{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:18:45Z","timestamp":1761895125782,"version":"build-2065373602"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017413","name":"Innovation Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017413","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209335","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Driven Emotion-Aware 3D Talking Face Generation from Single Image"],"prefix":"10.1109","author":[{"given":"Chun-Shuo","family":"Qiu","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbo","family":"Fu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technologyy,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong Technology and Business University,Shandong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan-Pei","family":"Cao","sequence":"additional","affiliation":[{"name":"VAST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"6","key":"ref1","first-page":"1","article-title":"MakeItTalk: speaker-aware talking-head animation","volume":"39","author":"Zhou","year":"2020","journal-title":"ACM Transactions On Graphics (TOG)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40417-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2024.08.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref15","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042567"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"article-title":"Geneface++: Generalized and stable real-time audio-driven 3d talking face generation","year":"2023","author":"Ye","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3323578"},{"key":"ref21","article-title":"Real3d-portrait: One-shot realistic 3d talking portrait synthesis","author":"Ye","year":"2024","journal-title":"ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"ref23","article-title":"PV3D: A 3D generative model for portrait video generation","author":"Xu","year":"2023","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555377"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref27","article-title":"Out of time: automated lip sync in the wild","author":"Chung","year":"2016","journal-title":"ACCVW"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803603"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0436-y"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3687756"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687686"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209335.pdf?arnumber=11209335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:43:35Z","timestamp":1761889415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209335","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}