{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:10:46Z","timestamp":1787505046189,"version":"build-2736575974"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403345"],"award-info":[{"award-number":["62403345"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanxi Provincial Department of Science and Technology Basic Research","award":["202403021212174"],"award-info":[{"award-number":["202403021212174"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521737","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T14:21:58Z","timestamp":1735050118000},"page":"1835-1847","source":"Crossref","is-referenced-by-count":11,"title":["STNet: Deep Audio\u2013Visual Fusion Network for Robust Speaker Tracking"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5236-7010","authenticated-orcid":false,"given":"Yidi","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7498-6541","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8978-2322","authenticated-orcid":false,"given":"Bing","family":"Yang","sequence":"additional","affiliation":[{"name":"Westlake Institute for Advanced Study, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audio-visual speaker tracking: Progress, challenges, and future directions","author":"Zhao","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01494"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.977177"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3120412"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746950"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2937185"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937600"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2599150"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1247172"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1327252"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803117"},{"key":"ref16","first-page":"974","article-title":"A joint particle filter to track the position and head orientation of people using audio visual cues","volume-title":"Proc. Eur. Signal Process. Conf.","author":"Brutti","year":"2010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461323"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2008.2001429"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.60"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2953020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tsmcb.2008.922063"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69568-4_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1049\/cp.2012.0410"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865702206058"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10190"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2010.06.005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_17"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301977"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3061800"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s23156969"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197528"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340938"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287677"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412682"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747595"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057230"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428373"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20035"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3226330"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2296173"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2277834"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416331"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952687"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16403"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16302"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3079897"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref59","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688191"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12212"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3163771"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/89.568735"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30568-2_16"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814658.pdf?arnumber=10814658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T17:56:14Z","timestamp":1744048574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521737","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}