{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:37:24Z","timestamp":1776883044177,"version":"3.51.2"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"2022 Hangzhou Key Science and Technology Innovation","award":["2022AIZD0054"],"award-info":[{"award-number":["2022AIZD0054"]}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2022C01011"],"award-info":[{"award-number":["2022C01011"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARC-Discovery","award":["DP220100800"],"award-info":[{"award-number":["DP220100800"]}]},{"name":"ARC-DECRA","award":["DE230100477"],"award-info":[{"award-number":["DE230100477"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176134"],"award-info":[{"award-number":["62176134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute Guo Qiang"},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","award":["2019GQG0002"],"award-info":[{"award-number":["2019GQG0002"]}],"id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SAIC Motor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tpami.2024.3357808","type":"journal-article","created":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T18:39:08Z","timestamp":1706121548000},"page":"4331-4347","source":"Crossref","is-referenced-by-count":13,"title":["StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7271-4481","authenticated-orcid":false,"given":"Suzhen","family":"Wang","sequence":"first","affiliation":[{"name":"Fuxi AI Lab, Netease, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4123-0091","authenticated-orcid":false,"given":"Yifeng","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, THUAI, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1834-4429","authenticated-orcid":false,"given":"Yu","family":"Ding","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, Netease, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4367-0816","authenticated-orcid":false,"given":"Zhipeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, Netease, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5420-0516","authenticated-orcid":false,"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, Netease, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9858-809X","authenticated-orcid":false,"given":"Tangjie","family":"Lv","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab, Netease, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9970-1023","authenticated-orcid":false,"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, THUAI, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-5649","authenticated-orcid":false,"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Queensland, Brisbane, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/184"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref14","article-title":"What comprises a good talking-head video generation?: A survey and benchmark","author":"Chen","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3117484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2022.3146783"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref26","article-title":"You said that?","author":"Chung","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916031"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01912"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref40","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2837742"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11206"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.570"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_14"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref55","first-page":"1307","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume":"32","author":"Yang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.529"},{"key":"ref58","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207606"},{"key":"ref62","first-page":"7137","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2009.5246972"},{"issue":"11","key":"ref67","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10522060\/10413601.pdf?arnumber=10413601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T17:33:39Z","timestamp":1715189619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10413601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3357808","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}