{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:27:18Z","timestamp":1781587638574,"version":"3.54.5"},"reference-count":98,"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":["62225112"],"award-info":[{"award-number":["62225112"]}],"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":["62132006"],"award-info":[{"award-number":["62132006"]}],"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":["62101326"],"award-info":[{"award-number":["62101326"]}],"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":["U24A20220"],"award-info":[{"award-number":["U24A20220"]}],"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":["62571324"],"award-info":[{"award-number":["62571324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3623560","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:57:06Z","timestamp":1760983026000},"page":"700-714","source":"Crossref","is-referenced-by-count":7,"title":["SingingHead: A Large-Scale 4D Dataset for Singing Head Animation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7753-1596","authenticated-orcid":false,"given":"Sijing","family":"Wu","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-1748","authenticated-orcid":false,"given":"Yunhao","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weitian","family":"Zhang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5424-4284","authenticated-orcid":false,"given":"Jun","family":"Jia","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3069-060X","authenticated-orcid":false,"given":"Yucheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"USC-SJTU Institute of Cultural and Creative Industry, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-8965","authenticated-orcid":false,"given":"Yichao","family":"Yan","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02104"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3414412"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3386836"},{"key":"ref7","article-title":"Mmface4D: A large-scale multi-modal 4D face dataset for audio-driven 3D face animation","author":"Wu","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref17","article-title":"Dreamtalk: When expressive talking head generation meets diffusion probabilistic models","author":"Ma","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657413"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref26","article-title":"GeneFace: Generalized and high-fidelity audio-driven 3D talking face synthesis","author":"Ye","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3410700.3425435"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0343-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1095878.1095881"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00050"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00177"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657499"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405721"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611775"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612065"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28594"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02009"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_12"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681366"},{"key":"ref49","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Den","year":"2017"},{"key":"ref50","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3623560"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091863"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214100"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142387"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207606"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02116"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00070"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref61","article-title":"DFA-NERF: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3308441"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02486"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0021"},{"key":"ref71","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024"},{"key":"ref72","article-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency","author":"Jiang","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref74","article-title":"Surrey audio-visual expressed emotion (savee) database","author":"Jackson","year":"2014"},{"key":"ref75","article-title":"Metashape","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref77","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00609"},{"key":"ref81","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref82","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn","year":"2015"},{"key":"ref83","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":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.11.004"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref86","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657462"},{"key":"ref92","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":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11208618.pdf?arnumber=11208618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:17Z","timestamp":1768255337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3623560","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}