{"total":21,"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":"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":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24,"area":null},{"id":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18,"area":null},{"id":"2403.12922","title":"Contextual AD Narration with Interleaved Multimodal Sequence","created":"2024-03-19","cited_by_count":14,"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":"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":"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":"2109.11243","title":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","created":"2021-09-23","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":"2306.10122","title":"Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation","created":"2023-06-16","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":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","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":"2101.02136","title":"LAEO-Net++: revisiting people Looking At Each Other in videos","created":"2021-01-06","cited_by_count":0,"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":"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":"2504.05033","title":"CloSE: A Geometric Shape-Agnostic Cloth State Representation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2606.06338","title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}