{"total":24,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"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":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"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":"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":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9,"area":null},{"id":"2203.15961","title":"Using Active Speaker Faces for Diarization in TV shows","created":"2022-03-30","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":"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":"2203.11368","title":"Audio visual character profiles for detecting background characters in entertainment media","created":"2022-03-21","cited_by_count":4,"area":null},{"id":"2212.00539","title":"Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2401.04023","title":"Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2504.12157","title":"FocusedAD: Character-centric Movie Audio Description","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2308.00588","title":"Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2410.11068","title":"Character-aware audio-visual subtitling in context","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2209.11896","title":"Unsupervised active speaker detection in media content using cross-modal information","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2402.13152","title":"AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2308.14105","title":"Unified and Dynamic Graph for Temporal Character Grouping in Long Videos","created":"2023-08-27","cited_by_count":0,"area":null},{"id":"2602.15381","title":"Automatic Funny Scene Extraction from Long-form Cinematic Videos","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2605.06309","title":"MultiLinguahah : A New Unsupervised Multilingual Acoustic Laughter Segmentation Method","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.03694","title":"Face versus Body Tracking for Human-Robot Interaction: An Egocentric Dataset","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}