{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T04:23:58Z","timestamp":1777350238715,"version":"3.51.4"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62272364"],"award-info":[{"award-number":["62272364"]}],"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":["62472342"],"award-info":[{"award-number":["62472342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Provincial Key Research and Development Program of Shaanxi","award":["2024GH-ZDXM-47"],"award-info":[{"award-number":["2024GH-ZDXM-47"]}]},{"name":"Higher Education Science Research Planning Project of China Association of Higher Education","award":["24PG0101"],"award-info":[{"award-number":["24PG0101"]}]},{"name":"Teaching Reform Project of the Chinese Society for Educational Development Strategy","award":["ZLB20250728"],"award-info":[{"award-number":["ZLB20250728"]}]},{"name":"China Adult Education Association Project","award":["2023-886ZB"],"award-info":[{"award-number":["2023-886ZB"]}]},{"name":"Xidian University Graduate Teaching Reform Project","award":["AIZS2501"],"award-info":[{"award-number":["AIZS2501"]}]},{"name":"China Education Society of Electronics Teaching Reform Project","award":["DJZ25005"],"award-info":[{"award-number":["DJZ25005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651074","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"2681-2692","source":"Crossref","is-referenced-by-count":2,"title":["EmoSpeaker: One-Shot Fine-Grained Emotion-Controlled Talking Face Generation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1190-676X","authenticated-orcid":false,"given":"Guanwen","family":"Feng","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3210-4272","authenticated-orcid":false,"given":"Haoran","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7316-4354","authenticated-orcid":false,"given":"Yunan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7154-7206","authenticated-orcid":false,"given":"Zhiyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2781-4683","authenticated-orcid":false,"given":"Chaoneng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7435-7136","authenticated-orcid":false,"given":"Zhihao","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6766-8310","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1788-3746","authenticated-orcid":false,"given":"Chi-Man","family":"Pun","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, University of Macau, Macao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"15917","article-title":"An adversarial learning framework for high fidelity face completion","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Wang","year":"2021"},{"issue":"4","key":"ref2","first-page":"1","article-title":"Human performance capture using a virtual mirror","volume":"39","author":"Yu","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref3","first-page":"6995","article-title":"Learning affordance for end-to-end visuomotor robot control in virtual reality","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhu","year":"2021"},{"issue":"4","key":"ref4","first-page":"1","article-title":"Interactive furniture layout using interior design guidelines","volume":"39","author":"Li","year":"2020","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"ref5","first-page":"1","article-title":"Digital actors: A survey of the state of the art","volume":"40","author":"Henderson","year":"2021","journal-title":"ACM Trans. Graph."},{"key":"ref6","first-page":"7606","article-title":"High-quality facial animation with an adaptive 3D morphable model","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Liu","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01621"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288925"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3308441"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091863"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/141"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00639"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_20"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/184"},{"key":"ref41","first-page":"5014","article-title":"Few-shot video-to-video synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32: Annu. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_31"},{"key":"ref43","first-page":"7137","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Siarohin","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref48","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","year":"2016"},{"key":"ref49","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref53","first-page":"6629","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.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref57","article-title":"Perception for autonomous systems (PAZ)","author":"Arriaga","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329499.pdf?arnumber=11329499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:05:21Z","timestamp":1776715521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651074","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}