{"total":89,"rows":[{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251,"area":"lr"},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220,"area":"mllm"},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195,"area":"mllm"},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117,"area":"inference"},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"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":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70,"area":"mllm"},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64,"area":"mllm"},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"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,"area":"mllm"},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29,"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":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20,"area":null},{"id":"2504.11199","title":"Video Summarization with Large Language Models","created":"2025-04-15","cited_by_count":16,"area":null},{"id":"2411.07076","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","created":"2024-11-11","cited_by_count":15,"area":"mllm"},{"id":"2501.06835","title":"X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding","created":"2025-01-12","cited_by_count":15,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"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":"2409.20557","title":"Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos","created":"2024-09-30","cited_by_count":12,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2502.08279","title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2510.06040","title":"VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization","created":"2025-10-07","cited_by_count":11,"area":"lr"},{"id":"2503.24379","title":"Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation","created":"2025-03-31","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":"2508.12687","title":"EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding","created":"2025-08-18","cited_by_count":10,"area":"mllm"},{"id":"2406.15771","title":"HCQA @ Ego4D EgoSchema Challenge 2024","created":"2024-06-22","cited_by_count":9,"area":null},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2503.04250","title":"An Egocentric Vision-Language Model based Portable Real-time Smart Assistant","created":"2025-03-06","cited_by_count":8,"area":"mllm"},{"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":"2504.18152","title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding","created":"2025-04-25","cited_by_count":7,"area":"mllm"},{"id":"2505.03173","title":"RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph","created":"2025-05-06","cited_by_count":7,"area":"mllm"},{"id":"2505.12911","title":"HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2407.11683","title":"Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2509.12145","title":"Open-ended Hierarchical Streaming Video Understanding with Vision Language Models","created":"2025-09-15","cited_by_count":6,"area":"mllm"},{"id":"2511.19436","title":"VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection","created":"2025-11-24","cited_by_count":6,"area":"agents"},{"id":"2501.14194","title":"ENTER: Event Based Interpretable Reasoning for VideoQA","created":"2025-01-24","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2409.17702","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2410.11702","title":"It's Just Another Day: Unique Video Captioning by Discriminative Prompting","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2503.24096","title":"DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2509.15233","title":"Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents","created":"2025-09-17","cited_by_count":3,"area":"agents"},{"id":"2602.17869","title":"Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models","created":"2026-02-19","cited_by_count":3,"area":"mllm"},{"id":"2407.19510","title":"EPD: Long-term Memory Extraction, Context-awared Planning and Multi-iteration Decision @ EgoPlan Challenge ICML 2024","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2505.14346","title":"Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2508.20976","title":"WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2509.00385","title":"HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization","created":"2025-08-30","cited_by_count":2,"area":null},{"id":"2510.06973","title":"Addressing the ID-Matching Challenge in Long Video Captioning","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2601.05495","title":"MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding","created":"2026-01-09","cited_by_count":2,"area":"mllm"},{"id":"2602.23294","title":"Towards Long-Form Spatio-Temporal Video Grounding","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2606.17798","title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","created":"2026-06-16","cited_by_count":2,"area":"inference"},{"id":"2606.21949","title":"CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales","created":"2026-06-20","cited_by_count":2,"area":null},{"id":"2408.02336","title":"Infusing Environmental Captions for Long-Form Video Language Grounding","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2504.10443","title":"Multimodal Long Video Modeling Based on Temporal Dynamic Context","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.12605","title":"Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding","created":"2025-05-19","cited_by_count":1,"area":"mllm"},{"id":"2507.06072","title":"MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding","created":"2025-07-08","cited_by_count":1,"area":"driving"},{"id":"2510.23043","title":"HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling","created":"2025-10-27","cited_by_count":1,"area":"ssm"},{"id":"2606.00620","title":"FlowNar: Scalable Streaming Narration for Long-Form Videos","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2606.06991","title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.13141","title":"Rethinking RAG in Long Videos: What to Retrieve and How to Use It?","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2501.04121","title":"Graph-Based Multimodal and Multi-view Alignment for Keystep Recognition","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2502.02406","title":"LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models","created":"2025-02-04","cited_by_count":0,"area":"mllm"},{"id":"2504.12513","title":"AdaVid: Adaptive Video-Language Pretraining","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2506.01102","title":"Keystep Recognition using Graph Neural Networks","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.16082","title":"PR-DETR: Injecting Position and Relation Prior for Dense Video Captioning","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2507.17050","title":"Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models","created":"2025-07-22","cited_by_count":0,"area":"mllm"},{"id":"2508.03039","title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.23957","title":"Vision-Grounded Machine Interpreting: Improving the Translation Process through Visual Cues","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2601.08204","title":"MobiDiary: Autoregressive Action Captioning with Wearable Devices and Wireless Signals","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2603.25145","title":"Learning to Rank Caption Chains for Video-Text Alignment","created":"2026-03-26","cited_by_count":0,"area":"alignment"},{"id":"2605.00826","title":"Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2607.16189","title":"Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2607.28509","title":"RefCaptioner: Multi-Reference Image-Grounded Video Captioning","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.09200","title":"NBA_Streaming: A Large-Scale Benchmark for Fine-Grained Basketball Commentary Generation in Continuous Streams","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.30068","title":"TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.35090","title":"Advancing Video-Text Pretraining with Multi-View Captions","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40195","title":"MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01461","title":"NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16066","title":"PIGEONS: Incremental Long-Video Captioning with Persistent Identity Gallery and Evolving Overarching Narrative Summary","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}