{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:11:48Z","timestamp":1774419108570,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889699","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Egocentric Speaker Diarization with Vision-Guided Clustering and Adaptive Speech Re-detection"],"prefix":"10.1109","author":[{"given":"He","family":"Huang","sequence":"first","affiliation":[{"name":"Hunan University,China"}]},{"given":"Haoyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Hunan University,China"}]},{"given":"Daibo","family":"Liu","sequence":"additional","affiliation":[{"name":"Hunan University,China"}]},{"given":"Haowen","family":"Chen","sequence":"additional","affiliation":[{"name":"Hunan University,China"}]},{"given":"Minjie","family":"Cai","sequence":"additional","affiliation":[{"name":"Hunan University,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053323"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3027117"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3050265"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01409"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447323"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10404"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447957"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref19","article-title":"3d-speaker: A large-scale multi-device, multi-distance, and multi-dialect corpus for speech representation disentanglement","author":"Zheng","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10106"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.30"},{"key":"ref30","article-title":"Intel labs at ego4d challenge 2022: A better baseline for audiovisual diarization","author":"Min","year":"2022"},{"key":"ref31","article-title":"Sthg: Spatial-temporal heterogeneous graph learning for advanced audio-visual diarization","author":"Min","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888389"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889699.pdf?arnumber=10889699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:31Z","timestamp":1774416031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889699","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}