Video_Caption
-
Evidence-Backed Video Question Answering
2026-07-13 17:49:10Shijie Wang, Honglu Zhou, Ziyang Wang, Ran Xu, Caiming Xiong, Silvio Savarese, Chen Sun, Juan Carlos NieblesAbstract
Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on textual rationales or sparse bounding boxes, which struggle to capture complex video dynamics such as occlusions and non-rigid deformations. We propose Evidence-Backed Video Question Answering (E-VQA), a novel task requiring models to jointly output a semantic answer and precise spatio-temporal evidence: temporal segments and dense, tracked object segmentation masklets. To support this, we introduce ST-Evidence, the first human-verified benchmark for both discriminative and generative pixel-level grounding. Evaluations of state-of-the-art models reveal a critical decoupling between QA accuracy and true visual perception that scaling alone fails to bridge. To address this, we develop scalable, automated generation pipelines to create ST-Evidence-Instruct, a 160k-scale dataset bridging high-level reasoning with fine-grained grounding. Fine-tuning grounded Video LLMs on this data yields substantial gains over the corresponding size-matched UniPixel baselines (e.g., +27.2 t-mean and +13.8 J&F on a 7B model), establishing a robust baseline for explainable, evidence-backed video understanding. Code and data are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11862
PDF
-
Beyond the Single Camera: Agentic Multi-View Reasoning in Sports Video Understanding
2026-07-13 17:34:36Kerui Chen, Jinglu Wang, Xiaoyi Zhang, Yan LuAbstract
Recent Multimodal Large Language Models (MLLMs) achieve strong performance on single-view video understanding benchmarks. However, sports videos involve dense occlusion, rapid motion, and complex interactions that are difficult to resolve from a single viewpoint. In practice, sports events are recorded from multiple camera angles, providing complementary evidence used by referees. Yet, no existing benchmark evaluates MLLMs on multi-view sports video understanding. To address this gap, we introduce SportMV-Bench, a comprehensive benchmark built from official match recordings, through a dedicated pipeline combining LLM-based generation, MLLM-based verification, and human filtering to ensure quality and consistency. SportMV-Bench containing 787 multi-view video bundles and 2592 question-answer pairs across three categories: Perception-Aware Recognition (PAR), Rule-aware Event Interpretation (REI), and Adjudicative Decision Reasoning(ADR). Our analysis shows that current MLLMs fail to effectively exploit multi-view information, with the bottlenecks lying in fine-grained visual perception and view selection rather than logical reasoning or domain knowledge. We propose SportMV-Agent, an agentic framework that orchestrates an iterative loop of active view selection, perception tool execution, and evidence-grounded reasoning, achieving a significant 14.46% relative improvement over the strongest MLLM baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11844
PDF
-
SLVMBench: Skill Learning from Video Memory
2026-07-13 09:26:13Yudong Yang, Guangzhi Sun, Yixuan Li, Chao ZhangAbstract
We introduce Skill Learning from Video Memory (SLVMBench), the first benchmark that jointly evaluates whether video large language models (video-LLMs) can learn skills from long video memory and apply them to real-time tasks. SLVMBench presents models with 2-3 hour video streams that contain a tutorial video embedded in a stream of arbitrary irrelevant videos, resembling real-world human learning practices. Video-LLMs are asked to apply the acquired skill to answer real-time questions about an ongoing video. Unlike long-video understanding benchmarks that emphasize passive comprehension and skill-learning benchmarks that rely on short, immediate demonstrations, SLVMBench tests the full pipeline of memorizing and extracting procedural knowledge, as well as transferring it to real-time tasks. Moreover, rigorous human annotations feature sub-second-level temporal calibration, manually engineered questions eliminating common-sense guessing, and collated tutorials to ensure coverage of the required skills. Evaluations on state-of-the-art proprietary and open-source video LLMs show that video-LLMs struggle substantially with learning and applying skill knowledge from videos. Moreover, performance degrades markedly when the skill knowledge is placed within a long video memory. These results reveal a key limitation of existing video LLMs and position SLVMBench as the first benchmark for studying real-time skill acquisition and application from long-context video memory.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11312
PDF
-
TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understanding
2026-07-13 01:27:20Thanh-Nhan Vo, Thanh-Khoi Nguyen, Trong-Thuan Nguyen, Trung-Hoang Le, Minh-Triet TranAbstract
Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in multi-step reasoning and coordinated tool integration. We present TreeSoc, a structured reasoning framework that reformulates soccer video question answering as a hierarchical search problem rather than a single-pass prediction. Specifically, TreeSoc employs a dynamic depth-first search (DFS) mechanism that decomposes complex queries into sequentially ordered sub-tasks, enabling iterative reasoning refinement through explicit intermediate states. This tree-structured decomposition naturally supports adaptive tool routing, wherein domain-specific modules are selectively activated and their outputs incorporated at each reasoning node to produce contextually grounded predictions. On SoccerBench, TreeSoc achieves state-of-the-art performance, with accuracies of 85.2%, 87.4%, and 82.2% on TextQA, ImageQA, and VideoQA, respectively. Additionally, TreeSoc further demonstrates strong cross-domain generalization, attaining 74.16% accuracy on NExT-QA. These results establish structured, tool-augmented tree reasoning as an effective paradigm for robust video understanding. Code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.10990
PDF
-
PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning
2026-07-11 08:06:04Wenyuan Wang, Lianyu Hu, Hao Wang, Yang LiuAbstract
Video-language models (VLMs) have achieved remarkable performance on video understanding and visual question answering, yet they remain unreliable in reasoning about physical plausibility, where understanding object interactions, causal dynamics, and fundamental physical principles is essential. This limitation is particularly evident on challenging physical reasoning benchmarks, revealing a persistent gap in physical commonsense reasoning. To address this challenge, we propose PhysMRV, a training-free physical memory and verification framework for physical plausibility reasoning. Unlike retrieval-augmented VLMs that retrieve semantically similar videos as additional context, PhysMRV transforms training videos into a Hierarchical Memory Bank of structured physical knowledge comprising three complementary levels: scene descriptions capturing visual context, physical-event graphs modeling object interactions and causal structure, and physics-rule summaries distilling reusable physical principles and cues. During inference, PhysMRV retrieves physically relevant memories and leverages their structured physical evidence to guide a frozen VLM in verifying physical plausibility, requiring neither fine-tuning nor parameter updates. We evaluate PhysMRV on three challenging physical reasoning benchmarks, ImplausiBench, IntPhys2, and GRASP Level 2, across multiple state-of-the-art VLMs. Experimental results demonstrate consistent improvements over direct prompting across diverse VLMs and evaluation benchmarks, showing that structured physical memories provide an effective and scalable means of enhancing physical plausibility reasoning without additional training.
Abstract (translated)
URL
https://arxiv.org/abs/2607.10190
PDF
-
MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding
2026-07-10 12:31:27Kun Li, Dan Guo, Jihao Gu, Pengyu Liu, Xiaobai Li, Haoyu Chen, Yanbin Hao, Guoying Zhao, Meng WangAbstract
Micro-Actions (MAs) are subtle and spontaneous human behaviors that provide important non-verbal cues in social interaction and affective communication. However, their short duration, weak motion patterns, and fine-grained semantic differences make them difficult to annotate, model, and evaluate in a standardized manner. To promote academic research on micro-action analysis, we proposed and have annually organized the Micro-Action Analysis Grand Challenge (MAC) as a public benchmark platform for this emerging field. The first two editions of MAC established standardized evaluation settings for micro-action recognition and detection, providing publicly accessible datasets and protocols. Building upon these editions, this paper presents the 3rd MAC, held in conjunction with ACM Multimedia 2026. Under the theme of moving from recognition to fine-grained micro-action understanding, this edition further expands the scope of the challenge beyond conventional recognition and detection. In particular, we introduce a new task named fine-grained micro-action understanding, evaluated with the assistance of multimodal large language models, aiming to assess models' ability to capture fine-grained semantic cues and interpret subtle human micro-actions at a deeper level. We summarize the datasets, task settings, evaluation protocols, competition results, and representative solutions from top-performing teams. Finally, we discuss future directions for micro-action analysis and its broader role in human-centric video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2607.16284
PDF
-
GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models
2026-07-10 03:58:26Guohuan Xie, Mengqi Lei, Chuan Shi, Wei Bao, Yue Gao, Siqi LiAbstract
Although Video Large Language Models (Video LLMs) have shown strong performance in video understanding, their efficiency is still limited by the large number of visual tokens. Existing video token compression methods typically rely on frame-wise saliency or heuristic token merging, which can over-focus on locally salient regions and produce ambiguous fused features. To address these issues, we propose GeoTrace, a training-free spatiotemporal token compression framework that decomposes video evidence into exact skeleton tokens and traceable residual event tokens. Specifically, Contextual Farthest-Point Anchoring (CFPA) preserves salient, context-consistent, and high-coverage skeleton tokens, while Trajectory-Constrained Residual Condensation (TCRC) compresses residual tokens through one-to-one temporal trajectories and constrained near-manifold condensation, producing traceable event tokens with reduced ambiguity. We evaluate GeoTrace on four Video LLMs across four video understanding benchmarks, and the results demonstrate its effectiveness and generalization across different model architectures and scenarios. On LLaVA-OneVision, with only 10\% visual tokens retained, GeoTrace achieves a \(12.99\times\) TFLOPs reduction while preserving 99.1\% of the vanilla performance. Overall, GeoTrace offers a compact and traceable token representation for efficient and robust Video LLM inference. Code is available at \href{this https URL}{\texttt{Code}}.
Abstract (translated)
URL
https://arxiv.org/abs/2607.09080
PDF
-
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
2026-07-09 17:46:24Siddharth Damodharan, Radhika Gupta, Ali Alshami, Ryan Rabinowitz, Jugal KalitaAbstract
Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reason about safety-critical incidents remains challenging. To address this gap, we present AUTOPILOT-VQA, an incident-centric visual question answering benchmark for dashcam video understanding. The dataset evaluates different systems through structured questions designed around real-world driving incidents and near-incidents. The benchmark covers diverse safety-relevant categories, including weather and lighting conditions, traffic environment, road layout, road surface state, signage, involved entities, accident occurrence, impact location, and avoidability-related reasoning. By requiring models to answer grounded questions about both contextual scene properties and event-level incident details, AUTOPILOT-VQA moves beyond object recognition toward temporally grounded, safety-aware reasoning. The dataset is released as part of the AUTOPILOT CVPR 2026 competition and provides a standardized benchmark for assessing the reliability of autonomous driving systems in different scenarios. Our benchmark support developments for more interpretable, robust, and safety-conscious vision-language systems for real-world autonomous driving.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08745
PDF
-
VEGAS: Human-Aligned Video Caption Evaluation via Gaze
2026-07-09 13:46:54Shenghui Chen, Po-han Li, Ximeng Sun, Shijia Yang, Emad Barsoum, Zicheng Liu, Sandeep Chinchali, Ufuk TopcuAbstract
Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention. We propose VEGAS (Video caption Evaluation via GAze Score), a training-free metric that leverages test-time gaze to sample personalized, attention-aligned text. It is a cross-modal, information-theoretic metric that quantifies how well a candidate caption matches a viewer's focus. To evaluate VEGAS, we curate a dataset of egocentric activities and instructional slides paired with synchronized gaze and reference annotations. We then select captions based on VEGAS via rejection sampling without model retraining. Experiments show that VEGAS-selected captions align significantly better with human focus and improve downstream caption-to-video retrieval, demonstrating the practical utility of incorporating viewer attention during inference.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08489
PDF
-
SoccerNet 2026 Challenges Results
2026-07-08 12:06:48Anthony Cioppa, Silvio Giancola, H{\aa}kan Ard\"o, Mohamad Dalal, Jan Held, J\'er\'emie Ochin, Jiayuan Rao, Karen Sanchez, Renaud Vandeghen, Artur Xarles, Olivier Barnich, Albert Clap\'es, Mathieu Delvaux, Sergio Escalera, Bernard Ghanem, C\'edric Hons, Antoine Houet, Sotiris Manitsaris, Tom Michel, Pierre Miralles, Thomas B. Moeslund, Mikael Nilsson, Bogdan Stanciulescu, Marc Van Droogenbroeck, Yanfeng Wang, Weidi Xie, Faisal Altawijri, Mohamed Atef, Semen Budennyy, Vasiliy Chelpanov, Puhua Chen, Yixin Chen, Lechao Cheng, Jianling Chu, Ju-Seong Do, Oleg Durygin, Omar Fetouh, Mirco Fuchs, Youssef Ghallab, Falguni Ghosh, Wonjun Heo, Yufeng Hu, Weixuan Huang, Phuong-Linh Huynh-Ha, Matvey Isupov, Yangguang Ji, Siyuan Jiang, Zhenxiang Jiang, Wonyong Jo, Ho-Young Jung, SeongHeon Kang, MinJae Kim, Youngseon Kim, Jakub Komosa, Artem Konshin, Trung-Hoang Le, Jongmin Lee, Lingling Li, Litao Li, Vadim Linkov, Fang Liu, Haoxuan Ma, Shun Makino, Ismail Mathkour, Konstantin Mitin, Mikhail Moiseev, Takumi Nagaya, Yuki Nakamura, Thanh-Khoi Nguyen, Hoang-Phuc Nguyen, Trong-Thuan Nguyen, Christian Orduz, Kwanyong Park, Fabian Perez, Parthsarthi Rawat, SuHyun Rim, Hoover Rueda-Chac\'on, Atom Scott, Minori Sugimura, Yuyang Sun, Shengeng Tang, Minh-Triet Tran, Ikuma Uchida, Juan Vanegas, Thanh-Nhan Vo, Jiangtao Wang, Yaxiong Wang, Xiaogang Wang, Ruifeng Wang, Rio Watanabe, Jiali Wen, Yongliang Wu, Di Yang, Xu Yang, Zhuo Yang, Xinyu Ye, Yibo Yu, Zihan Zhai, Yu Zhang, Zhenyu Zhao, Zhun Zhong, Yixi Zhou, Xingyu Zhu, Wenbo Zhu, Julian ZieglerAbstract
The SoccerNet 2026 Challenges constitute the sixth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in sports video understanding. This year's challenges span five vision-based tasks: (1) Ball Action Anticipation, predicting the timing and class of ball-related actions within a short future window from a preceding observation window; (2) Player-Centric Ball Action Spotting, temporally localizing and classifying ball-related actions while assigning each action to the acting player through team affiliation and jersey number; (3) Novel View Synthesis, rendering images from unobserved camera poses in multi-view football scenes; (4) Spiideo SoccerNet Synloc, localizing athletes in real-world pitch coordinates from a single calibrated static-camera image; and (5) Visual Question Answering, answering multiple-choice questions about football broadcasts across text, image, and video inputs. For each task, participants were provided with annotated data, a unified evaluation protocol, and a public baseline. This edition saw broad participation, with 427 teams submitting 1,129 entries across the five tasks and 28 teams contributing reviewed technical reports. This paper describes each task and its evaluation protocol, presents the challenge leaderboards, and summarizes the leading submissions, with the aim of documenting the current state of each task as measured on held-out challenge data.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07320
PDF
-
`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation
2026-07-08 10:13:20Waqas Arshid, Mohammad Awrangjeb, Alan Wee-Chung Liew, Yongsheng GaoAbstract
Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage. Self-supervised learning offers a promising alternative by removing the need for manual labels; however, existing approaches often struggle to jointly maintain spatial accuracy and temporal coherence, particularly in unconstrained multi-object scenarios. Many rely on optical flow, synthetic motion cues, or task-specific pretraining, limiting scalability and generalisation. We propose a self-supervised framework, Cross-Temporal Consistency and Clustering, that learns mid-level, part-aware representations by combining attention-guided token selection with lightweight temporal clustering. Instead of operating at the pixel or whole-object level, the method aligns soft part assignments across time using a saliency-weighted symmetric consistency objective. The framework leverages a frozen transformer backbone with lightweight modules for adaptive token selection and multi-offset temporal alignment, enabling efficient scaling across resolutions and motion patterns.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07230
PDF
-
Gen4U: Unifying Video Generation and Understanding via Diffusion
2026-07-07 23:17:26Michael King, Aravindh Mahendran, Matthew Koichi Grimes, Fedor Kitashov, Adham Elarabawy, Pedro Velez, Maks Ovsjanikov, Viorica P\u{a}tr\u{a}uceanAbstract
Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models overcome this limitation. By systematically probing their intermediate activations using recent mutual-kNN alignment metrics, we reveal a highly structured latent space where visual representations evolve across both network depth and noise levels. We show that while moderate noise levels yield linearly separable global semantics, fine-grained details persist at lower noise levels but become spatially scattered, requiring attention mechanisms to decode. Building on these insights, we introduce Gen4U (Generation for Understanding), a framework that repurposes these generative representations with a single forward pass. Our experiments establish that frozen, large-scale video diffusion models function as highly competitive video encoders across a wide spectrum of tasks, spanning semantic and non-semantic objectives (video classification, depth estimation, camera pose estimation, image and video captioning). Bypassing fine-tuning, Gen4U unifies the generation and understanding paradigms, achieving strong perception performance while fully preserving the model's ability to generate high-quality video.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06856
PDF
-
EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage
2026-07-07 16:28:10Max Gonzalez Saez-Diez, Jihoon Chung, Adam D. Wolsky, Gregory Lanzalotto, Dean Knox, Jonathan Mummolo, Brandon M. Stewart, Olga RussakovskyAbstract
We introduce EgoPolice, a carefully curated dataset of real, egocentric police-civilian interactions, sourced from publicly available body-worn camera videos. We select police-civilian action labels that are critical for police behavioral research and annotate them at a second-by-second granularity. The videos feature rapid and irregular camera motion, dense human interactions, and rare high-stakes events, making the dataset a challenging benchmark for motion-robust and context-aware egocentric perception. We provide two different tasks, classification and multiple-choice question-answering, and benchmark both open-source and closed-source models. We find that even the best video models like Gemini 2.5 Pro still struggle to accurately predict high-risk actions such as "Weapon Out". Beyond serving as a benchmark, EgoPolice provides a foundation for developing models capable of identifying events of interest in large-scale body-worn camera video repositories, enabling more efficient downstream human review.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06468
PDF
-
Andha-Dhun: A First Look at Audio Descriptions in Hindi
2026-07-07 16:15:46Ritabrata Chakraborty, Divy Kala, Nisheeth Bhooshan Gupta, Ganji Sreeram, Pailla Balakrishna Reddy, Makarand TapaswiAbstract
Audio Descriptions (ADs) narrate visual content for Blind and Low Vision (BLV) audiences during gaps in audiovisual media. There is growing momentum around ADs in movies and TV shows, and with mandates from India's Central Board of Film Certification (CBFC), there is a need to expand ADs beyond English. Yet, there is no work that generates ADs for any Indian language. To address this gap, we present the first systematic study of ADs in Hindi, contributing to aspects such as data, generation, and evaluation. We introduce Andha-Dhun, the first dataset of human-authored Hindi ADs collected from 8 full-length movies. We explore two approaches for generating ADs in Hindi: (i) directly from English dense video descriptions, and (ii) translating English ADs into Hindi. We evaluate these approaches using perplexity and LLM-as-a-judge metrics to assess fluency and quality respectively. We also analyze movies that have both English and Hindi human-authored ADs and find that naive translation introduces artifacts and narrows diversity compared to original Hindi ADs. Direct machine translation fails to adapt cultural references, while human-translated ADs do better but still fall short. Our findings emphasize that the purpose of Hindi ADs is accessibility for Indian BLV audiences, and that this requires adapting content for the audience more than strict fidelity to the source.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06457
PDF
-
Overview of the NLPCC 2026 Shared Task 1: Difficulty-Aware Multilingual and Multimodal Medical Instructional Video Understanding Evaluation
2026-07-07 09:24:48Shenxi Liu, Kan Li, Mingyang Zhao, Yuhang Tian, Bin LiAbstract
Following the CMIVQA, MMI-VQA, and M4IVQA challenges in NLPCC 2023--2025, we introduce the Difficulty-Aware Medical Instructional Video Question Answering (DA-MIVQA) shared task for NLPCC 2026. DA-MIVQA extends previous multilingual and multimodal medical video benchmarks by explicitly distinguishing questions according to the type and complexity of evidence required for answering. Specifically, simple questions can often be answered from subtitle-based textual cues, whereas complex questions require visual grounding, procedural understanding, and cross-modal evidence integration. The challenge contains three tracks: Difficulty-Aware Temporal Answer Grounding in Single Video (DA-TAGSV), Difficulty-Aware Video Corpus Retrieval (DA-VCR), and Difficulty-Aware Temporal Answer Grounding in Video Corpus (DA-TAGVC). The dataset is collected from public medical instructional channels, covers diverse scenarios such as first aid, emergency response, rehabilitation, nursing, and general medical education, and is manually verified with difficulty annotations. This paper presents the task motivation, dataset construction, evaluation protocol, participation overview, competition results, and representative systems of DA-MIVQA. DA-MIVQA provides a practical benchmark for evaluating medical instructional video question answering systems under varying textual, visual, temporal, and procedural reasoning requirements.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06618
PDF
-
Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory
2026-07-06 18:00:06Chang Nie, Jiaju Wei, Junlan Feng, Chaoyou Fu, Caifeng ShanAbstract
Agentic video understanding equips models with long-term memory to autonomously process and respond to continuous, long-horizon multimodal streams. However, advanced video agents often rely on ``detective-style'' iterative reasoning for action control (e.g., $\mathtt{search}$) and evidence aggregation, incurring prohibitive costs and latency. We argue that such heavy reasoning primarily compensates for the lack of global context and semantic misalignment in retrieval. This paper introduces Light-Omni, a multimodal agent framework for reflexive and lightweight video understanding. It achieves this through dual contextual states that instantly build the required context in a single forward pass. First, we maintain a global state, a finite-sized multimodal script continuously consolidated from episodic memory, serving as the global context for Light-Omni. Through hierarchical merging, it preserves recent details while summarizing past events. Second, conditioned on this global context, we generate a parametric latent state that directly drives autonomous actions and produces retrieval embeddings, with minimal latency. Benefiting from this coupled design, Light-Omni achieves semantically aligned retrieval and reflexive responses while avoiding iterative reasoning. Extensive experiments validate the effectiveness of Light-Omni across multiple video benchmarks. Notably, it outperforms M3-Agent with an average 2.4% accuracy gain, a 12.1$\times$ speedup, and a 2.6$\times$ improvement in GPU memory efficiency. Furthermore, it serves as a memory system to enhance both the performance and efficiency of existing MLLMs. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05511
PDF
-
Claim-Level Rubric Rewards for Video Caption Reinforcement Learning
2026-07-06 14:33:41Mingqi Gao, Hongyuan Dong, Yifei Chen, Zhisheng Zhong, Zheng Ruan, Wenjin Hou, Yu Chen, Han Hu, Yansong TangAbstract
In this paper, we introduce Claim-Level Rubric Rewards (CuRe), a structured reward framework designed to address the reward-design bottleneck in reinforcement learning for dense video captioning. Existing reward designs generally fall into two categories: holistic response-level judgment across heterogeneous criteria, or alignment-based evaluation against reference captions. However, both paradigms suffer from fundamental limitations. Holistic rewards struggle to ensure factual accuracy and are prone to stylistic reward hacking, while reference-based rewards overly rely on rigid textual alignment, failing to preserve the completeness and diversity inherent to open-ended generation tasks. To address these challenges, CuRe reformulates reward modeling as fine-grained claim-level verification. Specifically, CuRe decomposes captions into category-aware atomic claims through a structured rubric, converting holistic evaluation into simpler and more reliable claim-level verification.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05150
PDF
-
TimeThink: Reasoning with Time for Video LLMs
2026-07-06 13:50:15Handong Li, Longteng Guo, Zikang Liu, Dongze Hao, Yepeng Tang, Zijia Zhao, Jie Jiang, Zhiwei Jin, Chen Chen, Haonan Lu, Jing LiuAbstract
Video reasoning requires models to identify and verify temporally localized evidence within long video sequences. Recent Video Large Language Models (Video-LLMs) have shown promising reasoning abilities when aligned with reinforcement learning, yet existing approaches typically rely on outcome-based rewards that supervise only the final prediction. Such supervision provides limited guidance on how models should discover the relevant temporal evidence during intermediate reasoning. In this work, we propose TimeThink, a reinforcement learning framework that explicitly guides temporal evidence discovery in Video-LLMs. Our key idea is to treat temporal clue steps as the fundamental optimization primitive of video reasoning, where each reasoning step references a candidate time interval in the video. We introduce a step-wise temporal process reward that provides localized credit assignment for these clues and a joint process--outcome optimization objective that balances reasoning fidelity with task correctness. To enable scalable training, we construct TimeThink-RFT-20K, a dataset with automatically derived temporal evidence segments. Extensive experiments across video reasoning, temporal grounding, and general video understanding benchmarks show that TimeThink consistently improves both temporal localization and reasoning performance, achieving state-of-the-art results among open-source video RL models.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05089
PDF
-
QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding
2026-07-06 00:19:42Wei Ao, Lan Wang, Vishnu Naresh BoddetiAbstract
The performance of vision-language models (VLMs) in video understanding declines with increasing video duration, as video moments unrelated to the query confuse their language components. Multimodal retrieval has emerged as a critical component of video understanding, addressing this challenge by localizing key visual evidence. However, existing multimodal retrieval methods suffer from biased relevance estimation, limited diversity, and temporal collapse. In this paper, we propose QSVideo, a unified framework that systematically addresses relevance, diversity, and temporal modeling in video retrieval. We first introduce a query-conditioned semantic ranker, QSRanker, which reformulates arbitrary questions into retrieval-friendly queries and estimates structured relevance along object, action, and location dimensions. Building upon this, we design QSRetrieval to jointly optimize relevance and diversity for more informative frame selection. Moreover, we propose temporal alignment strategies tailored for both long and streaming videos to improve evidence recall. Extensive experiments on long and streaming video benchmarks demonstrate that QSVideo greatly enhances video VLM performance under strict frame limit constraints. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04559
PDF
-
VideoAgent: All-in-One Framework for Video Understanding and Editing
2026-07-03 09:09:11Hengji Zhou, Lingxuan Huang, Jian Wang, Bing Zhou, Si Wu, Lianghao Xia, Chao HuangAbstract
Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks. They face two critical limitations: i) inability to handle diverse video comprehension and editing operations, and ii) lack of long-video understanding for coherent narrative creation. We propose VideoAgent, an all-in-one agentic framework addressing these challenges through two key innovations. First, we develop automated video shot creation with shot planning agents for coherent narratives and cross-modal retrieval for aligned visual content. Second, we design a multi-agent orchestration framework integrating over thirty specialized editing agents. Intent parsing filters relevant tools while textual-gradient graph optimization assembles complex editing pipelines. Extensive experiments on our newly-proposed VideoEdit benchmark and public datasets demonstrate VideoAgent's superiority over existing multimodal LLMs and agentic systems. VideoAgent achieves 87-95% orchestration success rates while reducing API costs by 60%. Human evaluation across six video categories shows VideoAgent produces professional-quality content approaching human-level performance, with ratings only 4% below human-created videos. We release our code at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.23327
PDF
