{"total":60,"rows":[{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"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":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"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":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2409.12959","title":"MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines","created":"2024-09-19","cited_by_count":101,"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":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81,"area":null},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"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":"2507.09122","title":"SnapMoGen: Human Motion Generation from Expressive Texts","created":"2025-07-12","cited_by_count":47,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","cited_by_count":39,"area":null},{"id":"2310.12973","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","created":"2023-10-19","cited_by_count":39,"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":"2405.20305","title":"Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models","created":"2024-05-30","cited_by_count":33,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2603.08620","title":"StreamReady: Learning What to Answer and When in Long Streaming Videos","created":"2026-03-09","cited_by_count":19,"area":null},{"id":"2312.02310","title":"VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding","created":"2023-12-04","cited_by_count":18,"area":null},{"id":"2502.13449","title":"Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2503.18359","title":"Context-Enhanced Memory-Refined Transformer for Online Action Detection","created":"2025-03-24","cited_by_count":13,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2307.04251","title":"ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey","created":"2023-07-09","cited_by_count":10,"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":"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":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2506.01364","title":"Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review","created":"2025-06-02","cited_by_count":10,"area":null},{"id":"2508.01742","title":"Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation","created":"2025-08-03","cited_by_count":10,"area":null},{"id":"2506.02550","title":"Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2312.14206","title":"LLM4VG: Large Language Models Evaluation for Video Grounding","created":"2023-12-21","cited_by_count":8,"area":null},{"id":"2506.06253","title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2308.05787","title":"Temporally-Adaptive Models for Efficient Video Understanding","created":"2023-08-10","cited_by_count":7,"area":null},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2312.00055","title":"LEAP: LLM-Generation of Egocentric Action Programs","created":"2023-11-29","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":"2512.04532","title":"PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement","created":"2025-12-04","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":"2311.12820","title":"MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2308.14461","title":"Spatio-Temporal Analysis of Patient-Derived Organoid Videos Using Deep Learning for the Prediction of Drug Efficacy","created":"2023-08-28","cited_by_count":2,"area":null},{"id":"2408.06622","title":"ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2508.00374","title":"Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2512.10363","title":"Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2402.15746","title":"Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2411.14688","title":"Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning","created":"2024-11-22","cited_by_count":1,"area":null},{"id":"2603.22872","title":"ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2410.00649","title":"LASMP: Language Aided Subset Sampling Based Motion Planner","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2508.09818","title":"ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2509.03426","title":"Time-Scaling State-Space Models for Dense Video Captioning","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2509.22544","title":"HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detection","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2606.00640","title":"An Attribute-Based Measure of Video Complexity","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2607.10598","title":"Anomalous Frame Detection by Grouping Frame Similarities between Two Videos Computed by Vision-Language Model to Extract Expert Workers' Unique Actions","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.11957","title":"Anomalous Frame Detection Using VLM-Based Description Comparison for Extracting Expert-Specific Actions and Contextual Decision-Making Scenes with Intra-Video Self-Similarity","created":"2026-07-12","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":"2609.31665","title":"Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}