论文检索

Jihun Kim, Hoyong Kwon, Hyeokjun Kweon, Kuk-Jin Yoon

Fully supervised Video Semantic Segmentation (VSS) relies heavily on densely annotated video data, limiting practical applicability. Alternatively, applying pre-trained Image Semantic Segmentation (ISS) models frame-by-frame avoids annotation costs but ignores crucial temporal coherence. Recent foundation models such as SAM2 enable high-quality mask propagation yet remain impractical for direct VSS due to limited semantic understanding and computational overhead. In this paper, we propose DiTTA (Distillation-assisted Test-Time Adaptation), a novel framework that converts an ISS model into a temporally-aware VSS model through efficient test-time adaptation (TTA), without annotated videos. DiTTA distills SAM2's temporal segmentation knowledge into the ISS model during a brief, single-pass initialization phase, complemented by a lightweight temporal fusion module to aggregate cross-frame context. Crucially, DiTTA achieves robust generalization even when adapting with highly limited partial video snippets (e.g., initial 10%), significantly outperforming zero-shot refinement approaches that repeatedly invoke SAM2 during inference. Extensive experiments on VSPW and Cityscapes demonstrate DiTTA's effectiveness, achieving competitive or superior performance relative to fully-supervised VSS methods, thus providing a practical and annotation-free solution for real-world VSS tasks.

Yusong Wang, Zheyuan Gu, Keyu Mao, Minghao Shao, Mingkun Xu, Prayag Tiwari, Jiawei Shao, Qingsong Zhao

Crime anticipation enables proactive public safety interventions, yet existing video security systems remain largely reactive, unable to detect precursors of crime. While current visual language models (VLM)-based video understanding methods show promise in high-level reasoning, they are not designed to explicitly model the spatio-temporal causal relationships essential for anticipating crimes. We address this limitation by two causal-driven components. First, we develop the Spatio-Temporal Causal Reasoning Crime (STCRC) dataset, a hierarchical dataset comprising 73K samples across five progressive causal reasoning tasks, facilitating criminal precursors learning. Second, we propose the Spatio-Temporal Causal Hypergraph (STCH), a streaming module that transforms implicit entity dynamics into explicit causal structures to enhance causal reasoning for crime in VLMs. By combining these two components, our framework advances real-time crime anticipation, achieving improvements in anticipatory tasks: a 70.7% relative improvement in crime classification, a 10.1% in crime detection, and a 3.7% reduction in temporal prediction error.

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 only on the referred object (typically the actor), even when the expression clearly describes an interaction involving multiple objects with distinct roles. In this paper, we introduce Interaction-Aware Referring Video Object Segmentation (InterRVOS), a novel task that focuses on explicit interaction modeling by requiring separate segmentation of actor and target objects.This formulation enables fine-grained understanding of object relationships, as many video events are defined by such interactions rather than individual objects. We present InterRVOS-127K, a large-scale dataset of over 127K automatically annotated expressions with distinct actor-target mask pairs, and propose ReVIOSa, a MLLM-based architecture that introduces interaction-aware special tokens and attention mask loss (AML) to enhance interaction-aware segmentation. We also propose a new evaluation protocol that separately evaluates actor and target segmentation for more accurate role distinction. Comprehensive experiments demonstrate that ReVIOSa outperforms existing baselines on the proposed InterRVOS-127K benchmark, with further analyses validating the necessity and effectiveness of both ReVIOSa and InterRVOS-127K.

Jiaer Xia, Peixian Chen, Mengdan Zhang, Xing Sun, Kaiyang Zhou

We present Streamo, a real-time streaming video LLM that serves as a general-purpose interactive assistant. Unlike existing online video models that focus narrowly on question answering or captioning, Streamo performs a broad spectrum of streaming video tasks, including real-time narration, action understanding, event captioning, temporal event grounding, and time-sensitive question answering. To develop such versatility, we construct Streamo-Instruct-465K, a large-scale instruction-following dataset tailored for streaming video understanding. The dataset covers diverse temporal contexts and multi-task supervision, enabling unified training across heterogeneous streaming tasks. After training end-to-end on the instruction-following dataset through a streamlined pipeline, Streamo exhibits strong temporal reasoning, responsive interaction, and broad generalization across a variety of streaming benchmarks. Extensive experiments show that Streamo bridges the gap between offline video perception models and real-time multimodal assistants, making a step toward unified, intelligent video understanding in continuous video streams.

Xinhang Liu, Pedro Miraldo, Suhas Lohit, Huaizu Jiang, Naoko Sawada, Yu-Wing Tai, Chi-Keung Tang, Moitreya Chatterjee

Understanding how the 3D world evolves over time is a fundamental task in computer vision, essential for embodied settings, autonomous driving, etc. It requires not only the reconstruction of the observed scene but also the anticipation of how the scene dynamics will unfold in the future. While the area of 3D reconstruction has progressed rapidly with the advent of recent feed-forward neural networks, forecasting future dynamics in 3D, given the 2D frames of a video remains unexplored. We present Point4Cast, a unified framework that processes streaming 2D frame sequences of a video to estimate the past, present, and future of the underlying dynamic scene, in 3D. At the core of our approach lies a persistently evolving latent spacetime representation that models the environment's evolution across time. Upon receiving a new 2D frame, an update operation integrates the incoming evidence to refine the latent spacetime representation. When queried for any time instant, whether before, at, or beyond the timestamp of the last update. A readout procedure predicts temporally conditioned point maps and camera parameters describing the scene geometry at the queried time. Unlike prior approaches for online dynamic scene reconstruction that estimate each frame's point map solely at the timestamp of the last observed frame, Point4Cast achieves coherent reconstruction across any queried time. Empirical evaluations show that Point4Cast achieves state-of-the-art performance on streaming dynamic scene reconstruction and forecasting benchmarks, across multiple challenging datasets, while providing scene flow estimation and forecasting for free. The code will be released publicly.

Bowen Sun, Yujun Cai, Ming-Hsuan Yang, Hang Wu, Yiwei Wang

Video LLMs suffer from temporal inconsistency: small shifts in frame timing can flip attention and suppress relevant frames. We trace this instability to the common extension of Rotary Position Embeddings to video through multimodal RoPE. The induced inverse Fourier time kernel exhibits frame-scale ripples that multiply adjacent frames by different factors, which perturbs attention that should otherwise be governed by the raw query key inner product. We present Phase Aggregated Smoothing (PAS), a simple, training-free mechanism that applies small opposed phase offsets across heads and then aggregates their outputs. PAS preserves the per-head spectrum magnitude, while the aggregation effectively smooths the temporal kernel and reduces phase sensitivity without changing the positional encoding structure. Our analysis shows that the RoPE rotated logit can be approximated as a content dot product scaled by a time kernel; smoothing this kernel yields Lipschitz stability of attention to small temporal shifts; multi phase averaging attenuates high frequency ripples while preserving per-head spectra under Nyquist-valid sampling. Experiments on multiple video understanding benchmarks under matched token budgets show consistent improvements with negligible computational overhead. PAS provides a plug and play upgrade for robust temporal encoding in Video LLMs.

Jing Huang, Luyuan Chen, Zhijie Xu, Yadong Li, Xingzhong Xu, Siye Chen, Jie Liu, Ming Kong, Qiang Zhu

Long-video understanding remains challenging due to extreme temporal redundancy, sparse yet decisive events, and the instability of long-horizon reasoning in visual-language models (VLMs). Existing agent-based methods invoke external micro-tools but remain static, repeatedly rebuilding long chains of fine-grained operations for each task without acquiring reusable multi-step perceptual skills.We propose META, the first training-free agent capable of self-evolving its tool-augmented reasoning. META operates through dual Solving and Evolving loops: it analyzes its own tool trajectories, abstracts recurring multi-step patterns into reusable macro-tools, and distills failed executions into structured failure priors that refine tool usage. Through symbolic consolidation and pruning, META progressively shortens reasoning paths and acquires more general perceptual and temporal abilities--without any parameter updates. META achieves state-of-the-art performance on long-video benchmarks, demonstrating a scalable, model-agnostic paradigm for long-video understanding that can continually evolve without additional training.

Arkaprava Sinha, Monish Soundar Raj, Pu Wang, Ahmed Helmy, Hieu Le, Srijan Das

Temporal Action Detection (TAD) in untrimmed videos poses significant challenges, particularly for Activities of Daily Living (ADL) requiring models to (1) process long-duration videos, (2) capture temporal variations in actions, and (3) simultaneously detect dense overlapping actions. Existing CNN and Transformer-based approaches, struggle to jointly capture fine-grained detail and long-range structure at scale. State-space Model (SSM) based Mamba offers powerful long-range modeling, but naive application to TAD collapses fine-grained temporal structure and fails to account for the challenges inherent to TAD. To this end, we propose Multi-Scale Temporal Mamba (MS-Temba), which extends Mamba to TAD with newly introduced dilated SSMs. Each Temba block, comprising dilated SSMs coupled with our proposed additional losses, enables the learning of discriminative representations across temporal scales. A lightweight Multi-scale Mamba Fuser then unifies these multi-scale features via SSM-based aggregation, yielding precise action-boundary localization. With only 17M parameters, MS-Temba achieves state-of-the-art performance on densely labeled ADL benchmarks TSU & Charades, and further generalizes to long-form video summarization, setting new state-of-the-art results on TVSum & SumMe.

Ian Noronha, Heather Neave, Upinder Kaur

Understanding animal behavior requires modeling how bodies, objects, and other agents interact over time, not simply detecting isolated actions or estimating pose frame by frame. Existing animal video datasets target pose estimation or coarse, passively observed actions, and rarely provide the structured, multi-entity interaction annotations needed to study behavioral dynamics. We introduce MooCap, a multi-view video benchmark for animal-object-human interaction understanding under controlled experimental protocols. MooCap contains 42 hours of synchronized multi-camera video from 43 individually tested cows across seven standardized interaction scenarios, including novel environment, novel object, novel human, human approach, unfamiliar conspecifics (restricted and unrestricted) and Dam reunion (restricted and unrestricted). Recordings are densely annotated with 23 fine-grained behaviors, 39 body keypoints across 157 test sessions, 4 spatial zones, and 43 subjects, describing interactions among subjects, objects, humans, and other cattle. We establish three benchmarks on MooCap: (1) dense temporal action segmentation over 1200-1500-second sequences; (2) pose-based behavior and interaction recognition from keypoint trajectories; and (3) longitudinal behavioral classification linking adult behaviors with rearing conditions. Benchmarking results reveal that state-of-the-art temporal segmentation models achieve only 66.4% frame accuracy and 30.6% F1@0.5, with performance degrading further during interaction-heavy segments. Overall, MooCap bridges multi-view pose estimation, multi-entity tracking, and structured behavioral protocols to enable interaction-aware models for animal behavior analysis.

Jianhui Wei, Xiaotian Zhang, Yichen Li, Yuan Wang, Yan Zhang, Ziyi Chen, Zhihang Tang, Wei Xu, Zuozhu Liu

Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation benchmarks remain fragmented and limited in scope, as they each target a single task, rely on task-specific metrics, and typically use short or simple video clips. As a result, they do not capture the unified capabilities that these models are designed to deliver. To address this gap, we introduce UniVBench, a benchmark purpose-built for evaluating video foundation models across four core abilities: video understanding, video generation, video editing, and a newly proposed task, video reconstruction, which assesses how faithfully a model can reproduce video content it has encountered. Our benchmark substantially expands the complexity of evaluation by incorporating 200 high-quality, diverse and multi-shot videos, each paired with detailed captions, multi-format editing instructions, and reference images. All videos are entirely human-created and carefully validated, offering richer cinematic information than prior benchmarks. In addition, we develop a unified agentic evaluation system (UniV-Eval) that standardizes prompting, instruction parsing, and scoring across all tasks, enabling fair, scalable, and reproducible comparisons of unified video models. By grounding evaluation in instruction-based multi-shot video tasks, UniVBench provides the first framework for measuring the integrated capabilities that video foundation models aim to achieve. Extensive human annotations ensure our evaluation aligns with human judgment, enabling rigorous assessment and accelerating progress toward robust video intelligence.

Haiyang Yan, Hongyun Zhou, Peng Xu, Xiaoxue Feng, Mengyi Liu

Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high information density and extended temporal spans. Recent research on LVU agents demonstrates that simple task decomposition and collaboration mechanisms are insufficient for long-chain reasoning tasks. Moreover, directly reducing the time context through embedding-based retrieval may lose key information of complex problems. In this paper, we propose Symphony, a multi-agent system, to alleviate these limitations. By emulating human cognition patterns, Symphony decomposes LVU into fine-grained subtasks and incorporates a deep reasoning collaboration mechanism enhanced by reflection, effectively improving the reasoning capability. Additionally, Symphony provides a VLM-based grounding approach to analyze LVU tasks and assess the relevance of video segments, which significantly enhances the ability to locate complex problems with implicit intentions and large temporal spans. Experimental results show that Symphony achieves state-of-the-art performance on LVBench, LongVideoBench, VideoMME, and MLVU, with a 5.0% improvement over the prior state-of-the-art method on LVBench. Code is available at https://github.com/Haiyang0226/Symphony.

Jooyoung Kim, Wonje Choi, Younguk Song, Honguk Woo

Recent advances in Vision-Language Models (VLMs) have enabled video-instructed robotic programming, allowing agents to interpret video demonstrations and generate executable control code. We formulate video-instructed robotic programming as a cross-domain adaptation problem, where perceptual and physical differences between demonstration and deployment induce procedural mismatches. However, current VLMs lack the procedural understanding needed to reformulate causal dependencies and achieve task-compatible behavior under such domain shifts. We introduce NeSyCR, a neurosymbolic counterfactual reasoning framework that enables verifiable adaptation of task procedures, providing a reliable synthesis of code policies. NeSyCR abstracts video demonstrations into symbolic trajectories that capture the underlying task procedure. Given deployment observations, it derives counterfactual states that reveal cross-domain incompatibilities. By exploring the symbolic state space with verifiable checks, NeSyCR proposes procedural revisions that restore compatibility with the demonstrated procedure. NeSyCR achieves a 31.14% improvement in task success over the strongest baseline Statler, showing robust cross-domain adaptation across both simulated and real-world manipulation tasks.

Ziyi Chen, Yingnan Guo, Zedong Chu, Minghua Luo, Yanfen Shen, Mingchao Sun, Junjun Hu, Shichao Xie, Yang Kuan, Pei Shi 等

Embodied navigation that adheres to social norms remains an open research challenge. Our SocialNav is a foundational model for socially-aware navigation with a hierarchical "brain-action" architecture, capable of understanding high-level social norms and generating low-level, socially compliant trajectories. To enable such dual capabilities, we construct the SocNav Dataset, a large-scale collection of 7 million samples, comprising (1) a Cognitive Activation Dataset providing social reasoning signals such as chain-of-thought explanations and social traversability prediction, and (2) an Expert Trajectories Pyramid aggregating diverse navigation demonstrations from internet videos, simulated environments, and real-world robots. A multi-stage training pipeline is proposed to gradually inject and refine navigation intelligence: we first inject general navigation skills and social norms understanding into the model via imitation learning, and then refine such skills through a deliberately designed Socially-Aware FlowExploration GRPO (SAFE-GRPO), the first flow-based reinforcement learning framework for embodied navigation that explicitly rewards socially compliant behaviors. SocialNav achieves +38% success rate and +46% social compliance rate compared to the state-of-the-art method, demonstrating strong gains in both navigation performance and social compliance. Data and code will be made publicly available.

Yuanjun Tan, Aoran Xiao, Liqian Deng, Zhigang Tu

Human action recognition (HAR) in low-light environments remains challenging due to degraded visibility, illumination variance, and loss of appearance cues. We introduce DarkAct, a large-scale and high-quality RGB-thermal video dataset purpose-built for multimodal action recognition under low illumination. DarkAct contains 12,778 paired RGB-thermal videos covering 27 human actions across diverse viewpoints and scenes, offering a novel and comprehensive benchmark for understanding human actions in dark environments. We conduct extensive experiments on DarkAct, systematically benchmarking unimodal HAR models, multimodal fusion frameworks, and vision-language foundation models. Their limited performance on DarkAct underscores the urgent need for more robust perception systems under adverse illumination. To address this, we propose DarkAct-Net, an RGB-thermal fusion framework that enhances human-centric representation and achieves adaptive cross-modal fusion, enabling robust and fine-grained action recognition across diverse lighting conditions. Dataset and code are available at https://github.com/darkact-creator/DarkAct.git.

Junlin Xie, Quanlong Zheng, Ruifei Zhang, Kuo Wang, Yanhao Zhang, Jinguo Luo, Haonan Lu, Xiang Wan, Guanbin Li

The transition of Retrieval-Augmented Generation (RAG) from offline video analysis to online, streaming scenarios presents a set of critical, unexplored challenges. These include the need for on-the-fly semantic segmentation of continuous video, the inherent tension between low-latency processing and high-quality knowledge extraction, and the demand for query-specific temporal reasoning. We propose StreamRAG, a novel framework designed to overcome these hurdles. StreamRAG is built upon three core technical pillars: (1) a Stream Event Segmentation (SES) module that performs real-time boundary detection to chunk the stream into meaningful units; (2) a Token-Reusing Accelerator that drastically cuts down captioning latency by leveraging computational overlap between consecutive frames; and (3) a Dynamic Retrieval Gate that modulates the retrieval scope and strategy based on the query's temporal sensitivity and contextual similarity. Empirical evaluation confirms that StreamRAG establishes a new state-of-the-art, delivering superior accuracy with minimal latency in streaming video comprehension.

Youngjun Jun, Seil Kang, Woojung Han, Seong Jae Hwang

Video Diffusion Transformers (DiTs) have been synthesizing high-quality video with high fidelity from given text descriptions involving motion. However, understanding how Video DiTs convert motion words into video remains insufficient. Furthermore, while prior studies on interpretable saliency maps primarily target objects, motion-related behavior in Video DiTs remains largely unexplored. In this paper, we investigate concrete motion features that specify when and which object moves for a given motion concept. First, to spatially localize, we introduce GramCol, which adaptively produces per-frame saliency maps for any text concept, including both motion and non-motion. Second, we propose a motion-feature selection algorithm to obtain an Interpretable Motion-Attentive Map (IMAP) that localizes motion spatially and temporally. Our method discovers concept saliency maps without the need for any gradient calculation or parameter update. Experimentally, our method shows outstanding localization capability on the motion localization task and zero-shot video semantic segmentation, providing interpretable and clearer saliency maps for both motion and non-motion concepts.

Keda Tao, Kele Shao, Bohan Yu, Weiqiang Wang, Jian Liu, Huan Wang

Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of processing longer joint audio-video token sequences has become a key bottleneck. Existing token compression methods have not addressed the emerging need to jointly compress multimodal tokens. To bridge this gap, we present OmniZip, a training-free, audio-guided audio-visual token-compression framework that optimizes multimodal token representation and accelerates model inference. Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information density, thereby dynamically guiding video token pruning and preserving cues from audio anchors enhanced by cross-modal similarity. For each time window, OmniZip compresses the video tokens using an interleaved spatio-temporal scheme. Extensive results demonstrate the merits of OmniZip: it achieves a 3.42x inference speedup and a 1.4x memory reduction over other top-performing counterparts, while maintaining the performance of OmniLLMs without training.

Li Puyin, Tiange Xiang, Ella Mao, Shirley Wei, Xinye Chen, Adnan Masood, Li Fei-Fei, Ehsan Adeli

Understanding the physical world is essential for generalist AI agents. However, it remains unclear whether state-of-the-art vision perception models (e.g., large VLMs) can perform quantitative physical reasoning tasks. Existing evaluations are predominantly VQA-based and qualitative, offering limited insight into whether these models can infer the kinematic quantities of moving objects from videos. To address this, we present QuantiPhy, the first benchmark designed to quantitatively measure a VLM's physical reasoning ability. Comprising more than 3.3K video-text instances with numerical ground truth, QuantiPhy evaluates a VLM's performance on estimating an object's size, velocity, and acceleration at a given timestamp, using one of these properties as an input prior. The benchmark standardizes prompts and scoring to assess numerical accuracy, enabling fair comparisons across models. Our experiments on state-of-the-art VLMs reveal a consistent gap between their qualitative plausibility and actual numerical correctness. We further provide an in-depth analysis of key factors like background noise, counterfactual priors, and strategic prompting and find that state-of-the-art VLMs lean heavily on pre-trained world knowledge rather than faithfully using the provided visual and textual inputs when reasoning about objects' kinematic properties. QuantiPhy offers the first rigorous, scalable testbed to move VLMs beyond mere verbal plausibility toward a numerically grounded physical understanding.

Jerry Jiang, Haowen Sun, Denis Gudovskiy, Yohei Nakata, Tomoyuki Okuno, Kurt Keutzer, Wenzhao Zheng

Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world. Despite promising results, most existing methods follow the conventional 2D pipeline in VLMs and use pixel-aligned representations for the vision modality. However, correspondence-based models with implicit 3D scene understanding often fail to achieve spatial consistency, and representation-based models with 3D geometric priors lack efficiency in vision sequence serialization. To address this, we propose a Proxy3D method with compact yet comprehensive 3D proxy representations for the vision modality. Given only video frames as input, we employ semantic and geometric encoders to extract scene features and then perform their semantic-aware clustering to obtain a set of proxies in the 3D space. For representation alignment, we further curate the SpaceSpan dataset and apply multi-stage training to adopt the proposed 3D proxy representations with the VLM. When using shorter sequences for vision information, our method achieves competitive or state-of-the-art performance in 3D visual question answering, visual grounding and general spatial intelligence benchmarks.

Dohwan Ko, Jinyoung Park, Seoung Choi, Sanghyeok Lee, Seohyun Lee, Hyunwoo J. Kim

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm has recently been extended to Vision-Language Models (VLMs), enabling scalable multi-modal understanding with reduced computational cost. However, the widely adopted deterministic top-K routing mechanism may overlook more optimal expert combinations and lead to expert overfitting. To address this limitation and improve the diversity of expert selection, we propose MoE-GRPO, a reinforcement learning (RL)-based framework for optimizing expert routing in MoE-based VLMs. Specifically, we formulate expert selection as a sequential decision-making problem and optimize it using Group Relative Policy Optimization (GRPO), allowing the model to learn adaptive expert routing policies through exploration and reward-based feedback. Furthermore, we introduce a modality-aware router guidance that enhances training stability and efficiency by discouraging the router from exploring experts that are infrequently activated for a given modality. Extensive experiments on multi-modal image and video benchmarks show that MoE-GRPO consistently outperforms standard top-K routing and its variants by promoting more diverse expert selection, thereby mitigating expert overfitting and enabling a task-level expert specialization.