{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T05:07:22Z","timestamp":1773896842366,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["2021YFE0205700"],"award-info":[{"award-number":["2021YFE0205700"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ23016"],"award-info":[{"award-number":["JQ23016"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476273"],"award-info":[{"award-number":["62476273"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Fund of Macau","award":["0123\/2022\/A3"],"award-info":[{"award-number":["0123\/2022\/A3"]}]},{"name":"Science and Technology Development Fund of Macau","award":["0044\/2024\/AGJ"],"award-info":[{"award-number":["0044\/2024\/AGJ"]}]},{"name":"Science and Technology Development Fund of Macau","award":["0070\/2020\/AMJ"],"award-info":[{"award-number":["0070\/2020\/AMJ"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521701","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:32:25Z","timestamp":1735155145000},"page":"2570-2581","source":"Crossref","is-referenced-by-count":2,"title":["PMMTalk$:$ Speech-Driven 3D Facial Animation From Complementary Pseudo Multi-Modal Features"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3393-1597","authenticated-orcid":false,"given":"Tianshun","family":"Han","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, the Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8031-8667","authenticated-orcid":false,"given":"Shengnan","family":"Gui","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8722-2094","authenticated-orcid":false,"given":"Yiqing","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, the Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China"}]},{"given":"Baihui","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"given":"Lijian","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4883-5552","authenticated-orcid":false,"given":"Benjia","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, the Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4549-6372","authenticated-orcid":false,"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Company Ltd., Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4115-3068","authenticated-orcid":false,"given":"Quan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-4248","authenticated-orcid":false,"given":"Ruicong","family":"Zhi","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5780-8540","authenticated-orcid":false,"given":"Yanyan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, the Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China"}]},{"given":"Du","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, the Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4735-2885","authenticated-orcid":false,"given":"Jun","family":"Wan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3524496"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_8"},{"key":"ref4","article-title":"An analysis of the current and future state of 3d facial animation techniques and systems","author":"Liu","year":"2009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.7763\/IJCTE.2013.V5.770"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/81"},{"key":"ref7","article-title":"Learning audio-driven viseme dynamics for 3 D face animation","author":"Bao","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614157"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3522615"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00048-X"},{"key":"ref20","article-title":"Audio-Visual automatic speech recognition: An overview","volume":"22","author":"Potamianos","year":"2004","journal-title":"Issues Vis. Audio-Vis. Speech Process."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref23","article-title":"Mmface4D: A large-scale multi-modal 4 D face dataset for audio-driven 3 D face animation","author":"Wu","year":"2023"},{"key":"ref24","article-title":"3d-talkemo: Learning to synthesize 3 D emotional talking head","author":"Wang","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214100"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142387"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210002"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2013.249"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89991-4_6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00068"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15221\/14.357"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126510"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553788"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.374"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00537"},{"key":"ref44","article-title":"Fine-tuned XLSR-53 large model for speech recognition in Chinese","author":"Grosman","year":"2021"},{"key":"ref45","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Conf. Lang. Resour. Eval.","author":"Ardila","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"ref47","article-title":"St-cmds-20170001 1 free st Chinese Mandarin corpus","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref50","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":"ref51","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","year":"2022"},{"key":"ref52","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814703.pdf?arnumber=10814703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T17:33:35Z","timestamp":1747330415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521701","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}