{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T08:51:15Z","timestamp":1768035075634,"version":"3.49.0"},"reference-count":68,"publisher":"Tsinghua University Press","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.26599\/cvm.2025.9450491","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:41:37Z","timestamp":1756489297000},"page":"763-779","source":"Crossref","is-referenced-by-count":2,"title":["MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-Based Emotional Talking Face Generation"],"prefix":"10.26599","volume":"11","author":[{"given":"Chenxu","family":"Zhang","sequence":"first","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"Jianfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"Hongyi","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"Guoxian","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"You","family":"Xie","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"Linjie","family":"Luo","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"Yapeng","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas,Richardson,TX,USA,75080"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,San Jose,CA,USA,95110"}]},{"given":"Xiaohu","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas,Richardson,TX,USA,75080"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01912"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450482"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01330"},{"key":"ref14","first-page":"13467","article-title":"FaceComposer: A unified model for versatile facial content creation","volume-title":"Proceedings of the 37th Conference on Neural Information Processing Systems","author":"Wang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0373-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555393"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref21","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref23","article-title":"Arbitrary talking face generation via attentional audio-visual coherence learning","author":"Zhu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0343-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref28","article-title":"You said that?","author":"Chung","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01357"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref34","article-title":"Everybody\u2019s talkin\u2019: Let me talk as you want","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3409380"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3117484"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref40","article-title":"GeneFace: Generalized and high-fidelity audio-driven 3D talking face synthesis","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02481-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00639"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12277"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3099900"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/184"},{"key":"ref56","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref58","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref60","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"ref64","article-title":"First order motion model for image animation","author":"Siarohin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803603"},{"key":"ref68","volume-title":"Improving image generation with better captions","author":"Betker","year":"2023"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11184717\/11145205.pdf?arnumber=11145205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:11:31Z","timestamp":1759295491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11145205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":68,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450491","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}