{"total":31,"rows":[{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","cited_by_count":21,"area":null},{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20,"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":"2312.12870","title":"The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective","created":"2023-12-20","cited_by_count":14,"area":null},{"id":"2407.13083","title":"Modeling and Driving Human Body Soundfields through Acoustic Primitives","created":"2024-07-18","cited_by_count":12,"area":null},{"id":"2308.00122","title":"High-Quality Visually-Guided Sound Separation from Diverse Categories","created":"2023-07-31","cited_by_count":11,"area":null},{"id":"2403.12777","title":"Discover and Mitigate Multiple Biased Subgroups in Image Classifiers","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2405.20030","title":"EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2512.24731","title":"EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation","created":"2025-12-31","cited_by_count":6,"area":null},{"id":"2406.02554","title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","created":"2024-03-22","cited_by_count":5,"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":"2505.12154","title":"Learning to Highlight Audio by Watching Movies","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2505.23155","title":"PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2507.04667","title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2409.06224","title":"MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2409.06709","title":"Unveiling Visual Biases in Audio-Visual Localization Benchmarks","created":"2024-08-25","cited_by_count":3,"area":null},{"id":"2309.04579","title":"EGOFALLS: A visual-audio dataset and benchmark for fall detection using egocentric cameras","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2502.11858","title":"Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2505.09615","title":"UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2509.00385","title":"HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization","created":"2025-08-30","cited_by_count":2,"area":null},{"id":"2311.12268","title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2510.20736","title":"Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.03196","title":"Cross-Modal Alignment via Variational Copula Modelling","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.13863","title":"Segmenting Collision Sound Sources in Egocentric Videos","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2603.16936","title":"TDMM-LM: Bridging Facial Understanding and Animation via Language Models","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2607.15265","title":"SceneBind: Binding What and Where Across Vision, Audio and Language","created":"2026-07-16","cited_by_count":0,"area":null}],"next_cursor":null}