Semi-supervised Video Object Segmentation (VOS) aims to segment a user-specified object across all frames of a video using only the first frame's annotated mask. A key challenge in VOS is simultaneously preserving object identity and maintaining precise segmentation in dynamic scenes, especially during rapid motion. Many existing methods use previous frame masks as positional constraints, hindering segmentation of newly exposed regions-an issue known as over-suppression. To address these challenges, we propose FlowTrack, integrating two main components: an Adjacent-frame Motion Tracker (AMT) and an Adaptive Motion Predictor (AMP). AMT explicitly captures motion and positional information between adjacent frames and fuses it with historical target cues, improving segmentation constraint robustness and helping maintain stable object identity during rapid motion or significant deformation. However, relying primarily on historical masks and frame-level constraints may fail to accurately predict sudden changes in motion states, which still leads to over-suppression. To overcome this limitation, AMP predicts future states from historical motion data. Employing a learned state predictor and a Kalman-inspired recursive measurement fusion, AMP adapts to complex and abrupt motion changes. This dynamic prediction-update scheme refines segmentation boundaries, compensates for historical constraints, and effectively mitigates over-suppression. Experimental results on standard VOS benchmarks validate the effectiveness of the proposed FlowTrack framework in handling challenging dynamic scenes involving rapid motion and addressing the over-suppression issue.
论文检索
输入标题、作者或关键词，从 1,620 篇学术成果中精准定位
Image aesthetic assessment (IAA) is challenging due to its subjective and diverse nature, making visual information alone insufficient. Existing methods using paired image and user comments, though effective, have limited practicality. Moreover, user comments contain both high- and weak-aesthetic-related textual information, thus directly integrating all textual information with visual information cannot guarantee the effectiveness. To address these issues, we propose a novel synergistic coarse-fine vision-language alignment (CoFiVLA) framework for IAA. It includes a CoFiVLA pretraining network and a CoFiVLA prediction network, aiming to effectively and comprehensively align and synergize image and text modalities at both coarse and fine granularities during training, while eliminating the dependence on user comments during inference. In the CoFiVLA pretraining network, the coarse- and fine-grained vision-language alignment branches work together, aligning the visual features with the high-aesthetic-related textual information and all textual information, respectively. In the coarse-grained alignment branch, we innovatively propose employing the large language model LLaMA to construct an aesthetic summary dataset, which extracts high-aesthetic-related text from user comments. Furthermore, in the CoFiVLA prediction network, we first extract features corresponding to learnable prompts of different aesthetic quality categories based on the CoFiVLA pretrained model, then fuse visual features with these learnable textual features. Thus we achieve aesthetic quality semantics embedded image aesthetic representations for effective IAA without requiring user comments during inference. Our aesthetic summary dataset and source code are available at https://github.com/lifusheng-chn/CoFiVLA.
Scene understanding enables intelligent agents to interpret and comprehend their environment. While existing large vision-language models (LVLMs) for scene understanding have primarily focused on indoor household tasks, they face two significant limitations when applied to outdoor large-scale scene understanding. First, outdoor scenarios typically encompass larger-scale environments observed through various sensors from multiple viewpoints (e.g., bird view and terrestrial view), while existing indoor LVLMs mainly analyze single visual modalities within building-scale contexts from humanoid viewpoints. Second, existing LVLMs suffer from missing multidomain perception outdoor data and struggle to effectively integrate 2D and 3D visual information. To address the aforementioned limitations, we build the first multidomain perception outdoor scene understanding dataset, named SVM-City, deriving from multi-Scale scenarios with multi-View and multi-Modal instruction tuning data. It contains 420k images and 4, 811M point clouds with 567k question-answering pairs from vehicles, low-altitude drones, high-altitude aerial planes, and satellite. To effectively fuse multimodal data in the absence of one modality, we introduce incomplete multimodal learning to model outdoor scene understanding and design the LVLM named City-VLM. Multimodal fusion is realized by constructed as a joint probabilistic distribution space rather than implementing directly explicit fusion operations (e.g., concatenation). Experimental results on three typical outdoor scene understanding tasks show City-VLM achieves 18.14 % performance surpassing existing LVLMs in question-answering tasks averagely. Our method demonstrates pragmatic and generalization performance across multiple outdoor scenes.
DMC3: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering
PDF ↗Egocentric Video Question Answering (Egocentric VideoQA) plays an important role in egocentric video understanding, which refers to answering questions based on first-person videos. Although existing methods have made progress through the paradigm of pre-training and fine-tuning, they ignore the unique challenges posed by the first-person perspective, such as understanding multiple events and recognizing hand-object interactions. To deal with these challenges, we propose a Dual-Modal Counterfactual Contrastive Construction (DMC3) framework, which contains an egocentric videoqa baseline, a counterfactual sample construction module and a counterfactual sample-involved contrastive optimization. Specifically, We first develop a counterfactual sample construction module to generate positive and negative samples for textual and visual modalities through event description paraphrasing and core interaction mining, respectively. Then, We feed these samples together with the original samples into the baseline. Finally, in the counterfactual sample-involved contrastive optimization module, we apply contrastive loss to minimize the distance between the original sample features and the positive sample features, while maximizing the distance from the negative samples. Experiments show that our method achieve 52.51% and 46.04% on the normal and indirect splits of EgoTaskQA, and 13.2% on QAEGO4D, both reaching the state-of-the-art performance.
In existing Sign Language (SL) research, most datasets and backbone models focus on sentence-level samples. However, the annotated sentence-level SL datasets are rather limited, and it is in great need to expand sentence-level SL datasets. When considering the large-scale long SL videos with captions, we propose a new task, i.e., Sentence-level Sign Language Segmentation (SSLS), which splits the long videos into consecutive sentence-level videos. SSLS is an important and meaningful task, which can greatly reduce the labor costs in data annotation for sentence-level SL datasets. However, SSLS is a very challenging task, since it is rather difficult to accurately find the boundary of each sentence in a long video. To address this issue, we formalize, learn, and optimize the boundaries of sentences step by step. First, to distinguish the boundary and the inside of a sentence, we formalize SSLS as a frame-level classification task and design a boundary annotation scheme. Second, to learn the boundary of each sentence from the long video, we design a multimodal framework, SignBD, which correlates the local features and global features through dual dilated attention, while aligning visual and textual (i.e., sentences) modalities through gated cross-attention. Third, to alleviate the widely existed over-segmentation and under-segmentation problems in segmentation tasks, we propose a boundary optimization strategy, which utilizes the number of sentences provided by captions to optimize (i.e., insert or delete) boundaries based on information uncertainty. Extensive experimental results demonstrate the superiority of our solution.
Soccer is a globally popular sporting event, typically characterized by long matches and distinctive highlight moments. Recent advances in Multimodal Large Language Models (MLLMs) show promising capabilities in temporal grounding and video understanding. However, generating soccer commentary requires both precise temporal localization and semantically rich descriptions over long-form videos. Existing soccer MLLMs often rely on temporal priors for caption generation, which limits their ability to process the entire video in an end-to-end manner. Traditional approaches, on the other hand, follow a complex two-step paradigm that fails to capture the global context, leading to suboptimal performance. To solve the above issues, we present TimeSoccer, the first end-to-end soccer MLLM for Single-anchor Dense Video Captioning (SDVC) in full-match soccer videos. TimeSoccer jointly predicts timestamps and generates captions in a single pass, enabling global context modeling across 45-minute matches. To support long video understanding of soccer matches, we introduce MoFA-Select, a training-free, motion-aware frame compression module that adaptively selects representative frames via a coarse-to-fine strategy, and incorporates complementary training paradigms to strengthen the model's ability to handle long temporal sequences. Extensive experiments demonstrate that our TimeSoccer achieves State-of-The-Art (SoTA) performance on the SDVC task in an end-to-end form, generating high-quality commentary with accurate temporal alignment and strong semantic relevance. For more information, please visit: https://vpx-ecnu.github.io/TimeSoccer-Website/.
In clinical practice, medical image analysis often requires efficient execution on resource-constrained mobile devices. However, existing mobile models-primarily optimized for natural images-tend to perform poorly on medical tasks due to the significant information density gap between natural and medical domains. Combining computational efficiency with medical imaging-specific architectural advantages remains a challenge when developing lightweight, universal, and high-performing networks. To address this, we propose a mobile model called Mobile U-shaped Vision Transformer (Mobile U-ViT) tailored for medical image segmentation. Specifically, we employ the newly proposed ConvUtr as a hierarchical patch embedding, featuring a parameter-efficient large-kernel CNN with inverted bottleneck fusion. This design exhibits transformer-like representation learning capacity while being lighter and faster. To enable efficient local-global information exchange, we introduce a novel Large-kernel Local-Global-Local (LKLGL) block that effectively balances the low information density and high-level semantic discrepancy of medical images. Finally, we incorporate a shallow and lightweight transformer bottleneck for long-range modeling and employ a cascaded decoder with downsampled skip connections for dense prediction. Despite its reduced computational demands, our medical-optimized architecture achieves state-of-the-art performance across eight public 2D and 3D datasets covering diverse imaging modalities, including zero-shot testing on four unseen datasets. These results establish it as an efficient yet powerful and generalization solution for mobile medical image analysis. Code is available at: https://github.com/FengheTan9/Mobile-U-ViT.
Understanding dynamic outdoor environments requires capturing complex object interactions and their evolution over time. LiDAR-based 4D point clouds provide precise spatial geometry and rich temporal cues, making them ideal for representing real-world scenes. However, despite their potential, 4D LiDAR remains underexplored in the context of Multimodal Large Language Models (MLLMs) due to the absence of high-quality, modality-specific annotations and the lack of MLLM architectures capable of processing its high-dimensional composition. To address these challenges, we introduce B4DL, a new benchmark specifically designed for training and evaluating MLLMs on 4D LiDAR understanding. In addition, we propose a scalable data generation pipeline and an MLLM model that, for the first time, directly processes raw 4D LiDAR by bridging it with language understanding. Combined with our dataset and benchmark, our model offers a unified solution for spatio-temporal reasoning in dynamic outdoor environments. We provide rendered 4D LiDAR videos, generated dataset, and inference outputs on diverse scenarios at: https://mmb4dl.github.io/mmb4dl/
Animation data is often obtained through optical motion capture systems, which utilize a multitude of cameras to establish the position of optical markers. However, system errors or occlusions can result in missing markers, the manual cleaning of which can be time-consuming. This has sparked interest in machine learning-based solutions for missing marker reconstruction in the academic community. Most academic papers utilize a simplistic mean square error as the main metric. In this paper, we show that this metric does not correlate with subjective perception of the fill quality. Additionally, we introduce and evaluate a set of better-correlated metrics that can drive progress in the field.
Vision-Language Models (VLMs) such as GPT-4V and LLaVA have demonstrated impressive capabilities in multimodal understanding and generation. Unfortunately, their ability to infer sensitive information from visual content raises serious privacy concerns, especially when the images containing personal information. Existing solutions either rely on static alignment mechanisms, such as task-specific prompt turning, which are vulnerable to adversarial prompts, or irreversible redaction methods that permanently destroy content utility for legitimate users. To address these limitations, we propose a reversible privacy-preserving framework on VLMs via Adversarial Multimodal Key (AMK). Specifically, AMK embeds a learnable adversarial image key into mosaic-obscured images and generates a corresponding text key through multimodal contrastive learning model. The image key is optimized by gradient-based supervision from white-box VLMs, and the text key is implicitly derived from the image content to avoid exposure during transmission. These keys enable authorized users to restore sensitive information through VLMs, while unauthorized queries are explicitly rejected through a refusal response mechanism. Our experiments across various privacy scenarios show that the proposed method effectively restores redacted content with correct keys and prevents unauthorized disclosure, offering a practical solution for privacy protection in multimodal systems.
Although existing diffusion-based image super-resolution methods have achieved remarkable visual quality, they often struggle with fidelity issues, particularly in preserving consistency with the original input image. This issue arises because using low-quality images as conditional inputs introduces substantial errors in the diffusion backward denoising process, making the restored features deviate from target features and thus degrade image fidelity. To improve the accuracy of noise estimation, we propose a dual-memory module to reinforce the input low-quality conditional features, which consists of a pre-trained high-quality memory bank to enrich the structural information and a degradation memory to remove the degradation components. Furthermore, we develop an uncertainty-aware noise estimation framework, utilizing an extra branch in the denoising network to predict pixel-wise uncertainty values, thus dynamically adjust the optimization weights for high-uncertainty regions. This adaptive strategy effectively improves the accuracy of noise estimation in challenging reconstruction areas. Experimental results demonstrate that our method significantly enhances the fidelity while preserving high visual quality of diffusion-based super-resolution, improving the reliability of diffusion applications.
Recent advances in Generalized Zero-Shot Learning have demonstrated promising results by leveraging cross-modal attention mechanisms to model the nuanced relationships between semantic attributes and visual regions. However, we find that inherent attribute imbalance leads to significant attention disparities, i.e., those attributes with less sample weights often exhibit lower attention confidence and poorer localization accuracy. This attention illusion obviously leads to potential degraded or even counterproductive contributions to category determination. Conventional rebalancing approaches like resampling or reweighting are ineffective for attention calibration due to the complex interdependencies among attributes in one object and the absence of region-level annotation guidance. In this paper, we propose a novel coarse-to-fine framework termed Hierarchical Progressive Attention Network (HPAN), which leverages latent attention consistency across attributes to rectify the focus deviation of minor attributes. HPAN comprises two synergistic components, Super-Attribute Guided Generable Attention (SGGA) and Rebalanced Attribute Attention Calibration (RAAC). SGGA employs super-attributes to establish unified attention regions for both major and minor attributes, subsequently propagating these attention masks to RAAC for calibration. RAAC specializes in capturing fine-grained attribute-region interaction relations, with its output attention masks serving as supervisory signals to iteratively optimize the coarse attention of SGGA. Extensive experiments on three benchmark datasets verify the effectiveness of the proposed method. Code is available at github.com/zjrao/HPAN.
Despite recent progress in decoding static images from brain activity, reconstructing dynamic visual experiences from EEG signals remains challenging due to the complex temporal dynamics involved. Current approaches primarily rely on pre-trained video generation models while failing to fully leverage the rich temporal-spatial information embedded in EEG signals for video synthesis. This paper proposes MINDEV Multi-modal Integrated Neural DEcoding and Visualization), a framework that places EEG signal processing at the core of video reconstruction. We introduce three key technical contributions: (1) a dual-branch feature extractor that captures both temporal dynamics and spatial relationships in EEG signals, (2) an EEG-driven semantic bridge that uses neural patterns to guide language model interpretation, and (3) a multi-modal video synthesis pipeline where EEG features lead the generation process while semantic guidance provides refinement. Our framework prioritizes the millisecond-level temporal resolution of EEG signals, using them to drive both visual content generation and semantic understanding. Evaluated on the SEED-DV dataset, MINDEV demonstrates superior performance with a semantic classification accuracy of 93.2% and a structural similarity index (SSIM) of 0.4777, establishing a new state-of-the-art for EEG-based video reconstruction. Our code is publicly available at https://github.com/HHarr1son/MINDEV.
In response to the growing demands of real-world applications, models must be capable of learning continuously under inconsistent data distribution. However, existing Class-Incremental (CI) methods fail to alleviate domain shifts, while traditional Unsupervised Domain Adaptation (UDA) techniques suffer from catastrophic forgetting and privacy concerns. To address these limitations, we explore Source-Free Class Incremental Domain Adaptation (SFCIDA) and propose a novel approach, Quantifying Samples with Invariance (QSI), for this scenario. Our proposed method involves two main strategies: (1) Semantic Restructuring. We identify confusing source category pairs and restructure images to create a negative dataset that is semantically similar to the source features, refining accurate decision boundary among source categories. (2) Invariance Quantification. The sample's confidence is then quantified by its spatial location under the special data distribution, reflecting the trade-off between invariant features and domain shifts. Guided by such strategy, samples' confidence is accumulated for the target model to prioritize reliable categories, not only mitigating the poor performance of experience replay in unsupervised scenarios, but alleviating distribution discrepancies simultaneously. Experiments demonstrate that our approach outperforms previous methods, establishing new state-of-the-art performance on the Office-31, Office-Home and DomainNet-126 datasets, with average accuracy improvements of over 7.3%, 4.9% and 10.2% respectively.
Deep generative models, such as diffusion models, have shown promising progress in image generation and audio generation via simplified continuity assumptions. However, the development of generative modeling techniques for generating multi-modal data, such as parametric CAD sequences, still lags behind due to the challenges in addressing long-range constraints and parameter sensitivity. In this work, we propose a novel framework for quantitatively constrained CAD generation, termed Target-Guided Bayesian Flow Network (TGBFN). For the first time, TGBFN handles the multi-modality of CAD sequences (i.e., discrete commands and continuous parameters) in a unified continuous and differentiable parameter space rather than in the discrete data space. In addition, TGBFN penetrates the parameter update kernel and introduces a guided Bayesian flow to control the CAD properties. To evaluate TGBFN, we construct a new dataset for quantitatively constrained CAD generation. Extensive comparisons across single-condition and multi-condition constrained generation tasks demonstrate that TGBFN achieves state-of-the-art performance in generating high-fidelity, condition-aware CAD sequences. The code is available at https://github.com/scu-zwh/TGBFN.
Emotional Video Captioning (EVC) is an emerging task that aims to describe factual content with the intrinsic emotions expressed in videos. Existing EVC methods perceive global emotional cues through visual features at first, and then combine them with the video features to guide the emotional caption generation, which ignores the critical characteristic of the EVC task that emotional cues have intrinsic motivational causes reflected in the video content. Such video causes have a facilitative effect on both emotion perception and emotion-attributed caption generation. To this end, a multi-round mutual emotion-cause pair extraction network (MM-ECPE) is proposed in this paper for the joint extraction of emotional cues and visual causes through iterative mutual refinement. Specifically, in the 1st-round mutual learning, we propose a spatio-temporal disentangled visual adaptive refinement (ST-DVAR) and a multi-level video-guided emotion affine transformation (MV-EAT) to achieve preliminary refinement on video features and emotion lexicon to eliminate the noise caused by emotion-irrelevant visual information and video-irrelevant emotional information. Then, in the 2nd-round mutual learning, we exploit the cross-attention of the preliminary refined features and the original features to obtain the ultimate emotional cues and visual causes, and couple them in pair-wise extraction through contrastive loss. Overall, our approach optimizes complex semantic understanding and emotion perception of videos, leading to a promising performance in emotional captioning. Extensive experiments on three challenging datasets demonstrate the superiority of our approach and each proposed module, e.g., improving the latest records by +97.5% and +76.2% w.r.t. CIDEr and CFS, respectively, on the EVC-MSVD dataset.
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in visual understanding and multimodal reasoning. However, LVLMs frequently exhibit hallucination phenomena, manifesting as the generated textual responses that demonstrate inconsistencies with the provided visual content. Existing hallucination mitigation methods are predominantly text-centric, the challenges of visual-semantic alignment significantly limit their effectiveness, especially when confronted with fine-grained visual understanding scenarios. To this end, this paper presents ViHallu, a Vision-Centric Hallucination mitigation framework that enhances visual-semantic alignment through Visual Variation Image Generation and Visual Instruction Construction. ViHallu introduces visual variation images with controllable visual alterations while maintaining the overall image structure. These images, combined with carefully constructed visual instructions, enable LVLMs to better understand fine-grained visual content through fine-tuning, allowing models to more precisely capture the correspondence between visual content and text, thereby enhancing visual-semantic alignment. Extensive experiments on multiple benchmarks show that ViHallu effectively enhances models' fine-grained visual understanding while significantly reducing hallucination tendencies. Furthermore, we release ViHallu-Instruction, a visual instruction dataset specifically designed for hallucination mitigation and visual-semantic alignment. Code is available at https://github.com/oliviadzy/ViHallu.
Animated movies are captivating for their unique character designs and imaginative storytelling, yet they pose significant challenges for existing recognition systems. Unlike the consistent visual patterns detected by conventional face recognition methods, animated characters exhibit extreme diversity in their appearance, motion, and deformation. In this work, we propose an audio-visual pipeline to enable automatic and robust animated character recognition, and thereby enhance character-centric understanding of animated movies. Central to our approach is the automatic construction of an audio-visual character bank from online sources. This bank contains both visual exemplars and voice (audio) samples for each character, enabling subsequent multi-modal character recognition despite long-tailed appearance distributions. Building on accurate character recognition, we explore two downstream applications: Audio Description (AD) generation for visually impaired audiences, and character-aware subtitling for the hearing impaired. To support research in this domain, we introduce CMD-AM, a new dataset of 75 animated movies with comprehensive annotations. Our character-centric pipeline demonstrates significant improvements in both accessibility and narrative comprehension for animated content over prior face-detection-based approaches. For the code and dataset, visit https://www.robots.ox.ac.uk/~vgg/research/animated_ad/.
Learning with Noisy Labels (LNL) reduces reliance on high-quality labeled data but often overlooks open-set noise, where noisy samples belong to unknown classes, unlike closed-set noise within known categories.This paper advances LNL by reformulating the problem to incorporate open-set noise through a complete noise transition matrix, enabling a theoretical comparison of its impact on classification error rates against closed-set noise. Our analysis reveals that open-set noise induces smaller error increases, with distinct effects from 'hard' (semantically similar to inliers) and 'easy' (dissimilar) variants. We evaluate entropy-based detection, finding it effective only for easy open-set noise, and propose solutions leveraging vision-language models and self-supervised learning to address hard noise challenges. For empirical validation, we introduce CIFAR100-O, ImageNet-O, and a WebVision open-set test set, enabling robust benchmarking of LNL methods under open-set noise conditions. Recognizing classification accuracy's limitations in capturing model robustness, we advocate out-of-distribution (OOD) detection as a complementary metric. Our theoretical and empirical results highlight the unique challenges of open-set noise, offering new tools and evaluation frameworks to enhance LNL robustness in real-world scenarios.
Embodied artificial intelligence has rapidly developed under the impetus of multimodal learning, robotics, and cognitive science, demonstrating great potential in fields such as navigation and manipulation. However, building embodied agents that can robustly operate in diverse and dynamic environments still faces challenges, such as handling partial observability and environmental adaptability. Multimodal large language models (MLLMs) are vital for embodied intelligence due to their ability to process multimodal information, but they encounter difficulties in understanding spatial environments and performing dynamic decisions and evolution. Inspired by the functional specialization of the left and right hemispheres of the human brain, this paper proposes a brain-inspired learning and evolution paradigm for embodied agents. The method designs an embodied context-augmented MLLM to simulate the language processing and logical analysis capabilities of the left hemisphere, responsible for understanding instructions and visual scenes. At the same time, it constructs a perceptual context-guided world model based on the recurrent state space model to simulate the spatial perception and holistic thinking functions of the right hemisphere, capturing environmental dynamics and predicting future states. By simulating the communication function of the corpus callosum, we propose dynamic communication slots for efficient information exchange between MLLMs and the world model, which also allows the agent to quickly adapt to dynamic environments without requiring extensive computational resources. Experiments show that the proposed paradigm significantly improves the performance of embodied agents in a series of tasks and enhances their generalization ability in zero-shot tasks through embodied exploration experience and online evolution. Our project page is available at https://feliciaxyao.github.io/EvoAgent/.