{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:03:26Z","timestamp":1768280606873,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62306316"],"award-info":[{"award-number":["62306316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322120"],"award-info":[{"award-number":["62322120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2010"],"award-info":[{"award-number":["U21B2010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206278"],"award-info":[{"award-number":["62206278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific and Technological Innovation Important Plan of China","award":["2021ZD0201502"],"award-info":[{"award-number":["2021ZD0201502"]}]},{"name":"Open Research Fund Program of Beijing National Research Center for Information Science and Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3608949","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:32:35Z","timestamp":1757611955000},"page":"140-151","source":"Crossref","is-referenced-by-count":0,"title":["MSSG: Multi-Scale Speaker Graph Network for Active Speaker Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8200-5360","authenticated-orcid":false,"given":"Guanjun","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1632-4293","authenticated-orcid":false,"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-1881","authenticated-orcid":false,"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwang","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268568"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101178"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1561\/2300000049"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535357"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00238"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007350"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1474"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55214.2022.9943352"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746991"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01747"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref19","first-page":"1193","article-title":"How to design a three-stage architecture for audio-visual active speaker detection in the wild","volume-title":"Proc. 2021 IEEE\/CVF Int. Conf. Comput. Vis.","author":"Kpkl","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0408949102"},{"key":"ref23","volume-title":"Gestures and Speech: Psychological Investigations","author":"Feyereisen","year":"1991"},{"key":"ref24","first-page":"1","article-title":"Working with very sparse data to detect speaker and Listener participation in a meetings corpus","volume-title":"Proc. Workshop Programme","volume":"10","author":"Campbell","year":"2006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.02.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2041"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871073"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448124"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521791"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"issue":"6","key":"ref33","first-page":"33","article-title":"Pyramid methods in image processing","volume":"29","author":"Adelson","year":"1984","journal-title":"RCA Engineer"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.10.004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2609928"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_33"},{"key":"ref40","first-page":"17208","article-title":"Weakly-supervised audio-visual segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Mo","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2024.3412821"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445463"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00933"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19922"},{"key":"ref47","first-page":"16975","article-title":"Learning audio-visual dynamics using scene graphs for audio source separation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"35","author":"Chatterjee","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3260282"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02493"},{"key":"ref50","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Hamilton","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref52","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-574"},{"key":"ref60","article-title":"Unicon+ : ICTCAS-UCAS submission to the AVA-activespeaker task at activitynet challenge 2022","author":"Zhang","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11159256.pdf?arnumber=11159256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:58Z","timestamp":1768255318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11159256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3608949","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}