{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:04:01Z","timestamp":1783530241317,"version":"3.55.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0140000"],"award-info":[{"award-number":["2020AAA0140000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702502"],"award-info":[{"award-number":["61702502"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2024.3394850","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T17:49:41Z","timestamp":1714412981000},"page":"6888-6900","source":"Crossref","is-referenced-by-count":7,"title":["OSM-Net: One-to-Many One-Shot Talking Head Generation With Spontaneous Head Motions"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9106-8630","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6642-8160","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7195-0765","authenticated-orcid":false,"given":"Xiaomeng","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yesheng","family":"Chai","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0659-0967","authenticated-orcid":false,"given":"Cai","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3559-8009","authenticated-orcid":false,"given":"Jiao","family":"Dai","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356500"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref7","article-title":"Compressing video calls using synthetic talking heads","author":"Agarwal","year":"2022","journal-title":"arXiv:2210.03692"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref9","article-title":"What comprises a good talking-head video generation?: A survey and benchmark","author":"Chen","year":"2020","journal-title":"arXiv:2005.03201"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3425780"},{"issue":"9","key":"ref11","doi-asserted-by":"crossref","first-page":"2629","DOI":"10.11834\/jig.211243","article-title":"Critical review of human face reenactment methods","volume":"27","author":"Jin","year":"2022","journal-title":"J. Image Graph."},{"key":"ref12","article-title":"Talking face generation by conditional recurrent adversarial network","author":"Song","year":"2018","journal-title":"arXiv:1804.04786"},{"key":"ref13","article-title":"Arbitrary talking face generation via attentional audio-visual coherence learning","author":"Zhu","year":"2018","journal-title":"arXiv:1812.06589"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref18","article-title":"Progressive disentangled representation learning for fine-grained controllable talking head synthesis","author":"Wang","year":"2022","journal-title":"arXiv:2211.14506"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094598"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3117484"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207606"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref37","first-page":"7137","article-title":"First order motion model for image animation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Siarohin"},{"key":"ref38","article-title":"Diffused heads: Diffusion models beat GANs on talking-face generation","author":"Stypu\u0142kowski","year":"2023","journal-title":"arXiv:2301.03396"},{"key":"ref39","article-title":"SadTalker: Learning realistic 3D motion coefficients for stylized audio-driven single image talking face animation","author":"Zhang","year":"2022","journal-title":"arXiv:2211.12194"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00359"},{"key":"ref41","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2016","journal-title":"arXiv:1606.05908"},{"key":"ref42","article-title":"Talking head generation with probabilistic audio-to-visual diffusion priors","author":"Yu","year":"2022","journal-title":"arXiv:2212.04248"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00537"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428233"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268062"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.344"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00092"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275075"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413865"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3106047"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6970"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271130"},{"key":"ref69","article-title":"Memory networks","author":"Weston","year":"2014","journal-title":"arXiv:1410.3916"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref71","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020","journal-title":"arXiv:2002.10137"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/PRAI55851.2022.9904267"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref75","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"ref80","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Chung"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00281"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10510337.pdf?arnumber=10510337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:13:06Z","timestamp":1736453586000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10510337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":82,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3394850","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}