{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:50:52Z","timestamp":1779911452226,"version":"3.53.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["U1936203"],"award-info":[{"award-number":["U1936203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcsvt.2023.3311039","type":"journal-article","created":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T17:37:05Z","timestamp":1693589825000},"page":"2734-2748","source":"Crossref","is-referenced-by-count":15,"title":["Stochastic Latent Talking Face Generation Toward Emotional Expressions and Head Poses"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9245-3124","authenticated-orcid":false,"given":"Zhicheng","family":"Sheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-5510","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3271130"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350923"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref7","first-page":"1","article-title":"GeneFace: Generalized and high-fidelity audio-driven 3D talking face synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ye"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413909"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771396"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2002.1004186"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref17","first-page":"1","article-title":"Stochastic variational video prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Babaeizadeh"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2199399"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/184"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"ref32","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889774"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1561\/2200000089"},{"key":"ref35","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chung"},{"key":"ref36","first-page":"1","article-title":"Deep variational Bayes filters: Unsupervised learning of state space models from raw data","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Karl"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10779"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222418"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2984783"},{"key":"ref40","first-page":"1182","article-title":"Stochastic video generation with a learned prior","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Denton"},{"key":"ref41","first-page":"3233","article-title":"Stochastic latent residual video prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref42","first-page":"1","article-title":"Density estimation using real NVP","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dinh"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref44","first-page":"10215","article-title":"Glow: Generative flow with invertible 1\u00d71 convolutions","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref45","first-page":"6571","article-title":"Neural ordinary differential equations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref46","first-page":"1","article-title":"FFJORD: Free-form continuous dynamics for scalable reversible generative models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Grathwohl"},{"key":"ref47","first-page":"1","article-title":"Continuous latent process flows","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref48","first-page":"7805","article-title":"Modeling continuous stochastic processes with dynamic normalizing flows","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref49","first-page":"1","article-title":"Neural spatio-temproal point processes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ricky"},{"key":"ref50","first-page":"13412","article-title":"Ode2Vae: Deep generative second order odes with Bayesian neural networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Yildiz"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref53","first-page":"7137","article-title":"First order motion model for image animation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Siarohin"},{"key":"ref54","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2889052"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10492617\/10237279.pdf?arnumber=10237279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:11:51Z","timestamp":1736453511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10237279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":64,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3311039","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}