{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:10:52Z","timestamp":1781086252773,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ18017"],"award-info":[{"award-number":["JQ18017"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20223"],"award-info":[{"award-number":["U20A20223"]}],"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":["61721004"],"award-info":[{"award-number":["61721004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y201929"],"award-info":[{"award-number":["Y201929"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RIE2020 Industry Alignment Fund Industry Collaboration Projects (IAF-ICP) Funding Initiative"},{"name":"Cash and In-Kind Contribution from the Industry Partne"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tifs.2022.3146783","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T21:45:44Z","timestamp":1643319944000},"page":"585-598","source":"Crossref","is-referenced-by-count":94,"title":["Everybody\u2019s Talkin\u2019: Let Me Talk as You Want"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0817-2600","authenticated-orcid":false,"given":"Linsen","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref2","article-title":"Arbitrary talking face generation via attentional audio-visual coherence learning","author":"Zhu","year":"2018","journal-title":"arXiv:1812.06589"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-483"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.287"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref10","first-page":"37","article-title":"End-to-end speech-driven realistic facial animation with temporal GANs","volume-title":"Proc. CVPR Workshops","author":"Vougioukas"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref12","article-title":"MakeItTalk: Speaker-aware talking-head animation","author":"Zhou","year":"2020","journal-title":"arXiv:2004.12992"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref16","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv:1412.5567"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356500"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref21","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020","journal-title":"arXiv:2002.10137"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275075"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_37"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref32","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NeurIPS","author":"Goodfellow"},{"key":"ref33","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv:1511.06434"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref36","first-page":"1","article-title":"Dual-agent GANs for photorealistic and identity preserving profile face synthesis","volume-title":"Proc. NeurIPS","author":"Zhao"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01252-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00235"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858819"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019251"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref43","article-title":"Free-form image inpainting with gated convolution","author":"Yu","year":"2018","journal-title":"arXiv:1806.03589"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2638549"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12552"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.455"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.249"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993962"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2010.65"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743785"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.04.002"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00795"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.153"},{"key":"ref61","first-page":"1","article-title":"Conditional image generation for learning the structure of visual objects","volume-title":"Proc. NeurIPS","author":"Jakab"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00159"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882269"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818107"},{"key":"ref66","first-page":"5767","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. NeurIPS","author":"Gulrajani"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818107"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref72","first-page":"1","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. NeurIPS","author":"Heusel"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref74","first-page":"613","article-title":"Generating videos with scene dynamics","author":"Vondrick","year":"2016","journal-title":"NeurIPS"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref76","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10206\/9652463\/09693992.pdf?arnumber=9693992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:36:56Z","timestamp":1705185416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9693992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tifs.2022.3146783","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}