{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:13:56Z","timestamp":1784301236048,"version":"3.55.0"},"reference-count":49,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["61725204"],"award-info":[{"award-number":["61725204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Initiative Scientific Research Program"},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3142387","type":"journal-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:31:00Z","timestamp":1642105860000},"page":"2033-2046","source":"Crossref","is-referenced-by-count":47,"title":["Audio-Driven Talking Face Video Generation With Dynamic Convolution Kernels"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4322-7550","authenticated-orcid":false,"given":"Zipeng","family":"Ye","sequence":"first","affiliation":[{"name":"MOE-Key Laboratory of Pervasive Computing, BNRist, the Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengfei","family":"Xia","sequence":"additional","affiliation":[{"name":"MOE-Key Laboratory of Pervasive Computing, BNRist, the Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-3358","authenticated-orcid":false,"given":"Ran","family":"Yi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1805-1426","authenticated-orcid":false,"given":"Juyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuwei","family":"Huang","sequence":"additional","affiliation":[{"name":"Kwai Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kwai Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-1916","authenticated-orcid":false,"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"MOE-Key Laboratory of Pervasive Computing, BNRist, the Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref15","first-page":"835","article-title":"GANimation: Anatomically-aware facial animation from a single image","author":"pumarola","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130818"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref10","first-page":"1","article-title":"Everybody’s talkin’: Let me talk as you want","volume":"abs 2001 5201","author":"song","year":"2020","journal-title":"CoRR"},{"key":"ref17","article-title":"One-shot face reenactment","author":"zhang","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/h0020861"},{"key":"ref46","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref45","first-page":"1","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"0","journal-title":"Proc NIPS Autodiff Workshop Future Gradient-Based Mach Learn Softw Techn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01235"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref41","first-page":"133.1","article-title":"End-to-end speech-driven facial animation with temporal GANs","author":"vougioukas","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref43","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref9","first-page":"1","article-title":"Audio-driven talking face video generation with natural head pose","volume":"abs 2002 10137","author":"yi","year":"2020","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref3","first-page":"109.1","article-title":"You said that?","author":"chung","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2934824"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2798287"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960656"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2823900"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00704"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1109\/TVCG.2013.249","article-title":"Facewarehouse: A 3D facial expression database for visual computing","volume":"20","author":"cao","year":"2014","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"ref22","first-page":"1998","article-title":"Adaptive convolutional kernels","author":"esquivel","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis Workshop"},{"key":"ref21","first-page":"1","article-title":"Hypernetworks","author":"ha","year":"0","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref27","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Med Image Comput Comput - Assist Interv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/5.554205"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09681173.pdf?arnumber=9681173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:44:27Z","timestamp":1687805067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9681173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3142387","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}