{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:20Z","timestamp":1776890000559,"version":"3.51.2"},"reference-count":30,"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\/icassp49660.2025.10889368","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Audio-Faces Intra-Frame Alignment with Graph Attention Networks for Active Speaker Detection"],"prefix":"10.1109","author":[{"given":"Yongkang","family":"Yin","sequence":"first","affiliation":[{"name":"Peking University,ADSPLAB, School of ECE,Shenzhen,China"}]},{"given":"Xusheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University,ADSPLAB, School of ECE,Shenzhen,China"}]},{"given":"Liming","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University,ADSPLAB, School of ECE,Shenzhen,China"}]},{"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab,Shenzhen,China"}]},{"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[{"name":"Peking University,ADSPLAB, School of ECE,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746991"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00123"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01747"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55214.2022.9943352"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-80"},{"key":"ref17","first-page":"2","article-title":"Multi-task learning for audio-visual active speaker detection","volume":"4","author":"Zhang","year":"2019","journal-title":"The ActivityNet Large-Scale Activity Recognition Challenge"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448124"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref22","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"64-67","key":"ref23","first-page":"2","article-title":"Recurrent neural networks","volume":"5","author":"Medsker","year":"2001","journal-title":"Design and Applications"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0069-y"},{"issue":"20","key":"ref25","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"stat"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"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\/10889368.pdf?arnumber=10889368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:55Z","timestamp":1774416175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889368","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}