{"total":67,"rows":[{"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":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"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":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60,"area":null},{"id":"2305.13500","title":"Learning Emotion Representations from Verbal and Nonverbal Communication","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","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":"2109.05569","title":"MovieCuts: A New Dataset and Benchmark for Cut Type Recognition","created":"2021-09-12","cited_by_count":26,"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":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24,"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":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","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":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19,"area":null},{"id":"2103.06541","title":"Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality","created":"2021-03-11","cited_by_count":17,"area":null},{"id":"2210.11065","title":"MovieCLIP: Visual Scene Recognition in Movies","created":"2022-10-20","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":"2108.03541","title":"OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution","created":"2021-08-07","cited_by_count":15,"area":null},{"id":"2302.08672","title":"Multimodal Subtask Graph Generation from Instructional Videos","created":"2023-02-17","cited_by_count":13,"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":"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":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2208.01954","title":"Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos","created":"2022-08-03","cited_by_count":10,"area":null},{"id":"2106.01006","title":"SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues","created":"2021-06-02","cited_by_count":9,"area":null},{"id":"2111.05956","title":"Feature Generation for Long-tail Classification","created":"2021-11-10","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":"2112.06910","title":"DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points","created":"2021-12-13","cited_by_count":8,"area":null},{"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},{"id":"2308.09775","title":"Long-range Multimodal Pretraining for Movie Understanding","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2304.05634","title":"How you feelin'? Learning Emotions and Mental States in Movie Scenes","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2509.16811","title":"Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven Media","created":"2025-09-20","cited_by_count":6,"area":"agents"},{"id":"2604.11102","title":"OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video","created":"2026-04-13","cited_by_count":6,"area":"mllm"},{"id":"2307.16206","title":"Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual Space","created":"2023-07-30","cited_by_count":5,"area":null},{"id":"2109.11243","title":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2303.14768","title":"Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies","created":"2023-03-26","cited_by_count":4,"area":null},{"id":"2401.13296","title":"Visual Objectification in Films: Towards a New AI Task for Video Interpretation","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2505.17536","title":"Multimodal Conversation Structure Understanding","created":"2025-05-23","cited_by_count":4,"area":"mllm"},{"id":"2510.08543","title":"VideoNorms: Benchmarking Cultural Awareness of Video Language Models","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2107.03783","title":"Use of Affective Visual Information for Summarization of Human-Centric Videos","created":"2021-07-08","cited_by_count":3,"area":null},{"id":"2110.01774","title":"HighlightMe: Detecting Highlights from Human-Centric Videos","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2509.14227","title":"Cin\\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2208.06662","title":"Self-Contained Entity Discovery from Captioned Videos","created":"2022-08-13","cited_by_count":1,"area":null},{"id":"2306.02252","title":"MoviePuzzle: Visual Narrative Reasoning through Multimodal Order Learning","created":"2023-06-04","cited_by_count":1,"area":null},{"id":"2405.11487","title":"\"Previously on ...\" From Recaps to Story Summarization","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2407.12214","title":"VideoClusterNet: Self-Supervised and Adaptive Face Clustering For Videos","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2409.09362","title":"Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM","created":"2024-09-14","cited_by_count":1,"area":"mllm"},{"id":"2505.22084","title":"MObyGaze: a film dataset of multimodal objectification densely annotated by experts","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2511.15887","title":"Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2608.09765","title":"REFRAMED: Towards Realistic Audio Description Generation for Movies","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2101.06573","title":"Understanding in Artificial Intelligence","created":"2021-01-17","cited_by_count":0,"area":null},{"id":"2406.08358","title":"From a Social Cognitive Perspective: Context-aware Visual Social Relationship Recognition","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2412.17238","title":"Modality-Aware Shot Relating and Comparing for Video Scene Detection","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2504.05033","title":"CloSE: A Geometric Shape-Agnostic Cloth State Representation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2506.00667","title":"Scene Detection Policies and Keyframe Extraction Strategies for Large-Scale Video Analysis","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2511.00261","title":"Spot The Ball: A Benchmark for Visual Social Inference","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2604.08819","title":"SenBen: Sensitive Scene Graphs for Explainable Content Moderation","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.10385","title":"GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.23173","title":"One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.05640","title":"AffectSeek: Agentic Affective Understanding in Long Videos under Vague User Queries","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.15152","title":"Can Agents Read the Room? Benchmarking Visual Social Intelligence in Multimodal Simulation","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2606.19706","title":"NEST: Narrative Event Structures in Time for Long Video Understanding","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2607.11798","title":"StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.04302","title":"CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}