{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:19:05Z","timestamp":1778051945889,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00704","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7291-7300","source":"Crossref","is-referenced-by-count":0,"title":["LASER: Lip Landmark Assisted Speaker Detection for Robustness"],"prefix":"10.1109","author":[{"given":"Le Thien","family":"Phuc Nguyen","sequence":"first","affiliation":[{"name":"University of Wisconsin,Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoran","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Wisconsin,Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Wisconsin,Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746991"},{"key":"ref6","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.04.018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681488"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SDF55338.2022.9931697"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448124"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-021-00842-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2041"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref17","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.7554\/elife.14521"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref20","article-title":"Learning spatial-temporal graphs for active speaker detection","author":"Roy","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.251"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0018720816644364"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00447"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101178"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref27","volume-title":"Silero vad: pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756549"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01747"},{"key":"ref30","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492299.pdf?arnumber=11492299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:35:29Z","timestamp":1778049329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492299\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00704","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}