{"total":15,"rows":[{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2305.15699","title":"Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2306.04822","title":"Optimizing ViViT Training: Time and Memory Reduction for Action Recognition","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2308.12447","title":"MOFO: MOtion FOcused Self-Supervision for Video Understanding","created":"2023-08-23","cited_by_count":3,"area":null},{"id":"2212.04533","title":"Deep Architectures for Content Moderation and Movie Content Rating","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2306.08998","title":"Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2308.15345","title":"IndGIC: Supervised Action Recognition under Low Illumination","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2412.16446","title":"Sensitive Image Classification by Vision Transformers","created":"2024-12-21","cited_by_count":0,"area":null},{"id":"2501.03332","title":"CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2506.00827","title":"Improving Keystep Recognition in Ego-Video via Dexterous Focus","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2610.08192","title":"MacJEPA: Missingness-Robust Audio-Visual Recognition from Untrimmed Egocentric Videos","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}