{"total":22,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2106.03932","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2108.02607","title":"UniCon: Unified Context Network for Robust Active Speaker Detection","created":"2021-08-05","cited_by_count":28,"area":null},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26,"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":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","cited_by_count":25,"area":null},{"id":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2305.00201","title":"Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT","created":"2023-04-29","cited_by_count":14,"area":null},{"id":"2408.08074","title":"A Survey on Integrated Sensing, Communication, and Computation","created":"2024-08-15","cited_by_count":12,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2303.05321","title":"WASD: A Wilder Active Speaker Detection Dataset","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2412.08594","title":"ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection","created":"2024-12-11","cited_by_count":5,"area":null},{"id":"2202.01286","title":"ASR-Aware End-to-end Neural Diarization","created":"2022-02-02","cited_by_count":4,"area":null},{"id":"2408.12102","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2102.11588","title":"Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain","created":"2021-02-23","cited_by_count":1,"area":null},{"id":"2312.14021","title":"Leveraging Visual Supervision for Array-based Active Speaker Detection and Localization","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2405.08454","title":"Alignment Helps Make the Most of Multimodal Data","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2410.05964","title":"STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2603.16966","title":"CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2608.08510","title":"From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":null}