{"total":83,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138,"area":"rag"},{"id":"2311.07562","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","created":"2023-11-13","cited_by_count":137,"area":"mllm"},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127,"area":null},{"id":"2508.09736","title":"Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory","created":"2025-08-13","cited_by_count":97,"area":"agents"},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90,"area":null},{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77,"area":"rag"},{"id":"2503.21483","title":"BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding","created":"2025-03-27","cited_by_count":75,"area":"mllm"},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2406.12235","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","created":"2024-06-18","cited_by_count":64,"area":"mllm"},{"id":"2408.00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","created":"2024-08-01","cited_by_count":57,"area":"mllm"},{"id":"2409.15310","title":"Visual Prompting in Multimodal Large Language Models: A Survey","created":"2024-09-05","cited_by_count":54,"area":"mllm"},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45,"area":null},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38,"area":null},{"id":"2311.15732","title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","created":"2023-11-27","cited_by_count":35,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2406.16620","title":"OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer","created":"2024-06-24","cited_by_count":34,"area":"agents"},{"id":"2404.16375","title":"List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs","created":"2024-04-25","cited_by_count":32,"area":"mllm"},{"id":"2510.14032","title":"Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding","created":"2025-10-15","cited_by_count":31,"area":"lr"},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2403.02613","title":"Large Language Models and Video Games: A Preliminary Scoping Review","created":"2024-03-05","cited_by_count":23,"area":null},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23,"area":null},{"id":"2312.07424","title":"How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2510.12323","title":"RAG-Anything: All-in-One RAG Framework","created":"2025-10-14","cited_by_count":20,"area":"rag"},{"id":"2312.17661","title":"Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models","created":"2023-12-29","cited_by_count":16,"area":"lr"},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2501.04670","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","created":"2025-01-08","cited_by_count":16,"area":"lr"},{"id":"2504.20091","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","created":"2025-04-25","cited_by_count":16,"area":"lr"},{"id":"2404.12309","title":"iRAG: Advancing RAG for Videos with an Incremental Approach","created":"2024-04-18","cited_by_count":15,"area":"rag"},{"id":"2405.00983","title":"LLM-AD: Large Language Model based Audio Description System","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2506.13589","title":"AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding","created":"2025-06-16","cited_by_count":15,"area":"mllm"},{"id":"2403.12922","title":"Contextual AD Narration with Interleaved Multimodal Sequence","created":"2024-03-19","cited_by_count":14,"area":null},{"id":"2405.18358","title":"MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning","created":"2024-05-28","cited_by_count":13,"area":"lr"},{"id":"2504.01020","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2311.04199","title":"Exploring Recommendation Capabilities of GPT-4V(ision): A Preliminary Case Study","created":"2023-11-07","cited_by_count":12,"area":"mllm"},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2512.04000","title":"Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding","created":"2025-12-03","cited_by_count":11,"area":"mllm"},{"id":"2510.02262","title":"From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2401.10039","title":"GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition","created":"2024-01-18","cited_by_count":8,"area":"mllm"},{"id":"2405.17104","title":"LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2406.06559","title":"Harnessing Business and Media Insights with Large Language Models","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2406.09988","title":"Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2410.06777","title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding","created":"2024-10-09","cited_by_count":7,"area":"mllm"},{"id":"2311.07547","title":"GPT-4V(ision) as A Social Media Analysis Engine","created":"2023-11-13","cited_by_count":6,"area":"mllm"},{"id":"2406.17309","title":"Zero-Shot Long-Form Video Understanding through Screenplay","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2512.23483","title":"TV-RAG: A Temporal-aware and Semantic Entropy-Weighted Framework for Long Video Retrieval and Understanding","created":"2025-12-29","cited_by_count":6,"area":null},{"id":"2604.05418","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","created":"2026-04-07","cited_by_count":6,"area":"mllm"},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2411.12293","title":"Generative Timelines for Instructed Visual Assembly","created":"2024-11-19","cited_by_count":5,"area":null},{"id":"2504.17213","title":"MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding","created":"2025-04-24","cited_by_count":5,"area":null},{"id":"2509.11796","title":"FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning","created":"2025-09-15","cited_by_count":5,"area":"lr"},{"id":"2603.15280","title":"Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory","created":"2026-03-16","cited_by_count":5,"area":"lr"},{"id":"2605.17423","title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","created":"2026-05-17","cited_by_count":5,"area":null},{"id":"2412.09513","title":"Agent-based Video Trimming","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2408.03340","title":"An Empirical Comparison of Video Frame Sampling Methods for Multi-Modal RAG Retrieval","created":"2024-07-22","cited_by_count":3,"area":null},{"id":"2503.01201","title":"Parameter-free Video Segmentation for Vision and Language Understanding","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2504.12157","title":"FocusedAD: Character-centric Movie Audio Description","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2403.04798","title":"JMI at SemEval 2024 Task 3: Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2403.11468","title":"CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2412.09907","title":"IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2503.09027","title":"Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2504.15918","title":"Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2509.08538","title":"MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2509.13255","title":"ResidualViT for Efficient Temporally Dense Video Encoding","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2509.18754","title":"COLT: Enhancing Video Large Language Models with Continual Tool Usage","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2512.08410","title":"Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval","created":"2025-12-09","cited_by_count":2,"area":"mllm"},{"id":"2607.01737","title":"ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2511.09448","title":"MCAD: Multimodal Context-Aware Audio Description Generation For Soccer","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2511.20965","title":"TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2412.08158","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","created":"2024-12-11","cited_by_count":0,"area":"lr"},{"id":"2505.06594","title":"Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and Evaluation","created":"2025-05-10","cited_by_count":0,"area":"mllm"},{"id":"2509.22019","title":"EgoInstruct: An Egocentric Video Dataset of Face-to-face Instructional Interactions with Multi-modal LLM Benchmarking","created":"2025-09-26","cited_by_count":0,"area":"mllm"},{"id":"2605.05348","title":"How Do Novice Describers Edit AI Drafts? The Role of Draft Quality in Audio Description Authoring","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.06338","title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.11798","title":"StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2610.08674","title":"EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding","created":"2026-10-06","cited_by_count":0,"area":"rag"}],"next_cursor":null}