{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:02:18Z","timestamp":1779912138440,"version":"3.53.1"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["62376140"],"award-info":[{"award-number":["62376140"]}],"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":["62376137"],"award-info":[{"award-number":["62376137"]}],"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":["U23A20315"],"award-info":[{"award-number":["U23A20315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022YQ59"],"award-info":[{"award-number":["ZR2022YQ59"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program for Distinguished Young Scholars of Shandong Province Higher Education Institutions","award":["2023KJ128"],"award-info":[{"award-number":["2023KJ128"]}]},{"name":"Special Fund for Distinguished Professors of Shandong Jianzhu University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3414412","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T17:43:49Z","timestamp":1718387029000},"page":"11056-11069","source":"Crossref","is-referenced-by-count":12,"title":["Audio-Semantic Enhanced Pose-Driven Talking Head Generation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5764","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7586-9232","authenticated-orcid":false,"given":"Yongqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-4197","authenticated-orcid":false,"given":"Xuemeng","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271130"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3311039"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700843"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3375330"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3386836"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3117484"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412187"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2010.5453183"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607233"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00445"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/458"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref30","article-title":"ObamaNet: Photo-realistic lip-sync from text","author":"Kumar","year":"2017","journal-title":"arXiv:1801.01442"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01912"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288547"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3343733"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3215677"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.07.009"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3075491"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref44","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv:1412.5567"},{"key":"ref45","article-title":"DFA-NeRF: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022","journal-title":"arXiv:2201.00791"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","first-page":"1","article-title":"Image translation as diffusion visual programmers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00703"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref52","article-title":"Speech-driven facial reenactment using conditional generative adversarial networks","author":"Ali Jalalifar","year":"2018","journal-title":"arXiv:1803.07461"},{"key":"ref53","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020","journal-title":"arXiv:2002.10137"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/S1525-1578(10)60455-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091863"},{"key":"ref61","first-page":"1755","article-title":"Dlib-ML: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095684"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_8"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551574"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768433\/10557736.pdf?arnumber=10557736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:14:04Z","timestamp":1736453644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10557736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":69,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3414412","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}