Jian-Fang Hu

Haoxuan Chen, Xianqin Liu, Jian-Fang Hu

Spatio-Temporal Video Grounding aims to localize object tubes based on textual queries. While recent methods have achieved remarkable success, they mainly focus on high-quality(HQ) inputs, neglecting the widespread presence of low-quality(LQ) videos in real-world scenarios. Although tuning methods like LoRA can adapt to degraded inputs, they inevitably disrupt pre-trained knowledge. To address this, we propose Null-Space Tuning (NST). This framework exploits the geometric property that adding vectors within the null-space of frozen weights to the layer input does not affect the output. Leveraging this, NST injects learnable residuals into input features that can be selectively invisible to the pre-trained backbone. Specifically, NST combines the Quality-Adaptive Unit and Dual-Space Reparameterization to synthesize these residuals by confining components for HQ inputs to the null-space, while directing restoration components for LQ inputs to the non-null space. As the frozen weights eliminate null-space components, we effectively rectify degraded inputs while preserving pre-trained knowledge for HQ inputs. Extensive experiments show that NST outperforms state-of-the-art methods on our Mixed-Quality benchmark.

Yuan-Ming Li, Qize Yang, Nan Lei et al.

Recent advances in motion-aware large language models have shown remarkable promise for unifying motion understanding and generation tasks. However, these models typically treat understanding and generation separately, limiting the mutual benefits that could arise from interactive feedback between tasks. In this work, we reveal that motion assessment and refinement tasks act as crucial bridges to enable bidirectional knowledge flow between understanding and generation. Leveraging this insight, we propose Interleaved Reasoning for Motion Generation (IRMoGen), a novel paradigm that tightly couples motion generation with assessment and refinement through iterative text-motion dialogue. To realize this, we introduce IRG-MotionLLM, the first model that seamlessly interleaves motion generation, assessment, and refinement to improve generation performance. IRG-MotionLLM is developed progressively with a novel three-stage training scheme, initializing and subsequently enhancing native IRMoGen capabilities. To facilitate this development, we construct an automated data engine to synthesize interleaved reasoning annotations from existing text-motion datasets. Extensive experiments demonstrate that: (i) Assessment and refinement tasks significantly improve text-motion alignment; (ii) Interleaving motion generation, assessment, and refinement steps yields consistent performance gains across training stages; and (iii) IRG-MotionLLM clearly outperforms the baseline model and achieves advanced performance on standard text-to-motion generation benchmarks. Cross-evaluator testing further validates its effectiveness. Code & Data: https://github.com/HumanMLLM/IRG-MotionLLM/tree/main.

Xiaotong Lin, Tianming Liang, Jianhuang Lai et al.

Human trajectory prediction is a practical task of predicting the future positions of pedestrians on the road, which typically covers all temporal ranges from short-term to long-term within a trajectory. However, existing works attempt to address the entire trajectory prediction with a singular, uniform training paradigm, neglecting the distinction between short-term and long-term dynamics in human trajectories. To overcome this limitation, we introduce a novel Progressive Pretext Task learning (PPT) framework, which progressively enhances the model's capacity of capturing short-term dynamics and long-term dependencies for the final entire trajectory prediction. Specifically, we elaborately design three stages of training tasks in the PPT framework. In the first stage, the model learns to comprehend the short-term dynamics through a stepwise next-position prediction task. In the second stage, the model is further enhanced to understand long-term dependencies through a destination prediction task. In the final stage, the model aims to address the entire future trajectory task by taking full advantage of the knowledge from previous stages. To alleviate the knowledge forgetting, we further apply a cross-task knowledge distillation. Additionally, we design a Transformer-based trajectory predictor, which is able to achieve highly efficient two-step reasoning by integrating a destination-driven prediction strategy and a group of learnable prompt embeddings. Extensive experiments on popular benchmarks have demonstrated that our proposed approach achieves state-of-the-art performance with high efficiency. Code is available at https://github.com/iSEE-Laboratory/PPT.

Yuting Yang, Haichao Jiang, Tianming Liang et al.

Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past years, existing works always assume that the user-provided queries are already precise and clear. However, this assumption is impractical. In real-world scenarios, it is unrealistic to expect all users to thoroughly review their visual content and carefully ensure their queries are unique and unambiguous. When encountering such cases, existing segmentation models tend to arbitrarily guess the user preferences, often resulting in undesired outcomes. To address this limitation, we propose \textbf{IC-Seg}, a novel agentic framework that proactively clarifies user intent through multi-turn conversation before segmentation. To effectively incentivize this capability, we further introduce \textbf{Hi-GRPO}, a new hierarchical optimization strategy that injects dense and informative supervision signals at the trajectory, turn, and step levels. This strategy encourages efficient intent clarification, effectively eliminating redundant interactions and improving overall dialogue quality. For evaluation, we establish \textbf{Ambi-RVOS}, a referring video object segmentation benchmark with ambiguous user queries. Extensive experiments demonstrate that IC-Seg not only outperforms existing methods by a large margin in resolving ambiguous queries, but also maintains state-of-the-art performance on standard reasoning segmentation benchmarks. Code and data will be released at \url{https://github.com/iSEE-Laboratory/IC-Seg}.

Yi Zhang, Yulei Kang, Haoxuan Chen et al.

Parameter-efficient fine-tuning methods have gained considerable popularity for adapting large-scale models to downstream tasks, particularly LoRA and its variants. Existing methods perform low-rank adaptation over the full parameter space. However, fine-tuning within a subspace can achieve comparable effectiveness. Inspired by the observation that pre-trained models possess non-trivial null spaces, we propose Null-space based Low-Rank Adaptation (Null-LoRA). Null-LoRA effectively reduces redundancy and enhances effective rank by freezing portions of the low-rank matrices. To further improve parameter efficiency, Null-LoRA constrains the entire incremental update within the null space, maximizing the utilization of incremental updates to adapt to new task paradigms. Null-LoRA surpasses the state of the art with fewer parameters in extensive experiments across image-text retrieval and visual question answering tasks.

Tianming Liang, Qirui Du, Jian-Fang Hu et al.

Segmentation based on language has been a popular topic in computer vision. While recent advances in multimodal large language models (MLLMs) have endowed segmentation systems with reasoning capabilities, these efforts remain confined by the frozen internal knowledge of MLLMs, which limits their potential for real-world scenarios that involve up-to-date information or domain-specific concepts. In this work, we propose \textbf{Seg-ReSearch}, a novel segmentation paradigm that overcomes the knowledge bottleneck of existing approaches. By enabling interleaved reasoning and external search, Seg-ReSearch empowers segmentation systems to handle dynamic, open-world queries that extend beyond the frozen knowledge of MLLMs. To effectively train this capability, we introduce a hierarchical reward design that harmonizes initial guidance with progressive incentives, mitigating the dilemma between sparse outcome signals and rigid step-wise supervision. For evaluation, we construct OK-VOS, a challenging benchmark that explicitly requires outside knowledge for video object segmentation. Experiments on OK-VOS and two existing reasoning segmentation benchmarks demonstrate that our Seg-ReSearch improves state-of-the-art approaches by a substantial margin. Code and data will be released at https://github.com/iSEE-Laboratory/Seg-ReSearch.

Haoxuan Chen, Tianming Liang, Wei-Shi Zheng et al.

Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithms like GRPO often suffer from exploration collapse, where the models prematurely converge on a narrow set of high-scoring patterns, lacking the ability to explore new solutions. Recent efforts attempt to alleviate this by adding entropy regularization or diversity bonus. However, these approaches do not change the \textit{winner-takes-all} nature, where rollouts still compete for individual advantage rather than cooperating for maximizing global diversity. In this work, we propose Group Cooperative Policy Optimization (GCPO), which shifts the training paradigm from rollout competition to team cooperation. Specifically, GCPO replaces independent rollout scoring with team-level credit assignment: a rollout is rewarded by how much it contributes to the team's valid solution coverage, rather than its individual accuracy. This coverage is described as a determinant volume over reward-weighted semantic embeddings, where only correct and non-redundant rollouts contribute to this volume. During advantage estimation, GCPO redistributes the collective team reward to each single rollout according to its average marginal contribution to the team. This cooperative training paradigm routes optimization toward non-redundant correct reasoning paths. Experiments across multiple reasoning benchmarks demonstrate that GCPO significantly improves both reasoning accuracy and solution diversity over existing approaches. Code will be released at $\href{https://github.com/bradybuddiemarch/gcpo}{this}$.

Zihang Lin, Chaolei Tan, Jian-Fang Hu et al.

In this technical report, we introduce our solution to human-centric spatio-temporal video grounding task. We propose a concise and effective framework named STVGFormer, which models spatiotemporal visual-linguistic dependencies with a static branch and a dynamic branch. The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances. The dynamic branch performs cross-modal understanding across multiple frames. It learns to predict the starting and ending time of the target moment according to dynamic visual cues like motions. Both the static and dynamic branches are designed as cross-modal transformers. We further design a novel static-dynamic interaction block to enable the static and dynamic branches to transfer useful and complementary information from each other, which is shown to be effective to improve the prediction on hard cases. Our proposed method achieved 39.6% vIoU and won the first place in the HC-STVG track of the 4th Person in Context Challenge.

Chaolei Tan, Zihang Lin, Junfu Pu et al.

Video grounding is a fundamental problem in multimodal content understanding, aiming to localize specific natural language queries in an untrimmed video. However, current video grounding datasets merely focus on simple events and are either limited to shorter videos or brief sentences, which hinders the model from evolving toward stronger multimodal understanding capabilities. To address these limitations, we present a large-scale video grounding dataset named SynopGround, in which more than 2800 hours of videos are sourced from popular TV dramas and are paired with accurately localized human-written synopses. Each paragraph in the synopsis serves as a language query and is manually annotated with precise temporal boundaries in the long video. These paragraph queries are tightly correlated to each other and contain a wealth of abstract expressions summarizing video storylines and specific descriptions portraying event details, which enables the model to learn multimodal perception on more intricate concepts over longer context dependencies. Based on the dataset, we further introduce a more complex setting of video grounding dubbed Multi-Paragraph Video Grounding (MPVG), which takes as input multiple paragraphs and a long video for grounding each paragraph query to its temporal interval. In addition, we propose a novel Local-Global Multimodal Reasoner (LGMR) to explicitly model the local-global structures of long-term multimodal inputs for MPVG. Our method provides an effective baseline solution to the multi-paragraph video grounding problem. Extensive experiments verify the proposed model's effectiveness as well as its superiority in long-term multi-paragraph video grounding over prior state-of-the-arts. Dataset and code are publicly available. Project page: https://synopground.github.io/.

Jiangxin Sun, Feng Xue, Teng Long et al.

With advances in imitation learning (IL) and large-scale driving datasets, end-to-end autonomous driving (E2E-AD) has made great progress recently. Currently, IL-based methods have become a mainstream paradigm: models rely on standard driving behaviors given by experts, and learn to minimize the discrepancy between their actions and expert actions. However, this objective of "only driving like the expert" suffers from limited generalization: when encountering rare or unseen long-tail scenarios outside the distribution of expert demonstrations, models tend to produce unsafe decisions in the absence of prior experience. This raises a fundamental question: Can an E2E-AD system make reliable decisions without any expert action supervision? Motivated by this, we propose a unified framework named Risk-aware World Model Predictive Control (RaWMPC) to address this generalization dilemma through robust control, without reliance on expert demonstrations. Practically, RaWMPC leverages a world model to predict the consequences of multiple candidate actions and selects low-risk actions through explicit risk evaluation. To endow the world model with the ability to predict the outcomes of risky driving behaviors, we design a risk-aware interaction strategy that systematically exposes the world model to hazardous behaviors, making catastrophic outcomes predictable and thus avoidable. Furthermore, to generate low-risk candidate actions at test time, we introduce a self-evaluation distillation method to distill riskavoidance capabilities from the well-trained world model into a generative action proposal network without any expert demonstration. Extensive experiments show that RaWMPC outperforms state-of-the-art methods in both in-distribution and out-of-distribution scenarios, while providing superior decision interpretability.

Dian Zheng, Xiao-Ming Wu, Shuzhou Yang et al.

Universal image restoration is a practical and potential computer vision task for real-world applications. The main challenge of this task is handling the different degradation distributions at once. Existing methods mainly utilize task-specific conditions (e.g., prompt) to guide the model to learn different distributions separately, named multi-partite mapping. However, it is not suitable for universal model learning as it ignores the shared information between different tasks. In this work, we propose an advanced selective hourglass mapping strategy based on diffusion model, termed DiffUIR. Two novel considerations make our DiffUIR non-trivial. Firstly, we equip the model with strong condition guidance to obtain accurate generation direction of diffusion model (selective). More importantly, DiffUIR integrates a flexible shared distribution term (SDT) into the diffusion algorithm elegantly and naturally, which gradually maps different distributions into a shared one. In the reverse process, combined with SDT and strong condition guidance, DiffUIR iteratively guides the shared distribution to the task-specific distribution with high image quality (hourglass). Without bells and whistles, by only modifying the mapping strategy, we achieve state-of-the-art performance on five image restoration tasks, 22 benchmarks in the universal setting and zero-shot generalization setting. Surprisingly, by only using a lightweight model (only 0.89M), we could achieve outstanding performance. The source code and pre-trained models are available at https://github.com/iSEE-Laboratory/DiffUIR

Heng Li, Xiaotong Lin, Ling-An Zeng et al.

Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich in fine-grained detail. Although recent approaches can produce complex and natural movements, they usually operate at only one temporal scale, which limits both semantic alignment and temporal coherence. Inspired by the fact that complex motions are conceptualized hierarchically rather than at a single temporal scale in the human cognitive system, we propose \textit{MotionHiFlow}, a hierarchical flow matching framework to generate motion progressively by constructing flow path from low to high temporal scales. The flows at lower scales capture high-level semantics and coarse motion structures, while flows at higher scales refine temporal details. To link the flows across scales, we introduce a novel cross-scale transition process, ensuring continuity and preserving noise consistency. Furthermore, by integrating a Text-Motion Diffusion Transformer and a topology-aware Motion VAE, MotionHiFlow explicitly models structural dependencies among joints via joint-aware positional encoding and skeletal topology, enabling precise semantic alignment alongside fine-grained motion details. Extensive experiments on HumanML3D and KIT-ML benchmarks demonstrate state-of-the-art performance, with ablation studies confirming the effectiveness of the hierarchical design and key components. Code is available at https://github.com/ai-lh/MotionHiFlow.

Jin Li, Ziqiang He, Anwei Luo et al.

Imperceptible adversarial attacks aim to fool DNNs by adding imperceptible perturbation to the input data. Previous methods typically improve the imperceptibility of attacks by integrating common attack paradigms with specifically designed perception-based losses or the capabilities of generative models. In this paper, we propose Adversarial Attacks in Diffusion (AdvAD), a novel modeling framework distinct from existing attack paradigms. AdvAD innovatively conceptualizes attacking as a non-parametric diffusion process by theoretically exploring basic modeling approach rather than using the denoising or generation abilities of regular diffusion models requiring neural networks. At each step, much subtler yet effective adversarial guidance is crafted using only the attacked model without any additional network, which gradually leads the end of diffusion process from the original image to a desired imperceptible adversarial example. Grounded in a solid theoretical foundation of the proposed non-parametric diffusion process, AdvAD achieves high attack efficacy and imperceptibility with intrinsically lower overall perturbation strength. Additionally, an enhanced version AdvAD-X is proposed to evaluate the extreme of our novel framework under an ideal scenario. Extensive experiments demonstrate the effectiveness of the proposed AdvAD and AdvAD-X. Compared with state-of-the-art imperceptible attacks, AdvAD achieves an average of 99.9$\%$ (+17.3$\%$) ASR with 1.34 (-0.97) $l_2$ distance, 49.74 (+4.76) PSNR and 0.9971 (+0.0043) SSIM against four prevalent DNNs with three different architectures on the ImageNet-compatible dataset. Code is available at https://github.com/XianguiKang/AdvAD.

Jianwei Tang, Jiangxin Sun, Xiaotong Lin et al.

Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning of short-term predictions is hindered by the focus on long-term predictions, and the incorporation of prior information from past predictions into subsequent predictions is limited. In this paper, we introduce a novel multi-stage training framework called Temporal Continual Learning (TCL) to address the above challenges. To better preserve prior information, we introduce the Prior Compensation Factor (PCF). We incorporate it into the model training to compensate for the lost prior information. Furthermore, we derive a more reasonable optimization objective through theoretical derivation. It is important to note that our TCL framework can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on four HMP benchmark datasets demonstrate the effectiveness and flexibility of TCL. The code is available at https://github.com/hyqlat/TCL.

Haichao Jiang, Tianming Liang, Wei-Shi Zheng et al.

Referring Video Object Segmentation (RVOS) aims to segment objects in videos based on textual queries. Current methods mainly rely on large-scale supervised fine-tuning (SFT) of Multi-modal Large Language Models (MLLMs). However, this paradigm suffers from heavy data dependence and limited scalability against the rapid evolution of MLLMs. Although recent zero-shot approaches offer a flexible alternative, their performance remains significantly behind SFT-based methods, due to the straightforward workflow designs. To address these limitations, we propose \textbf{Refer-Agent}, a collaborative multi-agent system with alternating reasoning-reflection mechanisms. This system decomposes RVOS into step-by-step reasoning process. During reasoning, we introduce a Coarse-to-Fine frame selection strategy to ensure the frame diversity and textual relevance, along with a Dynamic Focus Layout that adaptively adjusts the agent's visual focus. Furthermore, we propose a Chain-of-Reflection mechanism, which employs a Questioner-Responder pair to generate a self-reflection chain, enabling the system to verify intermediate results and generates feedback for next-round reasoning refinement. Extensive experiments on five challenging benchmarks demonstrate that Refer-Agent significantly outperforms state-of-the-art methods, including both SFT-based models and zero-shot approaches. Moreover, Refer-Agent is flexible and enables fast integration of new MLLMs without any additional fine-tuning costs. Code will be released.

Wei-Jin Huang, Yuan-Ming Li, Zhi-Wei Xia et al.

Error detection in procedural activities is essential for consistent and correct outcomes in AR-assisted and robotic systems. Existing methods often focus on temporal ordering errors or rely on static prototypes to represent normal actions. However, these approaches typically overlook the common scenario where multiple, distinct actions are valid following a given sequence of executed actions. This leads to two issues: (1) the model cannot effectively detect errors using static prototypes when the inference environment or action execution distribution differs from training; and (2) the model may also use the wrong prototypes to detect errors if the ongoing action label is not the same as the predicted one. To address this problem, we propose an Adaptive Multiple Normal Action Representation (AMNAR) framework. AMNAR predicts all valid next actions and reconstructs their corresponding normal action representations, which are compared against the ongoing action to detect errors. Extensive experiments demonstrate that AMNAR achieves state-of-the-art performance, highlighting the effectiveness of AMNAR and the importance of modeling multiple valid next actions in error detection. The code is available at https://github.com/iSEE-Laboratory/AMNAR.

Ling-An Zeng, Gaojie Wu, Ancong Wu et al.

Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely describing diverse postures. To achieve more controllable generation, an intuitive way is to allow the user to input a few motion frames describing precise desired postures. Thus, we explore a new Text-Frame-to-Motion (TF2M) generation task that aims to generate motions from text and very few given frames. Intuitively, the closer a frame is to a given frame, the lower the uncertainty of this frame is when conditioned on this given frame. Hence, we propose a novel Progressive Motion Generation (PMG) method to progressively generate a motion from the frames with low uncertainty to those with high uncertainty in multiple stages. During each stage, new frames are generated by a Text-Frame Guided Generator conditioned on frame-aware semantics of the text, given frames, and frames generated in previous stages. Additionally, to alleviate the train-test gap caused by multi-stage accumulation of incorrectly generated frames during testing, we propose a Pseudo-frame Replacement Strategy for training. Experimental results show that our PMG outperforms existing T2M generation methods by a large margin with even one given frame, validating the effectiveness of our PMG. Code is available at https://github.com/qinghuannn/PMG.

Yulei Kang, Tianze Zhu, Jian-Fang Hu et al.

In-the-wild 3D Gaussian Splatting remains challenging due to transient distractors and illumination-induced cross-view appearance inconsistencies. Existing methods mainly rely on image-level masking to suppress unreliable supervision, but masking alone cannot fully eliminate residual occlusions or resolve illumination-induced inconsistencies, both of which can introduce conflicting cross-view gradients. These unresolved conflicts may destabilize Gaussian optimization and lead to visible reconstruction artifacts. We propose a conflict-aware 3DGS framework that addresses this problem from both image-space supervision and gradient-level optimization. Semantic Consistency-Guided Masking learns pixel-wise consistency scores to adaptively refine prior masks and suppress unreliable supervision before gradient formation. A dual-view Conflict-Aware Gradient Harmonization strategy further reconciles view-specific gradients by mutually rotating them into an orthogonal configuration, reducing negative directional interference across views. We also introduce conflict-aware densification and pruning to stabilize Gaussian growth and remove persistently conflicting primitives. Extensive experiments on standard in-the-wild benchmarks demonstrate that our method achieves state-of-the-art rendering quality under complex transient distractors and cross-view inconsistencies.

Tianming Liang, Haichao Jiang, Wei-Shi Zheng et al.

Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-agent interaction. Recently, ReferDINO has demonstrated promising performance in this task by adapting object-level vision-language knowledge from pretrained foundational image models. In this report, we further enhance its capabilities by incorporating the advantages of SAM2 in mask quality and object consistency. In addition, to effectively balance performance between single-object and multi-object scenarios, we introduce a conditional mask fusion strategy that adaptively fuses the masks from ReferDINO and SAM2. Our solution, termed ReferDINO-Plus, achieves 60.43 \(\mathcal{J}\&\mathcal{F}\) on MeViS test set, securing 2nd place in the MeViS PVUW challenge at CVPR 2025. The code is available at: https://github.com/iSEE-Laboratory/ReferDINO-Plus.

Mingyu Liu, Sihan Huang, Yijia Fan et al.

Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triplets. Projection-based ZS-CIR methods are attractive because they do not rely on LLMs at inference and remain lightweight, but they often underperform LLM-based approaches on complex semantic modifications. This gap reflects a semantic transition bottleneck in projection-based ZS-CIR: endpoint-level matching can let the edit text act as a target-side attribute cue rather than grounding it as a source-conditioned semantic transition. We further show that adding semantic transition supervision to the same text adapter creates an endpoint--transition conflict between endpoint alignment and semantic transition alignment. To address this conflict, DeCIR decouples endpoint and transition learning. It constructs paired forward/reverse edit tuples from image-caption pairs, trains separate low-rank text adapter branches for endpoint alignment and semantic transition alignment, and merges them with Low-Rank Directional Merge (LRDM) into one deployable adapter. Extensive experiments on CIRR, CIRCO, FashionIQ, and GeneCIS demonstrate that DeCIR consistently improves projection-based ZS-CIR without increasing inference complexity.

Jinxuan Li, Yi Zhang, Jian-Fang Hu et al.

Spatio-Temporal Video Grounding (STVG) aims to localize a spatio-temporal tube that corresponds to a given language query in an untrimmed video. This is a challenging task since it involves complex vision-language understanding and spatiotemporal reasoning. Recent works have explored weakly-supervised setting in STVG to eliminate reliance on fine-grained annotations like bounding boxes or temporal stamps. However, they typically follow a simple late-fusion manner, which generates tubes independent of the text description, often resulting in failed target identification and inconsistent target tracking. To address this limitation, we propose a Tube-conditioned Reconstruction with Mutual Constraints (\textbf{TubeRMC}) framework that generates text-conditioned candidate tubes with pre-trained visual grounding models and further refine them via tube-conditioned reconstruction with spatio-temporal constraints. Specifically, we design three reconstruction strategies from temporal, spatial, and spatio-temporal perspectives to comprehensively capture rich tube-text correspondences. Each strategy is equipped with a Tube-conditioned Reconstructor, utilizing spatio-temporal tubes as condition to reconstruct the key clues in the query. We further introduce mutual constraints between spatial and temporal proposals to enhance their quality for reconstruction. TubeRMC outperforms existing methods on two public benchmarks VidSTG and HCSTVG. Further visualization shows that TubeRMC effectively mitigates both target identification errors and inconsistent tracking.

Tianming Liang, Kun-Yu Lin, Chaolei Tan et al.

Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existing methods still exhibit a noticeable gap when considering all these aspects. In this work, we propose \textbf{ReferDINO}, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixel-level dense perception and cross-modal spatiotemporal reasoning. In detail, ReferDINO integrates two key components: 1) a grounding-guided deformable mask decoder that utilizes location prediction to progressively guide mask prediction through differentiable deformation mechanisms; 2) an object-consistent temporal enhancer that injects pretrained time-varying text features into inter-frame interaction to capture object-aware dynamic changes. Moreover, a confidence-aware query pruning strategy is designed to accelerate object decoding without compromising model performance. Extensive experimental results on five benchmarks demonstrate that our ReferDINO significantly outperforms previous methods (e.g., +3.9% (\mathcal{J}&\mathcal{F}) on Ref-YouTube-VOS) with real-time inference speed (51 FPS).

Chaolei Tan, Jianhuang Lai, Wei-Shi Zheng et al.

Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG approaches are heavily reliant on a considerable number of temporal labels that are laborious and time-consuming to acquire. In this work, we introduce and explore Weakly-Supervised Video Paragraph Grounding (WSVPG) to eliminate the need of temporal annotations. Different from previous weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG. Specifically, we devise a Siamese Grounding TRansformer (SiamGTR) consisting of two weight-sharing branches for learning complementary supervision. An Augmentation Branch is utilized for directly regressing the temporal boundaries of a complete paragraph within a pseudo video, and an Inference Branch is designed to capture the order-guided feature correspondence for localizing multiple sentences in a normal video. We demonstrate by extensive experiments that our paradigm has superior practicability and flexibility to achieve efficient weakly-supervised or semi-supervised learning, outperforming state-of-the-art methods trained with the same or stronger supervision.

Yi Zhang, Yulei Kang, Jian-Fang Hu

High-fidelity reconstruction of dynamic scenes is an important yet challenging problem. While recent 4D Gaussian Splatting (4DGS) has demonstrated the ability to model temporal dynamics, it couples Gaussian motion and geometric attributes within a single covariance formulation, which limits its expressiveness for complex motions and often leads to visual artifacts. To address this, we propose VeGaS, a novel velocity-based 4D Gaussian Splatting framework that decouples Gaussian motion and geometry. Specifically, we introduce a Galilean shearing matrix that explicitly incorporates time-varying velocity to flexibly model complex non-linear motions, while strictly isolating the effects of Gaussian motion from the geometry-related conditional Gaussian covariance. Furthermore, a Geometric Deformation Network is introduced to refine Gaussian shapes and orientations using spatio-temporal context and velocity cues, enhancing temporal geometric modeling. Extensive experiments on public datasets demonstrate that VeGaS achieves state-of-the-art performance.

Yuan-Ming Li, An-Lan Wang, Kun-Yu Lin et al.

To guide a learner in mastering action skills, it is crucial for a coach to 1) reason through the learner's action execution and technical points (TechPoints), and 2) provide detailed, comprehensible feedback on what is done well and what can be improved. However, existing score-based action assessment methods are still far from reaching this practical scenario. To bridge this gap, we investigate a new task termed Descriptive Action Coaching (DescCoach) which requires the model to provide detailed commentary on what is done well and what can be improved beyond a simple quality score for action execution. To this end, we first build a new dataset named EE4D-DescCoach. Through an automatic annotation pipeline, our dataset goes beyond the existing action assessment datasets by providing detailed TechPoint-level commentary. Furthermore, we propose TechCoach, a new framework that explicitly incorporates TechPoint-level reasoning into the DescCoach process. The central to our method lies in the Context-aware TechPoint Reasoner, which enables TechCoach to learn TechPoint-related quality representation by querying visual context under the supervision of TechPoint-level coaching commentary. By leveraging the visual context and the TechPoint-related quality representation, a unified TechPoint-aware Action Assessor is then employed to provide the overall coaching commentary together with the quality score. Combining all of these, we establish a new benchmark for DescCoach and evaluate the effectiveness of our method through extensive experiments. The data and code will be made publicly available.

Shenghao Fu, Qize Yang, Yuan-Ming Li et al.

Recent advances in Large Multi-modal Models (LMMs) are primarily focused on offline video understanding. Instead, streaming video understanding poses great challenges to recent models due to its time-sensitive, omni-modal and interactive characteristics. In this work, we aim to extend the streaming video understanding from a new perspective and propose a novel task named Visual Instruction Feedback in which models should be aware of visual contents and learn to extract instructions from them. For example, when users wave their hands to agents, agents should recognize the gesture and start conversations with welcome information. Thus, following instructions in visual modality greatly enhances user-agent interactions. To facilitate research, we define seven key subtasks highly relevant to visual modality and collect the ViSpeak-Instruct dataset for training and the ViSpeak-Bench for evaluation. Further, we propose the ViSpeak model, which is a SOTA streaming video understanding LMM with GPT-4o-level performance on various streaming video understanding benchmarks. After finetuning on our ViSpeak-Instruct dataset, ViSpeak is equipped with basic visual instruction feedback ability, serving as a solid baseline for future research.

Dian Zheng, Cheng Zhang, Xiao-Ming Wu et al.

Generating 360-degree panoramas from narrow field of view (NFoV) image is a promising computer vision task for Virtual Reality (VR) applications. Existing methods mostly assess the generated panoramas with InceptionNet or CLIP based metrics, which tend to perceive the image quality and is \textbf{not suitable for evaluating the distortion}. In this work, we first propose a distortion-specific CLIP, named Distort-CLIP to accurately evaluate the panorama distortion and discover the \textbf{``visual cheating''} phenomenon in previous works (\ie, tending to improve the visual results by sacrificing distortion accuracy). This phenomenon arises because prior methods employ a single network to learn the distinct panorama distortion and content completion at once, which leads the model to prioritize optimizing the latter. To address the phenomenon, we propose \textbf{PanoDecouple}, a decoupled diffusion model framework, which decouples the panorama generation into distortion guidance and content completion, aiming to generate panoramas with both accurate distortion and visual appeal. Specifically, we design a DistortNet for distortion guidance by imposing panorama-specific distortion prior and a modified condition registration mechanism; and a ContentNet for content completion by imposing perspective image information. Additionally, a distortion correction loss function with Distort-CLIP is introduced to constrain the distortion explicitly. The extensive experiments validate that PanoDecouple surpasses existing methods both in distortion and visual metrics.

Xing Liufu, Chaolei Tan, Xiaotong Lin et al.

Edge labels are typically at various granularity levels owing to the varying preferences of annotators, thus handling the subjectivity of per-pixel labels has been a focal point for edge detection. Previous methods often employ a simple voting strategy to diminish such label uncertainty or impose a strong assumption of labels with a pre-defined distribution, e.g., Gaussian. In this work, we unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our key insight is that the intermediate SAM features inherently correspond to object edges at various granularities, which reflects different edge options due to uncertainty. Therefore, we attempt to align uncertainty with granularity by regressing intermediate SAM features from different layers to object edges at multi-granularity levels. In doing so, the model can fully and explicitly explore diverse ``uncertainties'' in a data-driven fashion. Specifically, we inject a lightweight module (~ 1.5% additional parameters) into the frozen SAM to progressively fuse and adapt its intermediate features to estimate edges from coarse to fine. It is crucial to normalize the granularity level of human edge labels to match their innate uncertainty. For this, we simply perform linear blending to the real edge labels at hand to create pseudo labels with varying granularities. Consequently, our uncertainty-aligned edge detector can flexibly produce edges at any desired granularity (including an optimal one). Thanks to SAM, our model uniquely demonstrates strong generalizability for cross-dataset edge detection. Extensive experimental results on BSDS500, Muticue and NYUDv2 validate our model's superiority.

Henghui Ding, Chang Liu, Nikhila Ravi et al.

This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The challenge features two tracks: MOSE, which focuses on complex scene video object segmentation, and MeViS, which targets motion-guided, language-based video segmentation. Both tracks introduce new, more challenging datasets designed to better reflect real-world scenarios. Through detailed evaluation and analysis, the challenge offers valuable insights into the current state-of-the-art and emerging trends in complex video segmentation. More information can be found on the workshop website: https://pvuw.github.io/.

Tianming Liang, Haichao Jiang, Yuting Yang et al.

Referring video object segmentation (RVOS) aims to identify, track and segment the objects in a video based on language descriptions, which has received great attention in recent years. However, existing datasets remain focus on short video clips within several seconds, with salient objects visible in most frames. To advance the task towards more practical scenarios, we introduce \textbf{Long-RVOS}, a large-scale benchmark for long-term referring video object segmentation. Long-RVOS contains 2,000+ videos of an average duration exceeding 60 seconds, covering a variety of objects that undergo occlusion, disappearance-reappearance and shot changing. The objects are manually annotated with three different types of descriptions to individually evaluate the understanding of static attributes, motion patterns and spatiotemporal relationships. Moreover, unlike previous benchmarks that rely solely on the per-frame spatial evaluation, we introduce two new metrics to assess the temporal and spatiotemporal consistency. We benchmark 6 state-of-the-art methods on Long-RVOS. The results show that current approaches struggle severely with the long-video challenges. To address this, we further propose ReferMo, a promising baseline method that integrates motion information to expand the temporal receptive field, and employs a local-to-global architecture to capture both short-term dynamics and long-term dependencies. Despite simplicity, ReferMo achieves significant improvements over current methods in long-term scenarios. We hope that Long-RVOS and our baseline can drive future RVOS research towards tackling more realistic and long-form videos.

Jinxuan Li, Chaolei Tan, Haoxuan Chen et al.

Image-Language Foundation Models (ILFM) have demonstrated remarkable success in image-text understanding/generation tasks, providing transferable multimodal representations that generalize across diverse downstream image-based tasks. The advancement of video-text research has spurred growing interest in extending image-based models to the video domain. This paradigm, known as image-to-video transfer learning, succeeds in alleviating the substantial data and computational requirements associated with training video-language foundation models from scratch for video-text learning. This survey provides the first comprehensive review of this emerging field, which begins by summarizing the widely used ILFM and their capabilities. We then systematically classify existing image-to-video transfer learning strategies into two categories: frozen features and modified features, depending on whether the original representations from ILFM are preserved or undergo modifications. Building upon the task-specific nature of image-to-video transfer, this survey methodically elaborates these strategies and details their applications across a spectrum of video-text learning tasks, ranging from fine-grained (e.g., spatio-temporal video grounding) to coarse-grained (e.g., video question answering). We further present a detailed experimental analysis to investigate the efficacy of different image-to-video transfer learning paradigms on a range of downstream video understanding tasks. Finally, we identify prevailing challenges and highlight promising directions for future research. By offering a comprehensive and structured overview, this survey aims to establish a structured roadmap for advancing video-text learning based on existing ILFM, and to inspire future research directions in this rapidly evolving domain.

Tianming Liang, Chaolei Tan, Beihao Xia et al.

This paper focuses on open-ended video question answering, which aims to find the correct answers from a large answer set in response to a video-related question. This is essentially a multi-label classification task, since a question may have multiple answers. However, due to annotation costs, the labels in existing benchmarks are always extremely insufficient, typically one answer per question. As a result, existing works tend to directly treat all the unlabeled answers as negative labels, leading to limited ability for generalization. In this work, we introduce a simple yet effective ranking distillation framework (RADI) to mitigate this problem without additional manual annotation. RADI employs a teacher model trained with incomplete labels to generate rankings for potential answers, which contain rich knowledge about label priority as well as label-associated visual cues, thereby enriching the insufficient labeling information. To avoid overconfidence in the imperfect teacher model, we further present two robust and parameter-free ranking distillation approaches: a pairwise approach which introduces adaptive soft margins to dynamically refine the optimization constraints on various pairwise rankings, and a listwise approach which adopts sampling-based partial listwise learning to resist the bias in teacher ranking. Extensive experiments on five popular benchmarks consistently show that both our pairwise and listwise RADIs outperform state-of-the-art methods. Further analysis demonstrates the effectiveness of our methods on the insufficient labeling problem.

Xiaotong Lin, Tianming Liang, Jian-Fang Hu et al.

3D human-object interaction (HOI) anticipation aims to predict the future motion of humans and their manipulated objects, conditioned on the historical context. Generally, the articulated humans and rigid objects exhibit different motion patterns, due to their distinct intrinsic physical properties. However, this distinction is ignored by most of the existing works, which intend to capture the dynamics of both humans and objects within a single prediction model. In this work, we propose a novel contact-consistent decoupled diffusion framework CoopDiff, which employs two distinct branches to decouple human and object motion modeling, with the human-object contact points as shared anchors to bridge the motion generation across branches. The human dynamics branch is aimed to predict highly structured human motion, while the object dynamics branch focuses on the object motion with rigid translations and rotations. These two branches are bridged by a series of shared contact points with consistency constraint for coherent human-object motion prediction. To further enhance human-object consistency and prediction reliability, we propose a human-driven interaction module to guide object motion modeling. Extensive experiments on the BEHAVE and Human-object Interaction datasets demonstrate that our CoopDiff outperforms state-of-the-art methods.

Jianwei Tang, Hong Yang, Tengyue Chen et al.

Action-driven stochastic human motion prediction aims to generate future motion sequences of a pre-defined target action based on given past observed sequences performing non-target actions. This task primarily presents two challenges. Firstly, generating smooth transition motions is hard due to the varying transition speeds of different actions. Secondly, the action characteristic is difficult to be learned because of the similarity of some actions. These issues cause the predicted results to be unreasonable and inconsistent. As a result, we propose two memory banks, the Soft-transition Action Bank (STAB) and Action Characteristic Bank (ACB), to tackle the problems above. The STAB stores the action transition information. It is equipped with the novel soft searching approach, which encourages the model to focus on multiple possible action categories of observed motions. The ACB records action characteristic, which produces more prior information for predicting certain actions. To fuse the features retrieved from the two banks better, we further propose the Adaptive Attention Adjustment (AAA) strategy. Extensive experiments on four motion prediction datasets demonstrate that our approach consistently outperforms the previous state-of-the-art. The demo and code are available at https://hyqlat.github.io/STABACB.github.io/.

Yaokun Zhong, Siyu Jiang, Jian Zhu et al.

Semi-Supervised Video Paragraph Grounding (SSVPG) aims to localize multiple sentences in a paragraph from an untrimmed video with limited temporal annotations. Existing methods focus on teacher-student consistency learning and video-level contrastive loss, but they overlook the importance of perturbing query contexts to generate strong supervisory signals. In this work, we propose a novel Context Consistency Learning (CCL) framework that unifies the paradigms of consistency regularization and pseudo-labeling to enhance semi-supervised learning. Specifically, we first conduct teacher-student learning where the student model takes as inputs strongly-augmented samples with sentences removed and is enforced to learn from the adequately strong supervisory signals from the teacher model. Afterward, we conduct model retraining based on the generated pseudo labels, where the mutual agreement between the original and augmented views' predictions is utilized as the label confidence. Extensive experiments show that CCL outperforms existing methods by a large margin.

Chaolei Tan, Zihang Lin, Jian-Fang Hu et al.

We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an Augmented 2D Temporal Adjacent Network (Augmented 2D-TAN) to temporally ground the target moment corresponding to the given description. Primarily, we improve the original 2D-TAN from two aspects: First, a temporal context-aware Bi-LSTM Aggregation Module is developed to aggregate clip-level representations, replacing the original max-pooling. Second, we propose to employ Random Concatenation Augmentation (RCA) mechanism during the training phase. In the second stage, we use pretrained MDETR model to generate per-frame bounding boxes via language query, and design a set of hand-crafted rules to select the best matching bounding box outputted by MDETR for each frame within the grounded moment.

Jiafeng Xie, Bing Shuai, Jian-Fang Hu et al.

Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their application scenarios in practice. Meanwhile, existing fast segmentation models usually fail to obtain satisfactory segmentation accuracies on public benchmarks. In this paper, we propose a teacher-student learning framework that transfers the knowledge gained by a heavy and better performed segmentation network (i.e. teacher) to guide the learning of fast segmentation networks (i.e. student). Specifically, both zero-order and first-order knowledge depicted in the fine annotated images and unlabeled auxiliary data are transferred to regularize our student learning. The proposed method can improve existing fast segmentation models without incurring extra computational overhead, so it can still process images with the same fast speed. Extensive experiments on the Pascal Context, Cityscape and VOC 2012 datasets demonstrate that the proposed teacher-student learning framework is able to significantly boost the performance of student network.

Yongyi Tang, Peizhen Zhang, Jian-Fang Hu et al.

Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene. Previ- ous state-of-the-art methods using hand-crafted potentials in conventional graphical model which can only define a limited range of relations. Thus, the complex structural de- pendencies among individuals involved in a collective sce- nario cannot be fully modeled. In this paper, we overcome these limitations by embedding latent variables into feature space and learning the feature mapping functions in a deep learning framework. The embeddings of latent variables build a global relation containing person-group interac- tions and richer contextual information by jointly modeling broader range of individuals. Besides, we assemble atten- tion mechanism during embedding for achieving more com- pact representations. We evaluate our method on three col- lective activity datasets, where we contribute a much larger dataset in this work. The proposed model has achieved clearly better performance as compared to the state-of-the- art methods in our experiments.