{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:21:51Z","timestamp":1740169311098,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant"},{"DOI":"10.13039\/501100014188","name":"Korean Government (MSIT), Development of Artificial Intelligence Technology for Multi-Speaker Dialog Modeling","doi-asserted-by":"publisher","award":["2022-0-00989"],"award-info":[{"award-number":["2022-0-00989"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3325474","type":"journal-article","created":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T17:55:13Z","timestamp":1697651713000},"page":"116561-116569","source":"Crossref","is-referenced-by-count":1,"title":["Modeling Long-Term Multimodal Representations for Active Speaker Detection With Spatio-Positional Encoder"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2814-9386","authenticated-orcid":false,"given":"Minyoung","family":"Kyoung","sequence":"first","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8216-4812","authenticated-orcid":false,"given":"Hwa Jeon","family":"Song","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-80"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref14","first-page":"12462","article-title":"Active speakers in context","author":"alc\u00e1zar","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3116"},{"key":"ref31","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref11","first-page":"1173","article-title":"How to design a three-stage architecture for audio-visual active speaker detection in the wild","author":"k\u00f6p\u00fckl\u00fc","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis (ICCV)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.04.018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/GLU.2017-10"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3005467.3005470"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref19","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref8","first-page":"1589","article-title":"Look who’s talking: Speaker detection using video and audio correlation","author":"cutler","year":"2000","journal-title":"Proc ICME"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.92"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029977"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413776"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3061800"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10287283.pdf?arnumber=10287283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:30:29Z","timestamp":1699903829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10287283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3325474","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}