{"total":96,"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":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"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":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169,"area":null},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2404.00308","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","created":"2024-03-30","cited_by_count":126,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"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,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91,"area":null},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90,"area":null},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","cited_by_count":86,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2405.16886","title":"Hawk: Learning to Understand Open-World Video Anomalies","created":"2024-05-27","cited_by_count":49,"area":null},{"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":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"area":null},{"id":"2404.16038","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","created":"2024-01-30","cited_by_count":37,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"area":null},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2404.17113","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","created":"2024-04-26","cited_by_count":23,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2412.05185","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2509.24200","title":"UniVid: The Open-Source Unified Video Model","created":"2025-09-29","cited_by_count":19,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2411.12951","title":"On the Consistency of Video Large Language Models in Temporal Comprehension","created":"2024-11-20","cited_by_count":18,"area":null},{"id":"2412.09601","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2410.00771","title":"Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting","created":"2024-10-01","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2503.13016","title":"Efficient Motion-Aware Video MLLM","created":"2025-03-17","cited_by_count":14,"area":null},{"id":"2404.04458","title":"JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups","created":"2024-04-06","cited_by_count":13,"area":null},{"id":"2503.17069","title":"PVChat: Personalized Video Chat with One-Shot Learning","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2411.16156","title":"VideoOrion: Tokenizing Object Dynamics in Videos","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2411.16932","title":"Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11,"area":null},{"id":"2502.18863","title":"Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2410.05714","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2504.01407","title":"ZoomV: Temporal Zoom-in for Efficient Long Video Understanding","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2504.02061","title":"Aligned Better, Listen Better for Audio-Visual Large Language Models","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2504.05046","title":"MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2404.13370","title":"Movie101v2: Improved Movie Narration Benchmark","created":"2024-04-20","cited_by_count":9,"area":null},{"id":"2510.05836","title":"Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow","created":"2025-10-07","cited_by_count":9,"area":null},{"id":"2503.10719","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2503.18422","title":"Breaking the Encoder Barrier for Seamless Video-Language Understanding","created":"2025-03-24","cited_by_count":8,"area":null},{"id":"2508.06350","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models","created":"2025-08-08","cited_by_count":8,"area":null},{"id":"2512.14273","title":"Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2406.09390","title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2412.18609","title":"Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2505.24329","title":"DisTime: Distribution-based Time Representation for Video Large Language Models","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2409.19532","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","created":"2024-09-29","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":"2504.20384","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","created":"2025-04-29","cited_by_count":6,"area":null},{"id":"2402.13546","title":"LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2412.11906","title":"PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension","created":"2024-12-16","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":"2601.16449","title":"Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding","created":"2026-01-23","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":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2604.05079","title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2410.01180","title":"UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2510.04022","title":"Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2606.07289","title":"Closed-Form Spectral Regularization for Multi-Task Model Merging","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2504.14553","title":"Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2505.10257","title":"Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2510.15231","title":"Extending Audio Context for Long-Form Understanding in Large Audio-Language Models","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2503.00049","title":"Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2504.14429","title":"ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2511.14143","title":"SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2601.07366","title":"HiVid-Narrator: Hierarchical Video Narrative Generation with Scene-Primed ASR-anchored Compression","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2605.18904","title":"Dynamic Model Merging Made Slim","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2607.01117","title":"MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2408.10500","title":"SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2504.14432","title":"ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Task","created":"2025-04-20","cited_by_count":0,"area":null},{"id":"2509.06335","title":"Harnessing Object Grounding for Time-Sensitive Video Understanding","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.17421","title":"RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2509.19885","title":"Towards Self-Supervised Foundation Models for Critical Care Time Series","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2604.27968","title":"ClimateVID -- Social Media Videos Analysis and Challenges Involved","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.22352","title":"On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2608.28675","title":"Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.05596","title":"Time-Aware Assistive Navigation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}