{"total":31,"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":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75,"area":null},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40,"area":null},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2201.01928","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18,"area":null},{"id":"2212.11377","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","created":"2022-12-21","cited_by_count":8,"area":null},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2308.09514","title":"Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2502.14892","title":"EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2303.05321","title":"WASD: A Wilder Active Speaker Detection Dataset","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2408.05364","title":"Spherical World-Locking for Audio-Visual Localization in Egocentric Videos","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2412.05150","title":"BIAS: A Body-based Interpretable Active Speaker Approach","created":"2024-12-06","cited_by_count":5,"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":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2203.13166","title":"Self-supervised Video-centralised Transformer for Video Face Clustering","created":"2022-03-24","cited_by_count":3,"area":null},{"id":"2505.10596","title":"Inclusivity of AI Speech in Healthcare: A Decade Look Back","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2207.07296","title":"Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2406.04432","title":"LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2501.18157","title":"Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2511.11473","title":"Proactive Hearing Assistants that Isolate Egocentric Conversations","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2207.07273","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","created":"2022-07-15","cited_by_count":0,"area":null},{"id":"2406.00495","title":"Audio-Visual Talker Localization in Video for Spatial Sound Reproduction","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2406.08089","title":"Identification of Conversation Partners from Egocentric Video","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2411.13674","title":"FabuLight-ASD: Unveiling Speech Activity via Body Language","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2506.18954","title":"SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2509.02571","title":"Gaussian Process Regression of Steering Vectors With Physics-Aware Deep Composite Kernels for Augmented Listening","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2610.08828","title":"When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.14676","title":"CAST-ASD: Causal Attention over Speakers and Time for Online Active Speaker Detection","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}