{"total":86,"rows":[{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"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":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"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":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49,"area":null},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2407.12679","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","created":"2024-07-17","cited_by_count":40,"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":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","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":"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":"2407.01516","title":"E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness","created":"2024-07-01","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":"2111.01300","title":"Masking Modalities for Cross-modal Video Retrieval","created":"2021-11-01","cited_by_count":23,"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":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","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":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","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":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15,"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":"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":"2210.05766","title":"Match Cutting: Finding Cuts with Smooth Visual Transitions","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2210.12444","title":"Weakly-Supervised Temporal Article Grounding","created":"2022-10-22","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":"2209.12164","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","created":"2022-09-25","cited_by_count":10,"area":null},{"id":"2102.05645","title":"Automated Video Labelling: Identifying Faces by Corroborative Evidence","created":"2021-02-10","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":"2505.08350","title":"STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narratives","created":"2025-05-13","cited_by_count":9,"area":null},{"id":"2508.00548","title":"Video Color Grading via Look-Up Table Generation","created":"2025-08-01","cited_by_count":9,"area":null},{"id":"2512.10571","title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","created":"2025-12-11","cited_by_count":9,"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":"2308.14052","title":"MM-AU:Towards Multimodal Understanding of Advertisement Videos","created":"2023-08-27","cited_by_count":8,"area":null},{"id":"2510.00808","title":"What You See is What You Ask: Evaluating Audio Descriptions","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2510.05097","title":"Pulp Motion: Framing-aware multimodal camera and human motion generation","created":"2025-10-06","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":"2309.11569","title":"Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding","created":"2023-09-20","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":"2301.00135","title":"TeViS:Translating Text Synopses to Video Storyboards","created":"2022-12-31","cited_by_count":5,"area":null},{"id":"2309.03978","title":"LanSER: Language-Model Supported Speech Emotion Recognition","created":"2023-09-07","cited_by_count":5,"area":null},{"id":"2605.18467","title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","created":"2026-05-18","cited_by_count":5,"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":"2306.14644","title":"PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas","created":"2023-06-26","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":"2408.01669","title":"SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses","created":"2024-08-03","cited_by_count":4,"area":null},{"id":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2603.28366","title":"AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation","created":"2026-03-30","cited_by_count":4,"area":null},{"id":"2209.12694","title":"Multi-modal Video Chapter Generation","created":"2022-09-26","cited_by_count":3,"area":null},{"id":"2310.08032","title":"Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning","created":"2023-10-12","cited_by_count":3,"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":"2411.03531","title":"Personalized Video Summarization by Multimodal Video Understanding","created":"2024-11-05","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":"2406.13092","title":"Multilingual Synopses of Movie Narratives: A Dataset for Vision-Language Story Understanding","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2410.13585","title":"Pseudo Dataset Generation for Out-of-Domain Multi-Camera View Recommendation","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2410.19760","title":"Movie Trailer Genre Classification Using Multimodal Pretrained Features","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2208.06662","title":"Self-Contained Entity Discovery from Captioned Videos","created":"2022-08-13","cited_by_count":1,"area":null},{"id":"2301.06866","title":"Building Scalable Video Understanding Benchmarks through Sports","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2312.00115","title":"A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval","created":"2023-11-30","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":"2501.07983","title":"V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2604.02409","title":"LumiVideo: An Intelligent Agentic System for Video Color Grading","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2606.01900","title":"Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation","created":"2026-06-01","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":"2203.13281","title":"Movie Genre Classification by Language Augmentation and Shot Sampling","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2312.02188","title":"Video Summarization: Towards Entity-Aware Captions","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2501.19258","title":"VisualSpeech: Enhancing Prosody Modeling in TTS Using Video","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2606.29473","title":"MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.06875","title":"Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.06930","title":"AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.12549","title":"StrAD: A Streaming Method and Benchmark for Audio Description Generation for Long-form Videos","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.27044","title":"Omni-Interactive Universal Embedder","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01816","title":"Video2Reaction: Training Foundation Video Models to Predict Audience Reaction","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.29169","title":"Spot, Separate, and Enhance: Fully Generative Approach for Audio Mixing","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.29721","title":"SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.38683","title":"Unveiling the Value of Motion for Cinematic Camera Trajectories","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}