{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:10:36Z","timestamp":1781086236614,"version":"3.54.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["U1736123"],"award-info":[{"award-number":["U1736123"]}],"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":["61572450"],"award-info":[{"award-number":["61572450"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"USTC Research Fund of the Double First-Class Initiative","award":["YD2350002001"],"award-info":[{"award-number":["YD2350002001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/tcsvt.2020.2973374","type":"journal-article","created":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T21:30:01Z","timestamp":1581543001000},"page":"203-216","source":"Crossref","is-referenced-by-count":59,"title":["Multimodal Inputs Driven Talking Face Generation With Spatial\u2013Temporal Dependency"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-761X","authenticated-orcid":false,"given":"Lingyun","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5688-4130","authenticated-orcid":false,"given":"Qiang","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref33","author":"young","year":"2002","journal-title":"The HTK Book (for HTK Version 3 2)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887027"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299058"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref28","article-title":"Sound to visual: Hierarchical cross-modal talking face video generation","author":"chen","year":"2019","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit Workshops"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651375"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref20","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"High-resolution image synthesis and semantic manipulation with conditional GANs","author":"wang","year":"2017","journal-title":"arXiv 1711 11585"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref24","article-title":"Video-to-video synthesis","author":"wang","year":"2018","journal-title":"arXiv 1808 06601"},{"key":"ref23","article-title":"MoCoGAN: Decomposing motion and content for video generation","author":"tulyakov","year":"2017","journal-title":"arXiv 1707 04993"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2709465"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.11.008"},{"key":"ref50","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understand IEEE Signal Process Soc"},{"key":"ref51","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref11","first-page":"446","article-title":"Synthesizing photo-real talking head via trajectory-guided sample selection","author":"wang","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref16","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2018","journal-title":"arXiv 1805 08318"},{"key":"ref17","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2016","journal-title":"ArXiv 1611 07004"},{"key":"ref18","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018893"},{"key":"ref4","article-title":"FLNet: Landmark driven fetching and learning network for faithful talking facial animation synthesis","author":"gu","year":"2019","journal-title":"arXiv 1911 09224"},{"key":"ref3","article-title":"Talking face generation by conditional recurrent adversarial network","author":"song","year":"2018","journal-title":"arXiv 1804 04786"},{"key":"ref6","first-page":"37","article-title":"End-to-end speech-driven facial animation with temporal GANs","author":"vougioukas","year":"2019","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.109"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.06.006"},{"key":"ref7","article-title":"ObamaNet: Photo-realistic lip-sync from text","author":"kumar","year":"2017","journal-title":"arXiv 1801 01442"},{"key":"ref49","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc Autodiff Workshop Future Gradient-Based Mach Learn Softw Techn (NIPSW)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB.2017.7986143"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref47","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref41","article-title":"FaceForensics: A large-scale video dataset for forgery detection in human faces","author":"r\u00f6ssler","year":"2018","journal-title":"arXiv 1803 09179"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8080854"},{"key":"ref43","author":"li","year":"2016","journal-title":"Toward A Practical Perceptual Video Quality Metric"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9316347\/08995571.pdf?arnumber=8995571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:19Z","timestamp":1652194219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8995571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":51,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.2973374","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}