{"list":"other","total":105,"rows":[{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"2403.03890","title":"Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation","created":"2024-03-06","cited_by_count":93},{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91},{"id":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81},{"id":"2412.11198","title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","created":"2024-12-15","cited_by_count":78},{"id":"2501.13468","title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","created":"2025-01-23","cited_by_count":73},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51},{"id":"2503.22952","title":"OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts","created":"2025-03-29","cited_by_count":51},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46},{"id":"2503.12769","title":"ViSpeak: Visual Instruction Feedback in Streaming Videos","created":"2025-03-17","cited_by_count":42},{"id":"2509.24304","title":"FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting","created":"2025-09-29","cited_by_count":42},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37},{"id":"2508.01875","title":"StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding","created":"2025-08-03","cited_by_count":33},{"id":"2506.06097","title":"VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning","created":"2025-06-06","cited_by_count":32},{"id":"2506.10821","title":"VideoExplorer: Think With Videos For Agentic Long-Video Understanding","created":"2025-06-12","cited_by_count":29},{"id":"2508.20478","title":"Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding","created":"2025-08-28","cited_by_count":28},{"id":"2510.14560","title":"Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video","created":"2025-10-16","cited_by_count":28},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24},{"id":"2507.15028","title":"Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding","created":"2025-07-20","cited_by_count":24},{"id":"2412.08591","title":"RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation","created":"2024-12-11","cited_by_count":23},{"id":"2504.16082","title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","created":"2025-04-22","cited_by_count":23},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22},{"id":"2510.19488","title":"VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos","created":"2025-10-22","cited_by_count":22},{"id":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20},{"id":"2504.13915","title":"Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding","created":"2025-04-10","cited_by_count":19},{"id":"2509.26386","title":"PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer","created":"2025-09-30","cited_by_count":19},{"id":"2603.08620","title":"StreamReady: Learning What to Answer and When in Long Streaming Videos","created":"2026-03-09","cited_by_count":19},{"id":"2507.07151","title":"Robust Multimodal Large Language Models Against Modality Conflict","created":"2025-07-09","cited_by_count":18},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16},{"id":"2603.12938","title":"Thinking in Streaming Video","created":"2026-03-13","cited_by_count":16},{"id":"2506.13589","title":"AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding","created":"2025-06-16","cited_by_count":15},{"id":"2603.03447","title":"Proact-VL: A Proactive VideoLLM for Real-Time AI Companions","created":"2026-03-03","cited_by_count":15},{"id":"2505.12632","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","created":"2025-05-19","cited_by_count":14},{"id":"2411.16173","title":"SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis","created":"2024-11-25","cited_by_count":13},{"id":"2501.05069","title":"Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning","created":"2025-01-09","cited_by_count":12},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12},{"id":"2510.14672","title":"VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning","created":"2025-10-16","cited_by_count":12},{"id":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12},{"id":"2411.18983","title":"SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing","created":"2024-11-28","cited_by_count":11},{"id":"2602.03589","title":"SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM","created":"2026-02-03","cited_by_count":11},{"id":"2605.18577","title":"OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding","created":"2026-05-18","cited_by_count":11},{"id":"2512.04643","title":"SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding","created":"2025-12-04","cited_by_count":10},{"id":"2510.05836","title":"Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow","created":"2025-10-07","cited_by_count":9},{"id":"2604.09000","title":"StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding","created":"2026-04-10","cited_by_count":9},{"id":"2603.04977","title":"Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding","created":"2026-03-05","cited_by_count":8},{"id":"2502.05857","title":"EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds","created":"2025-02-09","cited_by_count":7},{"id":"2602.04094","title":"VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding","created":"2026-02-04","cited_by_count":7},{"id":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7},{"id":"2512.13874","title":"SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning","created":"2025-12-15","cited_by_count":6},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5},{"id":"2510.15440","title":"Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning","created":"2025-10-17","cited_by_count":5},{"id":"2604.18459","title":"Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions","created":"2026-04-20","cited_by_count":5},{"id":"2412.09513","title":"Agent-based Video Trimming","created":"2024-12-12","cited_by_count":4},{"id":"2505.13887","title":"Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation","created":"2025-05-20","cited_by_count":4},{"id":"2604.05079","title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","created":"2026-04-06","cited_by_count":4},{"id":"2605.17921","title":"An Efficient Streaming Video Understanding Framework with Agentic Control","created":"2026-05-18","cited_by_count":4}],"next_cursor":"100"}