{"total":44,"rows":[{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"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":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37,"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":"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":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"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":"2403.12922","title":"Contextual AD Narration with Interleaved Multimodal Sequence","created":"2024-03-19","cited_by_count":14,"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":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","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":"2510.00808","title":"What You See is What You Ask: Evaluating Audio Descriptions","created":"2025-10-01","cited_by_count":8,"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":"2510.25440","title":"More than a Moment: Towards Coherent Sequences of Audio Descriptions","created":"2025-10-29","cited_by_count":5,"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":"2504.19894","title":"CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2412.10002","title":"NowYouSee Me: Context-Aware Automatic Audio Description","created":"2024-12-13","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":"2504.12157","title":"FocusedAD: Character-centric Movie Audio Description","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2507.17844","title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2509.12204","title":"Character-Centric Understanding of Animated Movies","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2507.09693","title":"ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2405.11487","title":"\"Previously on ...\" From Recaps to Story Summarization","created":"2024-05-19","cited_by_count":1,"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":"2608.09765","title":"REFRAMED: Towards Realistic Audio Description Generation for Movies","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.01725","title":"From Visual Cues to Spoken Narration: Rethinking Audio Description","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2503.01416","title":"Learning to Generate Long-term Future Narrations Describing Activities of Daily Living","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.11232","title":"Leveraging multimodal explanatory annotations for video interpretation with Modality Specific Dataset","created":"2025-04-15","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":"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":"2608.30068","title":"TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.30121","title":"What, When, and How: Audio Description as Constrained Global Optimization","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.17042","title":"AD4EDU: Benchmarking University Lecture Audio Description across Accessibility Standards, Metrics, and Learner Preferences","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}