{"total":206,"rows":[{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652,"area":"mllm"},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109,"area":"mllm"},{"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":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546,"area":"mllm"},{"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":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292,"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":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144,"area":"mllm"},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142,"area":null},{"id":"2405.17220","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","created":"2024-05-27","cited_by_count":131,"area":"alignment"},{"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":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null},{"id":"2410.16261","title":"Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance","created":"2024-10-21","cited_by_count":94,"area":"mllm"},{"id":"2404.18532","title":"MileBench: Benchmarking MLLMs in Long Context","created":"2024-04-29","cited_by_count":88,"area":"mllm"},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81,"area":"mllm"},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2108.08755","title":"Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks","created":"2021-08-19","cited_by_count":69,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"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":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2406.07230","title":"Needle In A Multimodal Haystack","created":"2024-06-11","cited_by_count":58,"area":"mllm"},{"id":"2506.15745","title":"InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding","created":"2025-06-18","cited_by_count":58,"area":"inference"},{"id":"2502.10810","title":"SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding","created":"2025-02-15","cited_by_count":57,"area":"mllm"},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51,"area":null},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49,"area":null},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2105.15076","title":"Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark","created":"2021-05-31","cited_by_count":47,"area":null},{"id":"2601.14724","title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","created":"2026-01-21","cited_by_count":41,"area":"mllm"},{"id":"2407.12679","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","created":"2024-07-17","cited_by_count":40,"area":null},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2502.05177","title":"Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy","created":"2025-02-07","cited_by_count":39,"area":"mllm"},{"id":"2104.01546","title":"Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification","created":"2021-04-04","cited_by_count":37,"area":null},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36,"area":"diffusion"},{"id":"2503.15138","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2025-03-19","cited_by_count":36,"area":null},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","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":"2508.01875","title":"StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding","created":"2025-08-03","cited_by_count":33,"area":"inference"},{"id":"2301.08571","title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","created":"2023-01-20","cited_by_count":31,"area":null},{"id":"2207.14279","title":"The One Where They Reconstructed 3D Humans and Environments in TV Shows","created":"2022-07-28","cited_by_count":30,"area":null},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2109.05569","title":"MovieCuts: A New Dataset and Benchmark for Cut Type Recognition","created":"2021-09-12","cited_by_count":26,"area":null},{"id":"2207.09812","title":"The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing","created":"2022-07-20","cited_by_count":25,"area":null},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25,"area":null},{"id":"2412.09613","title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models","created":"2024-12-12","cited_by_count":25,"area":"mllm"},{"id":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24,"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":"2505.15145","title":"CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation","created":"2025-05-21","cited_by_count":23,"area":null},{"id":"2506.21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models","created":"2025-06-26","cited_by_count":22,"area":"mllm"},{"id":"2508.03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation","created":"2025-08-05","cited_by_count":22,"area":null},{"id":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20,"area":null},{"id":"2406.19875","title":"InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows","created":"2024-06-28","cited_by_count":20,"area":"mllm"},{"id":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"area":null},{"id":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19,"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":"2108.04294","title":"Learning to Cut by Watching Movies","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2201.05277","title":"Boundary-aware Self-supervised Learning for Video Scene Segmentation","created":"2022-01-14","cited_by_count":17,"area":null},{"id":"2504.08296","title":"Generative AI for Film Creation: A Survey of Recent Advances","created":"2025-04-11","cited_by_count":17,"area":"diffusion"},{"id":"2210.11065","title":"MovieCLIP: Visual Scene Recognition in Movies","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2403.11021","title":"Towards Neuro-Symbolic Video Understanding","created":"2024-03-16","cited_by_count":16,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2112.04477","title":"Tracking People by Predicting 3D Appearance, Location & Pose","created":"2021-12-08","cited_by_count":15,"area":null},{"id":"2206.08614","title":"Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment","created":"2022-06-17","cited_by_count":15,"area":null},{"id":"2405.00983","title":"LLM-AD: Large Language Model based Audio Description System","created":"2024-05-02","cited_by_count":15,"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":"2508.08244","title":"Cut2Next: Generating Next Shot via In-Context Tuning","created":"2025-08-11","cited_by_count":15,"area":null},{"id":"2403.12922","title":"Contextual AD Narration with Interleaved Multimodal Sequence","created":"2024-03-19","cited_by_count":14,"area":null},{"id":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"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":"2104.04182","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2111.08774","title":"Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition","created":"2021-11-16","cited_by_count":12,"area":null},{"id":"2203.00307","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","created":"2022-03-01","cited_by_count":12,"area":null},{"id":"2210.05766","title":"Match Cutting: Finding Cuts with Smooth Visual Transitions","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2506.15724","title":"MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference","created":"2025-06-06","cited_by_count":12,"area":"mllm"},{"id":"2202.10650","title":"Movies2Scenes: Using Movie Metadata to Learn Scene Representation","created":"2022-02-22","cited_by_count":11,"area":null},{"id":"2210.12444","title":"Weakly-Supervised Temporal Article Grounding","created":"2022-10-22","cited_by_count":11,"area":null},{"id":"2305.18756","title":"VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2408.00298","title":"Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names","created":"2024-08-01","cited_by_count":11,"area":null},{"id":"2309.10171","title":"Specification-Driven Video Search via Foundation Models and Formal Verification","created":"2023-09-18","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":"2407.07577","title":"IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model","created":"2024-07-10","cited_by_count":10,"area":"mllm"},{"id":"2410.05267","title":"Grounding Partially-Defined Events in Multimodal Data","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2412.16158","title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","created":"2024-12-20","cited_by_count":10,"area":"mllm"},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2510.02423","title":"RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation","created":"2025-10-02","cited_by_count":10,"area":null},{"id":"2205.05487","title":"Scene Consistency Representation Learning for Video Scene Segmentation","created":"2022-05-11","cited_by_count":9,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2404.03477","title":"Towards Automated Movie Trailer Generation","created":"2024-04-04","cited_by_count":9,"area":null},{"id":"2404.13370","title":"Movie101v2: Improved Movie Narration Benchmark","created":"2024-04-20","cited_by_count":9,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","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":"2512.13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","created":"2025-12-15","cited_by_count":9,"area":"wm"},{"id":"2602.00181","title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","created":"2026-01-30","cited_by_count":9,"area":"lr"},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8,"area":null}],"next_cursor":"100"}