{"total":93,"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198,"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":"2305.15525","title":"Large Language Models are Few-Shot Health Learners","created":"2023-05-24","cited_by_count":118,"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":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"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":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","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":"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":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42,"area":null},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36,"area":null},{"id":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36,"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":"2209.10918","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","created":"2022-09-22","cited_by_count":27,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","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":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24,"area":null},{"id":"2302.13372","title":"Localizing Moments in Long Video Via Multimodal Guidance","created":"2023-02-26","cited_by_count":23,"area":null},{"id":"2303.08345","title":"Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos","created":"2023-03-15","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":"2211.14053","title":"Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization","created":"2022-11-25","cited_by_count":19,"area":null},{"id":"2405.04883","title":"FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2312.06729","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","created":"2023-12-11","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":"2304.04220","title":"Towards Active Learning for Action Spotting in Association Football Videos","created":"2023-04-09","cited_by_count":14,"area":null},{"id":"2403.12922","title":"Contextual AD Narration with Interleaved Multimodal Sequence","created":"2024-03-19","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":"2405.07354","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","created":"2024-05-12","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":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2303.16990","title":"What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions","created":"2023-03-29","cited_by_count":10,"area":null},{"id":"2304.02934","title":"Boundary-Denoising for Video Activity Localization","created":"2023-04-06","cited_by_count":10,"area":null},{"id":"2502.20361","title":"OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection","created":"2025-02-27","cited_by_count":10,"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":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","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":"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":"2308.07102","title":"Temporal Sentence Grounding in Streaming Videos","created":"2023-08-14","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":"2404.15909","title":"Learning Long-form Video Prior via Generative Pre-Training","created":"2024-04-24","cited_by_count":8,"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":"2407.17792","title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","created":"2024-07-25","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":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","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":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2412.07157","title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2503.17975","title":"Shot Sequence Ordering for Video Editing: Benchmarks, Metrics, and Cinematology-Inspired Computing Methods","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2505.16376","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2508.04546","title":"Hierarchical Event Memory for Accurate and Low-latency Online Video Temporal Grounding","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2510.25440","title":"More than a Moment: Towards Coherent Sequences of Audio Descriptions","created":"2025-10-29","cited_by_count":5,"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":"2406.02761","title":"Multi-layer Learnable Attention Mask for Multimodal Tasks","created":"2024-06-04","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":"2410.05586","title":"TeaserGen: Generating Teasers for Long Documentaries","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2504.19894","title":"CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2604.25276","title":"OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2310.17395","title":"Learning Temporal Sentence Grounding From Narrated EgoVideos","created":"2023-10-26","cited_by_count":3,"area":null},{"id":"2401.04105","title":"Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning","created":"2024-01-08","cited_by_count":3,"area":null},{"id":"2412.10002","title":"NowYouSee Me: Context-Aware Automatic Audio Description","created":"2024-12-13","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":"2506.03885","title":"Video, How Do Your Tokens Merge?","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2509.13255","title":"ResidualViT for Efficient Temporally Dense Video Encoding","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2512.10363","title":"Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2606.12300","title":"Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2511.09448","title":"MCAD: Multimodal Context-Aware Audio Description Generation For Soccer","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2511.14143","title":"SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM","created":"2025-11-18","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":"2508.11903","title":"OVG-HQ: Online Video Grounding with Hybrid-modal Queries","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2509.16438","title":"AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2607.06457","title":"Andha-Dhun: A First Look at Audio Descriptions in Hindi","created":"2026-07-07","cited_by_count":0,"area":null},{"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":"2607.23951","title":"TimePLE: Rethinking Temporal Representation for Video Temporal Grounding","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.08075","title":"Search over the Visual World: Persistent Visual Memory, Layered Indexes, and Source-Grounded Evidence","created":"2026-08-08","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":"2609.20508","title":"Grounded Product Understanding in Livestream Videos","created":"2026-09-17","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":"2610.16009","title":"Meaningful Moments: A Corpus of VLM-Derived Temporal Importance Labels for Video Action Recognition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}