{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:28:52Z","timestamp":1787012932219,"version":"3.56.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62236006"],"award-info":[{"award-number":["62236006"]}],"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":["62320106007"],"award-info":[{"award-number":["62320106007"]}],"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":["62032022"],"award-info":[{"award-number":["62032022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013261","name":"Guangdong Provincial Key Laboratory","doi-asserted-by":"publisher","award":["2023B1212060076"],"award-info":[{"award-number":["2023B1212060076"]}],"id":[{"id":"10.13039\/100013261","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":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3523359","type":"journal-article","created":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T14:24:14Z","timestamp":1735223054000},"page":"4026-4038","source":"Crossref","is-referenced-by-count":3,"title":["Multimodal Emotional Talking Face Generation Based on Action Units"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9202-0947","authenticated-orcid":false,"given":"Jiayi","family":"Lyu","sequence":"first","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3624-5926","authenticated-orcid":false,"given":"Xing","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohong","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9258-521X","authenticated-orcid":false,"given":"Hanyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Gan","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5916-8965","authenticated-orcid":false,"given":"Jinbao","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data System Computing, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9460-802X","authenticated-orcid":false,"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/182"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/115"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3311039"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00802"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3311039"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00417-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3375330"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00417-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449075"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref17","article-title":"READ avatars: Realistic emotion-controllable audio driven avatars","author":"Saunders","year":"2023","journal-title":"arXiv:2303.00744"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3274676"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555393"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687525"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01380"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01330"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3117484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01413"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01350"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01621"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref31","article-title":"V-express: Conditional dropout for progressive training of portrait video generation","author":"Wang","year":"2024","journal-title":"arXiv:2406.02511"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref33","article-title":"VASA-1: Lifelike audio-driven talking faces generated in real time","author":"Xu","year":"2024","journal-title":"arXiv:2404.10667"},{"key":"ref34","article-title":"DREAM-talk: Diffusion-based realistic emotional audio-driven method for single image talking face generation","author":"Zhang","year":"2023","journal-title":"arXiv:2312.13578"},{"key":"ref35","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024","journal-title":"arXiv:2406.08801"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref37","article-title":"Progressive disentangled representation learning for fine-grained controllable talking head synthesis","author":"Wang","year":"2022","journal-title":"arXiv:2211.14506"},{"key":"ref38","article-title":"SPACE: Speech-driven portrait animation with controllable expression","author":"Gururani","year":"2022","journal-title":"arXiv:2211.09809"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00639"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01386"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref44","article-title":"GMTalker: Gaussian mixture-based audio-driven emotional talking video portraits","author":"Xia","year":"2023","journal-title":"arXiv:2312.07669"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00639"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.0-104"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288903"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00620"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tsmcb.2004.825931"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.01833"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.928887"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0006-3223(92)90120-o"},{"key":"ref55","article-title":"Towards localized fine-grained control for facial expression generation","author":"Varanka","year":"2024","journal-title":"arXiv:2407.20175"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.08.008"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.409"},{"issue":"5","key":"ref59","first-page":"2176","article-title":"An au-aware algorithm for 3D face reconstruction","volume":"35","author":"Zhang","year":"2023","journal-title":"J. Softw."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref61","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1117\/12.2643588"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.367"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref69","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10816597.pdf?arnumber=10816597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:38Z","timestamp":1767638498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":71,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3523359","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}