{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:15:55Z","timestamp":1778080555419,"version":"3.51.4"},"reference-count":39,"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\/icassp49660.2025.10888166","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Advancing Active Speaker Detection for Egocentric Videos"],"prefix":"10.1109","author":[{"given":"Jaesung","family":"Huh","sequence":"first","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan Azcarreta","family":"Ortiz","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashutosh","family":"Pandey","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Aroudi","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel D.E.","family":"Wong","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Nesta","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Buye","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob","family":"Donley","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01747"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2337"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.356"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00345"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00854"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.33"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.435"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_12"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00175"},{"key":"ref18","first-page":"10 470","article-title":"Improving robustness of semantic segmentation to motion-blur using class-centric augmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Rajagopalan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3424478"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref21","article-title":"Intel labs at ego4d challenge 2022: A better baseline for audio-visual diarization","author":"Min","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref24","article-title":"Improving robustness without sacrificing accuracy with patch gaussian augmentation","author":"Lopes","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref27","article-title":"Easycom: An augmented reality dataset to support algorithms for easy communication in noisy environments","author":"Donley","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01802"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref34","article-title":"Using active speaker faces for diarization in tv shows","author":"Sharma","year":"2022"},{"key":"ref35","article-title":"Simple Diarization github repository","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref38","article-title":"InsightFace: 2D and 3D Face Analysis Project","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3025105"}],"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\/10888166.pdf?arnumber=10888166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:16Z","timestamp":1774416376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888166","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}