{"total":19,"rows":[{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"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":"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":"2109.05569","title":"MovieCuts: A New Dataset and Benchmark for Cut Type Recognition","created":"2021-09-12","cited_by_count":26,"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":"2205.11981","title":"OPOM: Customized Invisible Cloak towards Face Privacy Protection","created":"2022-05-24","cited_by_count":22,"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":"2102.05645","title":"Automated Video Labelling: Identifying Faces by Corroborative Evidence","created":"2021-02-10","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":"2401.12039","title":"Look, Listen and Recognise: Character-Aware Audio-Visual Subtitling","created":"2024-01-22","cited_by_count":8,"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":"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":"2106.01667","title":"APES: Audiovisual Person Search in Untrimmed Video","created":"2021-06-03","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":"2410.11068","title":"Character-aware audio-visual subtitling in context","created":"2024-10-14","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":"2203.08931","title":"Creating Multimedia Summaries Using Tweets and Videos","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2610.10163","title":"Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question Answering","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}