{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T11:44:15Z","timestamp":1785843855572,"version":"3.56.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["JP25K21364"],"award-info":[{"award-number":["JP25K21364"]}]},{"name":"JSPS KAKENHI","award":["JP24K23890"],"award-info":[{"award-number":["JP24K23890"]}]},{"name":"JSPS KAKENHI","award":["JP24K20828"],"award-info":[{"award-number":["JP24K20828"]}]},{"name":"JSPS KAKENHI","award":["JP24K15247"],"award-info":[{"award-number":["JP24K15247"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tvcg.2025.3577807","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T13:41:48Z","timestamp":1749217308000},"page":"8755-8766","source":"Crossref","is-referenced-by-count":2,"title":["Diverse Code Query Learning for Speech-Driven Facial Animation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7280-337X","authenticated-orcid":false,"given":"Chunzhi","family":"Gu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-8112","authenticated-orcid":false,"given":"Shigeru","family":"Kuriyama","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8148-1445","authenticated-orcid":false,"given":"Katsuya","family":"Hotta","sequence":"additional","affiliation":[{"name":"Faculty of Science and Engineering, Iwate University, Morioka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1095878.1095881"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3230541"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555471"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00163"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3371064"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref14","article-title":"EmoFace: Emotion-content disentangled speech-driven 3D talking face with mesh attention","author":"Lin","year":"2024"},{"key":"ref15","article-title":"GLDiTalker: Speech-driven 3D facial animation with graph latent diffusion transformer","author":"Lin","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3107669"},{"key":"ref18","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01306"},{"key":"ref20","first-page":"200","article-title":"Animated speech: Research progress and applications","volume-title":"Proc. Auditory-Vis. Speech Process.","author":"Cohen","year":"2001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1201\/b10705"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.22"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"ref25","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00628"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02486"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2312\/SCA\/SCA12\/275-284"},{"key":"ref33","article-title":"3DiFACE: Diffusion-based speech-driven 3D facial animation and editing","author":"Thambiraja","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref35","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_15"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2522628.2522904"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02577"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref41","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00741"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref46","first-page":"30599","article-title":"Towards robust blind face restoration with codebook lookup transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3476275"},{"key":"ref49","article-title":"TalkingEyes: Pluralistic speech-driven 3D eye gaze animation","author":"Zhuang","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13382"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11151252\/11027787.pdf?arnumber=11027787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T19:19:09Z","timestamp":1757099949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11027787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":50,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3577807","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":[[2025,10]]}}}