{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T22:48:30Z","timestamp":1777675710748,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"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 (NSFC)","doi-asserted-by":"publisher","award":["62172421,62072459"],"award-info":[{"award-number":["62172421,62072459"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.00070","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:34:53Z","timestamp":1726508093000},"page":"666-676","source":"Crossref","is-referenced-by-count":72,"title":["SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"],"prefix":"10.1109","author":[{"given":"Ziqiao","family":"Peng","sequence":"first","affiliation":[{"name":"Renmin University of China"}]},{"given":"Wentao","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}]},{"given":"Yue","family":"Shi","sequence":"additional","affiliation":[{"name":"Psyche AI Inc."}]},{"given":"Xiangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences"}]},{"given":"Xiaomei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences"}]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Jun","family":"He","sequence":"additional","affiliation":[{"name":"Renmin University of China"}]},{"given":"Hongyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Zhaoxin","family":"Fan","sequence":"additional","affiliation":[{"name":"Renmin University of China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and man-darin. In","volume-title":"International conference on machine learning","author":"Amodei"},{"key":"ref3","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284869"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1007\/978-3-030-58577-8_25","article-title":"Speech-driven facial animation using cas-caded gans for learning of motion and texture","volume-title":"Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXX 16","author":"Das","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"ref11","article-title":"Nerf: Neural radiance field in 3d vision, a comprehensive review","author":"Gao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"From pixels to portraits A comprehensive survey of talking head generation techniques and applications","author":"Shreyank","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref15","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilib-rium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"1428","article-title":"Towards automatic face-to-face translation","volume-title":"Proceedings of the 27th ACM international conference on multimedia","author":"Prajwal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"issue":"6","key":"ref24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480484","article-title":"Live speech por-traits: real-time photorealistic talking-head animation","volume":"40","author":"Lu","year":"2021","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01357"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"issue":"3","key":"ref29","first-page":"209","article-title":"completely blind","volume-title":"IEEE Sig-nal processing letters","volume":"20","author":"Mittal","year":"2012"},{"issue":"4","key":"ref30","first-page":"1","article-title":"Instant neural graphics primitives with a mul-tire solution hash encoding","volume-title":"ACM Transactions on Graphics (ToG)","volume":"41","author":"M\u00fcller","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555393"},{"key":"ref38","article-title":"Real-time neural radiance talking portrait synthesis via audio-spatial decomposition","volume-title":"arXiv preprint","author":"Tang","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref43","article-title":"Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis","volume-title":"arXiv preprint","author":"Ye","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00319"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref51","first-page":"13545","article-title":"Im avatar: Implicit morphable head avatars from videos","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zheng"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00444"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Seattle, WA, USA","start":{"date-parts":[[2024,6,16]]},"end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10658063.pdf?arnumber=10658063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T06:21:50Z","timestamp":1726813310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10658063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.00070","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}