robotic manipulation. The source code and demo videos are publicly available at https://github.com/PopeyePxx/MKA.

comment: Accepted to IEEE Robotics and Automation Letters (RA-L). The source code and demo videos are publicly available at https://github.com/PopeyePxx/MKA

♻ ☆ SSPFusion: A Semantic Structure-Preserving Approach for Infrared and Visible Image Fusion

Qiao Yang, Yu Zhang, Yutong Chen, Jian Zhang, Shunli Zhang

Most existing learning-based multi-modality image fusion (MMIF) methods suffer from significant structure inconsistency due to their inappropriate usage of structural features at the semantic level. To alleviate these issues, we propose a semantic structure-preserving fusion approach for MMIF, namely SSPFusion. At first, we design a structural feature extractor (SFE) to extract the prominent structural features from multiple input images. Concurrently, we introduce a transformation function with Sobel operator to generate self-supervised structural signals in these extracted features. Subsequently, we design a multi-scale structure-preserving fusion (SPF) module, guided by the generated structural signals, to merge the structural features of input images. This process ensures the preservation of semantic structure consistency between the resultant fusion image and the input images. Through the synergy of these two robust modules of SFE and SPF, our method can generate high-quality fusion images and demonstrate good generalization ability. Experimental results, on both infrared-visible image fusion and medical image fusion tasks, demonstrate that our method outperforms nine state-of-the-art methods in terms of both qualitative and quantitative evaluations. The code is publicly available at https://github.com/QiaoYang-CV/SSPFUSION.

comment: Accepted by Expert Systems with Applications (ESWA)

♻ ☆ Adversarial Video Promotion Against Text-to-Video Retrieval

Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Qian Li, Shuai Liu, Chao Shen

Thanks to the development of cross-modal models, text-to-video retrieval (T2VR) is advancing rapidly, but its robustness remains largely unexamined. Existing attacks against T2VR are designed to push videos away from queries, i.e., suppressing the ranks of videos, while the attacks that pull videos towards selected queries, i.e., promoting the ranks of videos, remain largely unexplored. These attacks can be more impactful as attackers may gain more views/clicks for financial benefits and widespread (mis)information. To this end, we pioneer the first attack against T2VR to promote videos adversarially, dubbed the Video Promotion attack (ViPro). We further propose Modal Refinement (MoRe) to capture the finer-grained, intricate interaction between visual and textual modalities to enhance black-box transferability. Comprehensive experiments cover 2 existing baselines, 3 leading T2VR models, 3 prevailing datasets with over 10k videos, evaluated under 3 scenarios. All experiments are conducted in a multi-target setting to reflect realistic scenarios where attackers seek to promote the video regarding multiple queries simultaneously. We also evaluated our attacks for defences and imperceptibility. Overall, ViPro surpasses other baselines by over $30/10/4\%$ for white/grey/black-box settings on average. Our work highlights an overlooked vulnerability, provides a qualitative analysis on the upper/lower bound of our attacks, and offers insights into potential counterplays. Code will be publicly available at https://github.com/michaeltian108/ViPro.

♻ ☆ Unsupervised Document and Template Clustering using Multimodal Embeddings

Phillipe R. Sampaio, Helene Maxcici

This paper investigates a novel approach to unsupervised document clustering by leveraging multimodal embeddings as input to clustering algorithms such as $k$-Means, DBSCAN, a combination of HDBSCAN and $k$-NN, and BIRCH. Our method aims to achieve a finer-grained document understanding by not only grouping documents at the type level (e.g., invoices, purchase orders), but also distinguishing between different templates within the same document category. This is achieved by using embeddings that capture textual content, layout information, and visual features of documents. We evaluated the effectiveness of this approach using embeddings generated by several state-of-the-art pre-trained multimodal models, including SBERT, LayoutLMv1, LayoutLMv3, DiT, Donut, ColPali, Gemma3, and InternVL3. Our findings demonstrate the potential of multimodal embeddings to significantly enhance document clustering, offering benefits for various applications in intelligent document processing, document layout analysis, and unsupervised document classification. This work provides valuable insight into the advantages and limitations of different multimodal models for this task and opens new avenues for future research to understand and organize document collections.

comment: 22 pages, 12 figures

♻ ☆ From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models

Yuying Shang, Xinyi Zeng, Yutao Zhu, Xiao Yang, Zhengwei Fang, Jingyuan Zhang, Jiawei Chen, Zinan Liu, Yu Tian

Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to effectively extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (feature decoupling). Motivated by our findings on the preliminary investigation, we propose a novel tuning strategy, PATCH, to mitigate hallucinations in LVLMs. This plug-and-play method can be integrated into various LVLMs, utilizing adaptive virtual tokens to extract object features from bounding boxes, thereby addressing hallucinations caused by insufficient decoupling of visual features. PATCH achieves state-of-the-art performance on multiple multi-modal hallucination datasets. We hope this approach provides researchers with deeper insights into the underlying causes of hallucinations in LVLMs, fostering further advancements and innovation in this field.

♻ ☆ PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations

Md Rakibul Hasan, Pouria Behnoudfar, Dan MacKinlay, Thomas Poulet

Machine Learning, particularly Generative Adversarial Networks (GANs), has revolutionised Super-Resolution (SR). However, generated images often lack physical meaningfulness, which is essential for scientific applications. Our approach, PC-SRGAN, enhances image resolution while ensuring physical consistency for interpretable simulations. PC-SRGAN significantly improves both the Peak Signal-to-Noise Ratio and the Structural Similarity Index Measure compared to conventional SR methods, even with limited training data (e.g., only 13% of training data is required to achieve performance similar to SRGAN). Beyond SR, PC-SRGAN augments physically meaningful machine learning, incorporating numerically justified time integrators and advanced quality metrics. These advancements promise reliable and causal machine-learning models in scientific domains. A significant advantage of PC-SRGAN over conventional SR techniques is its physical consistency, which makes it a viable surrogate model for time-dependent problems. PC-SRGAN advances scientific machine learning by improving accuracy and efficiency, enhancing process understanding, and broadening applications to scientific research. We publicly release the complete source code of PC-SRGAN and all experiments at https://github.com/hasan-rakibul/PC-SRGAN.

comment: 11 pages, combining the main content and the appendices, unlike having them separated in the published version at IEEE Xplore (https://doi.org/10.1109/TPAMI.2025.3596647)

♻ ☆ Zero-shot Emotion Annotation in Facial Images Using Large Multimodal Models: Benchmarking and Prospects for Multi-Class, Multi-Frame Approaches

He Zhang, Xinyi Fu

This study investigates the feasibility and performance of using large multimodal models (LMMs) to automatically annotate human emotions in everyday scenarios. We conducted experiments on the DailyLife subset of the publicly available FERV39k dataset, employing the GPT-4o-mini model for rapid, zero-shot labeling of key frames extracted from video segments. Under a seven-class emotion taxonomy ("Angry," "Disgust," "Fear," "Happy," "Neutral," "Sad," "Surprise"), the LMM achieved an average precision of approximately 50%. In contrast, when limited to ternary emotion classification (negative/neutral/positive), the average precision increased to approximately 64%. Additionally, we explored a strategy that integrates multiple frames within 1-2 second video clips to enhance labeling performance and reduce costs. The results indicate that this approach can slightly improve annotation accuracy. Overall, our preliminary findings highlight the potential application of zero-shot LMMs in human facial emotion annotation tasks, offering new avenues for reducing labeling costs and broadening the applicability of LMMs in complex multimodal environments.

comment: 10 pages, accepted to MRAC'25: 3rd International Workshop on Multimodal and Responsible Affective Computing (ACM-MM 2025)

♻ ☆ Mjölnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density

Minjong Cheon

Recent advances in AI-based weather forecasting models, such as FourCastNet, Pangu-Weather, and GraphCast, have demonstrated the remarkable ability of deep learning to emulate complex atmospheric dynamics. Building on this momentum, we propose Mj\"olnir, a novel deep learning-based framework for global lightning flash density parameterization. Trained on ERA5 atmospheric predictors and World Wide Lightning Location Network (WWLLN) observations at a daily temporal resolution and 1 degree spatial resolution, Mj\"olnir captures the nonlinear mapping between large-scale environmental conditions and lightning activity. The model architecture is based on the InceptionNeXt backbone with SENet, and a multi-task learning strategy to simultaneously predict lightning occurrence and magnitude. Extensive evaluations yield that Mollnir accurately reproduces the global distribution, seasonal variability, and regional characteristics of lightning activity, achieving a global Pearson correlation coefficient of 0.96 for annual mean fields. These results suggest that Mj\"olnir serves not only as an effective data-driven global lightning parameterization but also as a promising AI-based scheme for next-generation Earth system models (AI-ESMs).

comment: After an internal review, we found that the current version does not meet our intended academic standards due to incomplete descriptions and insufficient detail in key sections. No revised manuscript can be prepared in the near future. To ensure academic quality, we withdraw this version and plan to resubmit when the work is substantially improved

♻ ☆ Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video

Renlong Wu, Zhilu Zhang, Mingyang Chen, Zifei Yan, Wangmeng Zuo

Recent 4D reconstruction methods have yielded impressive results but rely on sharp videos as supervision. However, motion blur often occurs in videos due to camera shake and object movement, while existing methods render blurry results when using such videos for reconstructing 4D models. Although a few approaches attempted to address the problem, they struggled to produce high-quality results, due to the inaccuracy in estimating continuous dynamic representations within the exposure time. Encouraged by recent works in 3D motion trajectory modeling using 3D Gaussian Splatting (3DGS), we take 3DGS as the scene representation manner, and propose Deblur4DGS to reconstruct a high-quality 4D model from blurry monocular video. Specifically, we transform continuous dynamic representations estimation within an exposure time into the exposure time estimation. Moreover, we introduce the exposure regularization term, multi-frame, and multi-resolution consistency regularization term to avoid trivial solutions. Furthermore, to better represent objects with large motion, we suggest blur-aware variable canonical Gaussians. Beyond novel-view synthesis, Deblur4DGS can be applied to improve blurry video from multiple perspectives, including deblurring, frame interpolation, and video stabilization. Extensive experiments in both synthetic and real-world data on the above four tasks show that Deblur4DGS outperforms state-of-the-art 4D reconstruction methods. The codes are available at https://github.com/ZcsrenlongZ/Deblur4DGS.

comment: 16 pages

♻ ☆ RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow

Liang Yao, Fan Liu, Hongbo Lu, Chuanyi Zhang, Rui Min, Shengxiang Xu, Shimin Di, Pai Peng

Remote sensing imagery presents vast, inherently unstructured spatial data, necessitating sophisticated reasoning to interpret complex user intents and contextual relationships beyond simple recognition tasks. In this paper, we aim to construct an Earth observation workflow to handle complex queries by reasoning about spatial context and user intent. As a reasoning workflow, it should autonomously explore and construct its own inference paths, rather than being confined to predefined ground-truth sequences. Ideally, its architecture ought to be unified yet generalized, possessing capabilities to perform diverse reasoning tasks through one model without requiring additional fine-tuning. Existing remote sensing approaches rely on supervised fine-tuning paradigms and task-specific heads, limiting both autonomous reasoning and unified generalization. To this end, we propose RemoteReasoner, a unified workflow for geospatial reasoning. The design of RemoteReasoner integrates a multi-modal large language model (MLLM) for interpreting user instructions and localizing targets, together with task transformation strategies that enable multi-granularity tasks, including object-, region-, and pixel-level. In contrast to existing methods, our framework is trained with reinforcement learning (RL) to endow the MLLM sufficient reasoning autonomy. At the inference stage, our transformation strategies enable diverse task output formats without requiring task-specific decoders or further fine-tuning. Experiments demonstrated that RemoteReasoner achieves state-of-the-art (SOTA) performance across multi-granularity reasoning tasks. Furthermore, it retains the MLLM's inherent generalization capability, demonstrating robust performance on unseen tasks and out-of-distribution categories.

♻ ☆ Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Process

Yuanze Li, Shihao Yuan, Haolin Wang, Qizhang Li, Ming Liu, Chen Xu, Guangming Shi, Wangmeng Zuo

Although recent methods have tried to introduce large multimodal models (LMMs) into industrial anomaly detection (IAD), their generalization in the IAD field is far inferior to that for general purposes. We summarize the main reasons for this gap into two aspects. On one hand, general-purpose LMMs lack cognition of defects in the visual modality, thereby failing to sufficiently focus on defect areas. Therefore, we propose to modify the AnyRes structure of the LLaVA model, providing the potential anomalous areas identified by existing IAD models to the LMMs. On the other hand, existing methods mainly focus on identifying defects by learning defect patterns or comparing with normal samples, yet they fall short of understanding the causes of these defects. Considering that the generation of defects is closely related to the manufacturing process, we propose a manufacturing-driven IAD paradigm. An instruction-tuning dataset for IAD (InstructIAD) and a data organization approach for Chain-of-Thought with manufacturing (CoT-M) are designed to leverage the manufacturing process for IAD. Based on the above two modifications, we present Triad, a novel LMM-based method incorporating an expert-guided region-of-interest tokenizer and manufacturing process for industrial anomaly detection. Extensive experiments show that our Triad not only demonstrates competitive performance against current LMMs but also achieves further improved accuracy when equipped with manufacturing processes. Source code, training data, and pre-trained models will be publicly available at https://github.com/tzjtatata/Triad.

♻ ☆ Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text AAAI2024

Xuyang Chen, Dong Wang, Konrad Schindler, Mingwei Sun, Yongliang Wang, Nicolo Savioli, Liqiu Meng

Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. However, this approach incurs a significant memory overhead and struggles to effectively capture the intricate relationships between vertices belonging to the same instance. Consequently, irregular text layouts often lead to the prediction of outlined vertices, diminishing the quality of results. To address these challenges, we present an innovative approach rooted in Sparse R-CNN: a cascade decoding pipeline for polygon prediction. Our method ensures precision by iteratively refining polygon predictions, considering both the scale and location of preceding results. Leveraging this stabilized regression pipeline, even employing just a single feature vector to guide polygon instance regression yields promising detection results. Simultaneously, the leverage of instance-level feature proposal substantially enhances memory efficiency (>50% less vs. the state-of-the-art method DPText-DETR) and reduces inference speed (>40% less vs. DPText-DETR) with minor performance drop on benchmarks.

comment: Accepted to AAAI2024

♻ ☆ DriveIndia: An Object Detection Dataset for Diverse Indian Traffic Scenes

Rishav Kumar, D. Santhosh Reddy, P. Rajalakshmi

We introduce DriveIndia, a large-scale object detection dataset purpose-built to capture the complexity and unpredictability of Indian traffic environments. The dataset contains 66,986 high-resolution images annotated in YOLO format across 24 traffic-relevant object categories, encompassing diverse conditions such as varied weather (fog, rain), illumination changes, heterogeneous road infrastructure, and dense, mixed traffic patterns and collected over 120+ hours and covering 3,400+ kilometers across urban, rural, and highway routes. DriveIndia offers a comprehensive benchmark for real-world autonomous driving challenges. We provide baseline results using state-of-the-art YOLO family models, with the top-performing variant achieving a mAP50 of 78.7%. Designed to support research in robust, generalizable object detection under uncertain road conditions, DriveIndia will be publicly available via the TiHAN-IIT Hyderabad dataset repository https://tihan.iith.ac.in/TiAND.html (Terrestrial Datasets -> Camera Dataset).

comment: Accepted at ITSC 2025 Conference

♻ ☆ Investigating the Relationship between the Weighted Figure of Merit and Rosin's Measure

Bimal Kumar Ray

Many studies have been conducted to solve the problem of approximating a digital boundary by piece straight-line segments for the further processing required in computer vision applications. The authors of these studies compared their schemes to determine the best one. The initial measure used to assess the goodness of fit of a polygonal approximation was the figure of merit. Later,it was noted that this measure was not an appropriate metric for a valid reason which is why Rosin-through mathematical analysis-introduced a measure called merit. However,this measure involves an optimal scheme of polygonal approximation,so it is time-consuming to compute it to assess the goodness of fit of an approximation. This led many researchers to use a weighted figure of merit as a substitute for Rosin's measure to compare sub optimal schemes. An attempt is made in this communication to investigate whether the two measures-weighted figure of merit and Rosin's measure-are related so that one can be used instead of the other, and toward this end, theoretical analysis, experimental investigation and statistical analysis are carried out. The mathematical formulas for the weighted figure of merit and Rosin's measure are analyzed, and through proof of theorems,it is found that the two measures are theoretically independent of each other. The graphical analysis of experiments carried out using a public dataset supports the results of the theoretical analysis. The statistical analysis via Pearson's correlation coefficient and non-linear correlation measure also revealed that the two measures are uncorrelated. This analysis leads one to conclude that if a suboptimal scheme is found to be better (worse) than some other suboptimal scheme,as indicated by Rosin's measure,then the same conclusion cannot be drawn using a weighted figure of merit,so one cannot use a weighted figure of merit instead of Rosin's measure.

♻ ☆ From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Tianwei Yin, Qiang Zhang, Richard Zhang, William T. Freeman, Fredo Durand, Eli Shechtman, Xun Huang

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence, including the future. We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly. To further reduce latency, we extend distribution matching distillation (DMD) to videos, distilling 50-step diffusion model into a 4-step generator. To enable stable and high-quality distillation, we introduce a student initialization scheme based on teacher's ODE trajectories, as well as an asymmetric distillation strategy that supervises a causal student model with a bidirectional teacher. This approach effectively mitigates error accumulation in autoregressive generation, allowing long-duration video synthesis despite training on short clips. Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models. It enables fast streaming generation of high-quality videos at 9.4 FPS on a single GPU thanks to KV caching. Our approach also enables streaming video-to-video translation, image-to-video, and dynamic prompting in a zero-shot manner.

comment: Project Page: https://causvid.github.io/

♻ ☆ SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data

Xilin He, Cheng Luo, Xiaole Xian, Bing Li, Muhammad Haris Khan, Zongyuan Ge, Weicheng Xie, Siyang Song, Linlin Shen, Bernard Ghanem, Xiangyu Yue

Facial expression datasets remain limited in scale due to the subjectivity of annotations and the labor-intensive nature of data collection. This limitation poses a significant challenge for developing modern deep learning-based facial expression analysis models, particularly foundation models, that rely on large-scale data for optimal performance. To tackle the overarching and complex challenge, instead of introducing a new large-scale dataset, we introduce SynFER (Synthesis of Facial Expressions with Refined Control), a novel synthetic framework for synthesizing facial expression image data based on high-level textual descriptions as well as more fine-grained and precise control through facial action units. To ensure the quality and reliability of the synthetic data, we propose a semantic guidance technique to steer the generation process and a pseudo-label generator to help rectify the facial expression labels for the synthetic images. To demonstrate the generation fidelity and the effectiveness of the synthetic data from SynFER, we conduct extensive experiments on representation learning using both synthetic data and real-world data. Results validate the efficacy of our approach and the synthetic data. Notably, our approach achieves a 67.23% classification accuracy on AffectNet when training solely with synthetic data equivalent to the AffectNet training set size, which increases to 69.84% when scaling up to five times the original size. Code is available here.

comment: ICCV 2025

♻ ☆ REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents

Rui Tian, Qi Dai, Jianmin Bao, Kai Qiu, Yifan Yang, Chong Luo, Zuxuan Wu, Yu-Gang Jiang

Commercial video generation models have exhibited realistic, high-fidelity results but are still restricted to limited access. One crucial obstacle for large-scale applications is the expensive training and inference cost. In this paper, we argue that videos contain significantly more redundant information than images, allowing them to be encoded with very few motion latents. Towards this goal, we design an image-conditioned VAE that projects videos into extremely compressed latent space and decode them based on content images. This magic Reducio charm enables 64x reduction of latents compared to a common 2D VAE, without sacrificing the quality. Building upon Reducio-VAE, we can train diffusion models for high-resolution video generation efficiently. Specifically, we adopt a two-stage generation paradigm, first generating a condition image via text-to-image generation, followed by text-image-to-video generation with the proposed Reducio-DiT. Extensive experiments show that our model achieves strong performance in evaluation. More importantly, our method significantly boosts the training and inference efficiency of video LDMs. Reducio-DiT is trained in just 3.2K A100 GPU hours in total and can generate a 16-frame 1024$\times$1024 video clip within 15.5 seconds on a single A100 GPU. Code released at https://github.com/microsoft/Reducio-VAE .

comment: Accepted to ICCV2025. Code available at https://github.com/microsoft/Reducio-VAE

♻ ☆ A Fast Unsupervised Scheme for Polygonal Approximation

Bimal Kumar Ray

This paper proposes a fast and unsupervised scheme for the polygonal approximation of a closed digital curve. It is demonstrated that the approximation scheme is faster than state-of-the-art approximation and is competitive with Rosin's measure and aesthetic aspects. The scheme comprises of three phases: initial segmentation, iterative vertex insertion, iterative merging, and vertex adjustment. The initial segmentation is used to detect sharp turns, that is, vertices that seemingly have high curvature. It is likely that some of the important vertices with low curvature might have been missed in the first phase; therefore, iterative vertex insertion is used to add vertices in a region where the curvature changes slowly but steadily. The initial phase may pick up some undesirable vertices, and thus merging is used to eliminate redundant vertices. Finally, vertex adjustment was used to enhance the aesthetic appearance of the approximation. The quality of the approximations was measured using the Rosin's method. The robustness of the proposed scheme with respect to geometric transformation was observed.

♻ ☆ Automated Muscle and Fat Segmentation in Computed Tomography for Comprehensive Body Composition Analysis

Yaqian Chen, Hanxue Gu, Yuwen Chen, Jichen Yang, Haoyu Dong, Joseph Y. Cao, Adrian Camarena, Christopher Mantyh, Roy Colglazier, Maciej A. Mazurowski

Body composition assessment using CT images can potentially be used for a number of clinical applications, including the prognostication of cardiovascular outcomes, evaluation of metabolic health, monitoring of disease progression, assessment of nutritional status, prediction of treatment response in oncology, and risk stratification for surgical and critical care outcomes. While multiple groups have developed in-house segmentation tools for this analysis, there are very limited publicly available tools that could be consistently used across different applications. To mitigate this gap, we present a publicly accessible, end-to-end segmentation and feature calculation model specifically for CT body composition analysis. Our model performs segmentation of skeletal muscle, subcutaneous adipose tissue (SAT), and visceral adipose tissue (VAT) across the chest, abdomen, and pelvis area in axial CT images. It also provides various body composition metrics, including muscle density, visceral-to-subcutaneous fat (VAT/SAT) ratio, muscle area/volume, and skeletal muscle index (SMI), supporting both 2D and 3D assessments. To evaluate the model, the segmentation was applied to both internal and external datasets, with body composition metrics analyzed across different age, sex, and race groups. The model achieved high dice coefficients on both internal and external datasets, exceeding 89% for skeletal muscle, SAT, and VAT segmentation. The model outperforms the benchmark by 2.40% on skeletal muscle and 10.26% on SAT compared to the manual annotations given by the publicly available dataset. Body composition metrics show mean relative absolute errors (MRAEs) under 10% for all measures. Furthermore, the model provided muscular fat segmentation with a Dice coefficient of 56.27%, which can be utilized for additional analyses as needed.

♻ ☆ On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations

Jordan Vice, Naveed Akhtar, Yansong Gao, Richard Hartley, Ajmal Mian

Vision-Language Models (VLMs) are increasingly used as perceptual modules for visual content reasoning, including through captioning and DeepFake detection. In this work, we expose a critical vulnerability of VLMs when exposed to subtle, structured perturbations in the frequency domain. Specifically, we highlight how these feature transformations undermine authenticity/DeepFake detection and automated image captioning tasks. We design targeted image transformations, operating in the frequency domain to systematically adjust VLM outputs when exposed to frequency-perturbed real and synthetic images. We demonstrate that the perturbation injection method generalizes across five state-of-the-art VLMs which includes different-parameter Qwen2/2.5 and BLIP models. Experimenting across ten real and generated image datasets reveals that VLM judgments are sensitive to frequency-based cues and may not wholly align with semantic content. Crucially, we show that visually-imperceptible spatial frequency transformations expose the fragility of VLMs deployed for automated image captioning and authenticity detection tasks. Our findings under realistic, black-box constraints challenge the reliability of VLMs, underscoring the need for robust multimodal perception systems.

comment: Keywords: Vision-Language Models, Frequency-Domain Perturbations, Adversarial Robustness, Image Authenticity, Reliability

♻ ☆ Gotta Hear Them All: Towards Sound Source Aware Audio Generation

Wei Guo, Heng Wang, Jianbo Ma, Weidong Cai

comment: 17 pages, 12 figures, source code available at https://github.com/wguo86/SSV2A

♻ ☆ What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning

Chi-Hsi Kung, Frangil Ramirez, Juhyung Ha, Yi-Ting Chen, David Crandall, Yi-Hsuan Tsai

Understanding a procedural activity requires modeling both how action steps transform the scene, and how evolving scene transformations can influence the sequence of action steps, even those that are accidental or erroneous. Existing work has studied procedure-aware video representations by modeling the temporal order of actions, but has not explicitly learned the state changes (scene transformations). In this work, we study procedure-aware video representation learning by incorporating state-change descriptions generated by Large Language Models (LLMs) as supervision signals for video encoders. Moreover, we generate state-change counterfactuals that simulate hypothesized failure outcomes, allowing models to learn by imagining unseen "What if" scenarios. This counterfactual reasoning facilitates the model's ability to understand the cause and effect of each step in an activity. We conduct extensive experiments on procedure-aware tasks, including temporal action segmentation, error detection, action phase classification, frame retrieval, multi-instance retrieval, and action recognition. Our results demonstrate the effectiveness of the proposed state-change descriptions and their counterfactuals, and achieve significant improvements on multiple tasks.

comment: 16 pages, 4 figures

♻ ☆ Decoupled Functional Evaluation of Autonomous Driving Models via Feature Map Quality Scoring

Ludan Zhang, Sihan Wang, Yuqi Dai, Shuofei Qiao, Qinyue Luo, Lei He

End-to-end models are emerging as the mainstream in autonomous driving perception and planning. However, the lack of explicit supervision signals for intermediate functional modules leads to opaque operational mechanisms and limited interpretability, making it challenging for traditional methods to independently evaluate and train these modules. Pioneering in the issue, this study builds upon the feature map-truth representation similarity-based evaluation framework and proposes an independent evaluation method based on Feature Map Convergence Score (FMCS). A Dual-Granularity Dynamic Weighted Scoring System (DG-DWSS) is constructed, formulating a unified quantitative metric - Feature Map Quality Score - to enable comprehensive evaluation of the quality of feature maps generated by functional modules. A CLIP-based Feature Map Quality Evaluation Network (CLIP-FMQE-Net) is further developed, combining feature-truth encoders and quality score prediction heads to enable real-time quality analysis of feature maps generated by functional modules. Experimental results on the NuScenes dataset demonstrate that integrating our evaluation module into the training improves 3D object detection performance, achieving a 3.89 percent gain in NDS. These results verify the effectiveness of our method in enhancing feature representation quality and overall model performance.

♻ ☆ Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

Fangyuan Mao, Aiming Hao, Jintao Chen, Dongxia Liu, Xiaokun Feng, Jiashu Zhu, Meiqi Wu, Chubin Chen, Jiahong Wu, Xiangxiang Chu

Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation models offer cost-efficient solutions for VFX production, current methods are constrained by per-effect LoRA training, which limits generation to single effects. This fundamental limitation impedes applications that require spatially controllable composite effects, i.e., the concurrent generation of multiple effects at designated locations. However, integrating diverse effects into a unified framework faces major challenges: interference from effect variations and spatial uncontrollability during multi-VFX joint training. To tackle these challenges, we propose Omni-Effects, a first unified framework capable of generating prompt-guided effects and spatially controllable composite effects. The core of our framework comprises two key innovations: (1) LoRA-based Mixture of Experts (LoRA-MoE), which employs a group of expert LoRAs, integrating diverse effects within a unified model while effectively mitigating cross-task interference. (2) Spatial-Aware Prompt (SAP) incorporates spatial mask information into the text token, enabling precise spatial control. Furthermore, we introduce an Independent-Information Flow (IIF) module integrated within the SAP, isolating the control signals corresponding to individual effects to prevent any unwanted blending. To facilitate this research, we construct a comprehensive VFX dataset Omni-VFX via a novel data collection pipeline combining image editing and First-Last Frame-to-Video (FLF2V) synthesis, and introduce a dedicated VFX evaluation framework for validating model performance. Extensive experiments demonstrate that Omni-Effects achieves precise spatial control and diverse effect generation, enabling users to specify both the category and location of desired effects.

♻ ☆ SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition

Mengqi Lei, Yihong Wu, Siqi Li, Xinhu Zheng, Juan Wang, Yue Gao, Shaoyi Du

Visual recognition relies on understanding both the semantics of image tokens and the complex interactions among them. Mainstream self-attention methods, while effective at modeling global pair-wise relations, fail to capture high-order associations inherent in real-world scenes and often suffer from redundant computation. Hypergraphs extend conventional graphs by modeling high-order interactions and offer a promising framework for addressing these limitations. However, existing hypergraph neural networks typically rely on static and hard hyperedge assignments, leading to excessive and redundant hyperedges with hard binary vertex memberships that overlook the continuity of visual semantics. To overcome these issues, we present Soft Hypergraph Neural Networks (SoftHGNNs), which extend the methodology of hypergraph computation, to make it truly efficient and versatile in visual recognition tasks. Our framework introduces the concept of soft hyperedges, where each vertex is associated with hyperedges via continuous participation weights rather than hard binary assignments. This dynamic and differentiable association is achieved by using the learnable hyperedge prototype. Through similarity measurements between token features and the prototype, the model generates semantically rich soft hyperedges. SoftHGNN then aggregates messages over soft hyperedges to capture high-order semantics. To further enhance efficiency when scaling up the number of soft hyperedges, we incorporate a sparse hyperedge selection mechanism that activates only the top-k important hyperedges, along with a load-balancing regularizer to ensure balanced hyperedge utilization. Experimental results across three tasks on five datasets demonstrate that SoftHGNN efficiently captures high-order associations in visual scenes, achieving significant performance improvements.

♻ ☆ AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

Lixuan He, Jie Feng, Yong Li

Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal trade-offs between imitation and exploration. Recent single-stage methods attempt to unify SFT and RL using heuristics, but lack a principled mechanism for dynamically balancing the two paradigms. In this paper, we reframe this challenge through the theoretical lens of \textbf{implicit rewards}, viewing SFT and RL not as distinct methods but as complementary reward signals. We introduce \textbf{Adaptive Meta Fine-Tuning (AMFT)}, a novel single-stage algorithm that learns the optimal balance between SFT's implicit, path-level reward and RL's explicit, outcome-based reward. The core of AMFT is a \textbf{meta-gradient adaptive weight controller} that treats the SFT-RL balance as a learnable parameter, dynamically optimizing it to maximize long-term task performance. This forward-looking approach, regularized by policy entropy for stability, autonomously discovers an effective training curriculum. We conduct a comprehensive evaluation on challenging benchmarks spanning mathematical reasoning, abstract visual reasoning (General Points), and vision-language navigation (V-IRL). AMFT consistently establishes a new state-of-the-art and demonstrats superior generalization on out-of-distribution (OOD) tasks. Ablation studies and training dynamic analysis confirm that the meta-learning controller is crucial for AMFT's stability, sample efficiency, and performance, offering a more principled and effective paradigm for LLM alignment. Our codes are open-sourced via https://github.com/hlxtsyj/AMFT.

comment: https://github.com/hlxtsyj/AMFT

♻ ☆ GPSMamba: A Global Phase and Spectral Prompt-guided Mamba for Infrared Image Super-Resolution

Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Shinichiro Omachi

Infrared Image Super-Resolution (IRSR) is challenged by the low contrast and sparse textures of infrared data, requiring robust long-range modeling to maintain global coherence. While State-Space Models like Mamba offer proficiency in modeling long-range dependencies for this task, their inherent 1D causal scanning mechanism fragments the global context of 2D images, hindering fine-detail restoration. To address this, we propose Global Phase and Spectral Prompt-guided Mamba (GPSMamba), a framework that synergizes architectural guidance with non-causal supervision. First, our Adaptive Semantic-Frequency State Space Module (ASF-SSM) injects a fused semantic-frequency prompt directly into the Mamba block, integrating non-local context to guide reconstruction. Then, a novel Thermal-Spectral Attention and Phase Consistency Loss provides explicit, non-causal supervision to enforce global structural and spectral fidelity. By combining these two innovations, our work presents a systematic strategy to mitigate the limitations of causal modeling. Extensive experiments demonstrate that GPSMamba achieves state-of-the-art performance, validating our approach as a powerful new paradigm for infrared image restoration. Code is available at https://github.com/yongsongH/GPSMamba.

comment: This manuscript is under review, and copyright will be transferred without notice

♻ ☆ Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

Bowen Xue, Qixin Yan, Wenjing Wang, Hao Liu, Chen Li

Generating high-fidelity human videos that match user-specified identities is important yet challenging in the field of generative AI. Existing methods often rely on an excessive number of training parameters and lack compatibility with other AIGC tools. In this paper, we propose Stand-In, a lightweight and plug-and-play framework for identity preservation in video generation. Specifically, we introduce a conditional image branch into the pre-trained video generation model. Identity control is achieved through restricted self-attentions with conditional position mapping, and can be learned quickly with only 2000 pairs. Despite incorporating and training just $\sim$1% additional parameters, our framework achieves excellent results in video quality and identity preservation, outperforming other full-parameter training methods. Moreover, our framework can be seamlessly integrated for other tasks, such as subject-driven video generation, pose-referenced video generation, stylization, and face swapping.

♻ ☆ IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model

Anqing Jiang, Yu Gao, Yiru Wang, Zhigang Sun, Shuo Wang, Yuwen Heng, Hao Sun, Shichen Tang, Lijuan Zhu, Jinhao Chai, Jijun Wang, Zichong Gu, Hao Jiang, Li Sun

comment: 9 pagres, 2 figures

♻ ☆ A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

Junjun Jiang, Zengyuan Zuo, Gang Wu, Kui Jiang, Xianming Liu

Image restoration (IR) seeks to recover high-quality images from degraded observations caused by a wide range of factors, including noise, blur, compression, and adverse weather. While traditional IR methods have made notable progress by targeting individual degradation types, their specialization often comes at the cost of generalization, leaving them ill-equipped to handle the multifaceted distortions encountered in real-world applications. In response to this challenge, the all-in-one image restoration (AiOIR) paradigm has recently emerged, offering a unified framework that adeptly addresses multiple degradation types. These innovative models enhance the convenience and versatility by adaptively learning degradation-specific features while simultaneously leveraging shared knowledge across diverse corruptions. In this survey, we provide the first in-depth and systematic overview of AiOIR, delivering a structured taxonomy that categorizes existing methods by architectural designs, learning paradigms, and their core innovations. We systematically categorize current approaches and assess the challenges these models encounter, outlining research directions to propel this rapidly evolving field. To facilitate the evaluation of existing methods, we also consolidate widely-used datasets, evaluation protocols, and implementation practices, and compare and summarize the most advanced open-source models. As the first comprehensive review dedicated to AiOIR, this paper aims to map the conceptual landscape, synthesize prevailing techniques, and ignite further exploration toward more intelligent, unified, and adaptable visual restoration systems. A curated code repository is available at https://github.com/Harbinzzy/All-in-One-Image-Restoration-Survey.

comment: IEEE Transactions on Pattern Analysis and Machine Intelligence

♻ ☆ StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback

Hongbo Ma, Fei Shen, Hongbin Xu, Xiaoce Wang, Gang Xu, Jinkai Zheng, Liangqiong Qu, Ming Li

The advancement of intelligent agents has revolutionized problem-solving across diverse domains, yet solutions for personalized fashion styling remain underexplored, which holds immense promise for promoting shopping experiences. In this work, we present StyleTailor, the first collaborative agent framework that seamlessly unifies personalized apparel design, shopping recommendation, virtual try-on, and systematic evaluation into a cohesive workflow. To this end, StyleTailor pioneers an iterative visual refinement paradigm driven by multi-level negative feedback, enabling adaptive and precise user alignment. Specifically, our framework features two core agents, i.e., Designer for personalized garment selection and Consultant for virtual try-on, whose outputs are progressively refined via hierarchical vision-language model feedback spanning individual items, complete outfits, and try-on efficacy. Counterexamples are aggregated into negative prompts, forming a closed-loop mechanism that enhances recommendation quality. To assess the performance, we introduce a comprehensive evaluation suite encompassing style consistency, visual quality, face similarity, and artistic appraisal. Extensive experiments demonstrate StyleTailor's superior performance in delivering personalized designs and recommendations, outperforming strong baselines without negative feedback and establishing a new benchmark for intelligent fashion systems.

comment: 24pages, 5 figures

♻ ☆ Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Jiwen Yu, Jianhong Bai, Yiran Qin, Quande Liu, Xintao Wang, Pengfei Wan, Di Zhang, Xihui Liu

Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we propose Context-as-Memory, which utilizes historical context as memory for video generation. It includes two simple yet effective designs: (1) storing context in frame format without additional post-processing; (2) conditioning by concatenating context and frames to be predicted along the frame dimension at the input, requiring no external control modules. Furthermore, considering the enormous computational overhead of incorporating all historical context, we propose the Memory Retrieval module to select truly relevant context frames by determining FOV (Field of View) overlap between camera poses, which significantly reduces the number of candidate frames without substantial information loss. Experiments demonstrate that Context-as-Memory achieves superior memory capabilities in interactive long video generation compared to SOTAs, even generalizing effectively to open-domain scenarios not seen during training. The link of our project page is https://context-as-memory.github.io/.

comment: SIGGRAPH Asia 2025, Project Page: https://context-as-memory.github.io/

♻ ☆ Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

Zeqian Long, Mingzhe Zheng, Kunyu Feng, Xinhua Zhang, Hongyu Liu, Harry Yang, Linfeng Zhang, Qifeng Chen, Yue Ma

While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose Follow-Your-Shape, a training-free and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a Scheduled KV Injection mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce ReShapeBench, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement.

comment: Project webpage is available at https://follow-your-shape.github.io/

♻ ☆ WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image

Yuci Liang, Xinheng Lyu, Wenting Chen, Meidan Ding, Jipeng Zhang, Xiangjian He, Song Wu, Xiaohan Xing, Sen Yang, Xiyue Wang, Linlin Shen

Recent advancements in computational pathology have produced patch-level Multi-modal Large Language Models (MLLMs), but these models are limited by their inability to analyze whole slide images (WSIs) comprehensively and their tendency to bypass crucial morphological features that pathologists rely on for diagnosis. To address these challenges, we first introduce WSI-Bench, a large-scale morphology-aware benchmark containing 180k VQA pairs from 9,850 WSIs across 30 cancer types, designed to evaluate MLLMs' understanding of morphological characteristics crucial for accurate diagnosis. Building upon this benchmark, we present WSI-LLaVA, a novel framework for gigapixel WSI understanding that employs a three-stage training approach: WSI-text alignment, feature space alignment, and task-specific instruction tuning. To better assess model performance in pathological contexts, we develop two specialized WSI metrics: WSI-Precision and WSI-Relevance. Experimental results demonstrate that WSI-LLaVA outperforms existing models across all capability dimensions, with a significant improvement in morphological analysis, establishing a clear correlation between morphological understanding and diagnostic accuracy.

comment: ICCV 2025, 38 pages, 22 figures, 35 tables

♻ ☆ Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference

Cheng Yuan, Zhening Liu, Jiashu Lv, Jiawei Shao, Yufei Jiang, Jun Zhang, Xuelong Li

With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the predominant inference pipeline involves directly forwarding the input data to an edge server which handles all computations. However, this approach introduces high transmission latency due to limited uplink bandwidth of edge devices and significant computation latency caused by the prohibitive number of visual tokens, thus hindering delay-sensitive tasks and degrading user experience. To address this challenge, we propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework, where visual features are merged by clustering and encoded by a learnable and selective entropy model before feature projection. Specifically, we employ density peaks clustering based on K nearest neighbors to reduce the number of visual features, thereby minimizing both data transmission and computational complexity. Subsequently, a learnable entropy model with hyperprior is utilized to encode and decode merged features, further reducing transmission overhead. To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features, enabling a more accurate estimation of the probability distribution. Comprehensive experiments on seven visual question answering benchmarks validate the effectiveness of the proposed TOFC method. Results show that TOFC achieves up to 52% reduction in data transmission overhead and 63% reduction in system latency while maintaining identical task performance, compared with neural compression ELIC.

♻ ☆ FUTransUNet-GradCAM: A Hybrid Transformer-U-Net with Self-Attention and Explainable Visualizations for Foot Ulcer Segmentation

Akwasi Asare, Mary Sagoe, Justice Williams Asare

Automated segmentation of diabetic foot ulcers (DFUs) plays a critical role in clinical diagnosis, therapeutic planning, and longitudinal wound monitoring. However, this task remains challenging due to the heterogeneous appearance, irregular morphology, and complex backgrounds associated with ulcer regions in clinical photographs. Traditional convolutional neural networks (CNNs), such as U-Net, provide strong localization capabilities but struggle to model long-range spatial dependencies due to their inherently limited receptive fields. To address this, we propose FUTransUNet, a hybrid architecture that integrates the global attention mechanism of Vision Transformers (ViTs) into the U-Net framework. This combination allows the model to extract global contextual features while maintaining fine-grained spatial resolution through skip connections and an effective decoding pathway. We trained and validated FUTransUNet on the public Foot Ulcer Segmentation Challenge (FUSeg) dataset. FUTransUNet achieved a training Dice Coefficient of 0.8679, an IoU of 0.7672, and a training loss of 0.0053. On the validation set, the model achieved a Dice Coefficient of 0.8751, an IoU of 0.7780, and a validation loss of 0.009045. To ensure clinical transparency, we employed Grad-CAM visualizations, which highlighted model focus areas during prediction. These quantitative outcomes clearly demonstrate that our hybrid approach successfully integrates global and local feature extraction paradigms, thereby offering a highly robust, accurate, explainable, and interpretable solution and clinically translatable solution for automated foot ulcer analysis. The approach offers a reliable, high-fidelity solution for DFU segmentation, with implications for improving real-world wound assessment and patient care.

♻ ☆ A Data-driven Loss Weighting Scheme across Heterogeneous Tasks for Image Denoising

Xiangyu Rui, Xiangyong Cao, Xile Zhao, Deyu Meng, Michael K. NG

In a variational denoising model, weight in the data fidelity term plays the role of enhancing the noise-removal capability. It is profoundly correlated with noise information, while also balancing the data fidelity and regularization terms. However, the difficulty of assigning weight is expected to be substantial when the noise pattern is beyond independent identical Gaussian distribution, e.g., impulse noise, stripe noise, or a mixture of several patterns, etc. Furthermore, how to leverage weight to balance the data fidelity and regularization terms is even less evident. In this work, we propose a data-driven loss weighting (DLW) scheme to address these issues. Specifically, DLW trains a parameterized weight function (i.e., a neural network) that maps the noisy image to the weight. The training is achieved by a bilevel optimization framework, where the lower level problem is solving several denoising models with the same weight predicted by the weight function and the upper level problem minimizes the distance between the restored image and the clean image. In this way, information from both the noise and the regularization can be efficiently extracted to determine the weight function. DLW also facilitates the easy implementation of a trained weight function on denoising models. Numerical results verify the remarkable performance of DLW on improving the ability of various variational denoising models to handle different complex noise. This implies that DLW has the ability to transfer the noise knowledge at the model level to heterogeneous tasks beyond the training ones and the generalization theory underlying DLW is studied, validating its intrinsic transferability.

♻ ☆ Enhancing Wide-Angle Image Using Narrow-Angle View of the Same Scene

Hussain Md. Safwan, Mahbub Islam Mahim

A common dilemma while photographing a scene is whether to capture it at a wider angle, allowing more of the scene to be covered but in less detail or to click in a narrow angle that captures better details but leaves out portions of the scene. We propose a novel method in this paper that infuses wider shots with finer quality details that is usually associated with an image captured by the primary lens by capturing the same scene using both narrow and wide field of view (FoV) lenses. We do so by training a Generative Adversarial Network (GAN)-based model to learn to extract the visual quality parameters from a narrow-angle shot and to transfer these to the corresponding wide-angle image of the scene using residual connections and an attention-based fusion module. We have mentioned in details the proposed technique to isolate the visual essence of an image and to transfer it into another image. We have also elaborately discussed our implementation details and have presented the results of evaluation over several benchmark datasets and comparisons with contemporary advancements in the field.