{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:53:15Z","timestamp":1771267995824,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF China","award":["62172357"],"award-info":[{"award-number":["62172357"]}]},{"name":"NSF China","award":["62421003"],"award-info":[{"award-number":["62421003"]}]},{"name":"NSF China","award":["62572430"],"award-info":[{"award-number":["62572430"]}]},{"name":"XPLORER PRIZE"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tvcg.2025.3615390","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T17:53:08Z","timestamp":1759168388000},"page":"10801-10814","source":"Crossref","is-referenced-by-count":1,"title":["A Semantic Talking Style Space for Speech-Driven Facial Animation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5525-6527","authenticated-orcid":false,"given":"Yujin","family":"Chai","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5223-4253","authenticated-orcid":false,"given":"Yanlin","family":"Weng","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5485-3752","authenticated-orcid":false,"given":"Tianjia","family":"Shao","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4243-6112","authenticated-orcid":false,"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258880"},{"key":"ref2","first-page":"275","article-title":"Dynamic units of visual speech","volume-title":"Proc. ACM SIGGRAPH\/Eurographics Symp. Comput. Animation","author":"Taylor"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref11","first-page":"700","article-title":"Unsupervised image-to-image translation networks","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01284-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00520"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114308"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356500"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref18","article-title":"Multiface: A dataset for neural face rendering","author":"Wuu","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.287"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3230541"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3581808"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28594"},{"key":"ref38","first-page":"1","article-title":"Audio-driven speech animation with text-guided expression","volume-title":"Proc. Pacific Graph. Conf. Papers Posters","author":"Jung"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00639"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref42","article-title":"3DiFACE: Diffusion-based speech-driven 3D facial animation and editing","author":"Thambiraja","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456213"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref51","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.","author":"Baevski"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"ref53","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref55","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins"},{"key":"ref56","first-page":"1","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Press"},{"key":"ref57","article-title":"JAX: Composable transformations of Python NumPy programs","author":"Bradbury","year":"2018"},{"key":"ref58","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2024.123471"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11231102\/11184642.pdf?arnumber=11184642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:10:07Z","timestamp":1762539007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11184642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":62,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3615390","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":[[2025,12]]}}}