{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:36:56Z","timestamp":1770932216813,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tvcg.2025.3649047","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:38:10Z","timestamp":1767033490000},"page":"2568-2582","source":"Crossref","is-referenced-by-count":0,"title":["Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4526-440X","authenticated-orcid":false,"given":"Zikai","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6869-780X","authenticated-orcid":false,"given":"Yihan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8006-3663","authenticated-orcid":false,"given":"Xuemiao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4281-6214","authenticated-orcid":false,"given":"Cheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Centre for Smart Health, Hong Kong Polytechnic University, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0016-9055","authenticated-orcid":false,"given":"Xiaofen","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-0860","authenticated-orcid":false,"given":"Jing","family":"Qin","sequence":"additional","affiliation":[{"name":"Centre for Smart Health, Hong Kong Polytechnic University, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350865"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3623560"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0343-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00514"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00184"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799460"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0057-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/17470218.2014.971034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32277"},{"key":"ref10","article-title":"SINGER: Vivid audio-driven singing video generation with multi-scale spectral diffusion model","author":"Li","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00262"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2312\/SCA\/SCA12\/275-284"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2522628.2522904"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611775"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456213"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3409568"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00060"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00283"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6911"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"ref39","article-title":"Human motion diffusion model","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Tevet","year":"2022"},{"key":"ref40","article-title":"Human motion diffusion as a generative prior","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shafir","year":"2023"},{"key":"ref41","article-title":"Text-driven human motion generation with motion masked diffusion model","author":"Chen","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657447"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3581808"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3390182"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681366"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28594"},{"key":"ref48","first-page":"1","article-title":"Audio-driven speech animation with text-guided expression","volume-title":"Proc. Pacific Graph. Conf. Papers Posters","author":"Jung","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111447"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3410700.3425435"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00609"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2018.01.012"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1121\/1.5002886"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.117"},{"key":"ref60","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lewis","year":"2020"},{"key":"ref61","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195169157.003.0014"},{"key":"ref63","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref64","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref67","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3423382"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32449"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00703"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_16"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11392779\/11316801.pdf?arnumber=11316801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:23Z","timestamp":1770929963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":74,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3649047","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}