{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:23:09Z","timestamp":1786119789376,"version":"build-2736575974"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2025ZD1601300"],"award-info":[{"award-number":["2025ZD1601300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402138"],"award-info":[{"award-number":["62402138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM901"],"award-info":[{"award-number":["JYB2025XDXM901"]}]},{"name":"Suzhou Key Core Technology Project","award":["SYG2025118"],"award-info":[{"award-number":["SYG2025118"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcsvt.2026.3684020","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T19:55:06Z","timestamp":1776369306000},"page":"11817-11830","source":"Crossref","is-referenced-by-count":0,"title":["M2DAO-Talker: Harmonizing Multi-Granular Motion Decoupling and Alternating Optimization for Talking-Head Generation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4055-7503","authenticated-orcid":false,"given":"Kui","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology and Zhengzhou Advanced Research Institute, Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8302-9083","authenticated-orcid":false,"given":"Shiyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5694-505X","authenticated-orcid":false,"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3298-2574","authenticated-orcid":false,"given":"Hongxun","family":"Yao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3560369"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3488960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3523359"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394850"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271130"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3117484"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3530452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3397828"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref15","article-title":"Real-time neural radiance talking portrait synthesis via audio-spatial decomposition","author":"Tang","year":"2022","journal-title":"arXiv:2211.12368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00070"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681627"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555393"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3476275"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459375"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/83.668027"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"ref35","first-page":"11313","article-title":"SKFlow: Learning optical flow with super kernels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657463"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"ref43","first-page":"1934","article-title":"Real-time photorealistic dynamic scene representation and rendering with 4D Gaussian splatting","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"ref45","article-title":"Shape of motion: 4D reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv:2407.13764"},{"key":"ref46","article-title":"S3 Gaussian: Self-supervised street Gaussians for autonomous driving","author":"Huang","year":"2024","journal-title":"arXiv:2405.20323"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref48","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5220\/0013135300003912"},{"key":"ref50","article-title":"DFA-NeRF: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022","journal-title":"arXiv:2201.00791"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211006"},{"key":"ref52","article-title":"GeneFace: Generalized and high-fidelity audio-driven 3D talking face synthesis","author":"Ye","year":"2023","journal-title":"arXiv:2301.13430"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11643439\/11482202.pdf?arnumber=11482202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T19:06:39Z","timestamp":1786043199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11482202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":56,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3684020","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}