{"total":310,"rows":[{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062,"area":null},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"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":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"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":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"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":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","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":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"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":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129,"area":null},{"id":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","cited_by_count":117,"area":null},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","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":"2305.05662","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","created":"2023-05-09","cited_by_count":96,"area":null},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93,"area":null},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"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":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80,"area":null},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2503.04812","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","created":"2025-03-04","cited_by_count":55,"area":null},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"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":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49,"area":null},{"id":"2311.17241","title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","created":"2023-11-28","cited_by_count":47,"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":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45,"area":null},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"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":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"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":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37,"area":null},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36,"area":null},{"id":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2303.15772","title":"Ecosystem Graphs: The Social Footprint of Foundation Models","created":"2023-03-28","cited_by_count":32,"area":null},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32,"area":null},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2308.11606","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2310.10513","title":"Unifying Image Processing as Visual Prompting Question Answering","created":"2023-10-16","cited_by_count":29,"area":null},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2408.16219","title":"Training-free Video Temporal Grounding using Large-scale Pre-trained Models","created":"2024-08-29","cited_by_count":28,"area":null},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27,"area":null},{"id":"2311.18827","title":"Motion-Conditioned Image Animation for Video Editing","created":"2023-11-30","cited_by_count":26,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2512.21334","title":"Streaming Video Instruction Tuning","created":"2025-12-24","cited_by_count":26,"area":null},{"id":"2511.05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","created":"2025-11-07","cited_by_count":25,"area":null},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24,"area":null},{"id":"2409.17692","title":"MIO: A Foundation Model on Multimodal Tokens","created":"2024-09-26","cited_by_count":24,"area":null},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2310.05010","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2410.01615","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21,"area":null},{"id":"2501.05453","title":"An Empirical Study of Autoregressive Pre-training from Videos","created":"2025-01-09","cited_by_count":21,"area":null},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20,"area":null},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2403.02076","title":"VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT","created":"2024-03-04","cited_by_count":19,"area":null},{"id":"2407.03197","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","created":"2024-07-03","cited_by_count":19,"area":null},{"id":"2407.15047","title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","created":"2024-07-21","cited_by_count":19,"area":null},{"id":"2504.11732","title":"EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos","created":"2025-04-16","cited_by_count":19,"area":null}],"next_cursor":"100"}