{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T21:00:29Z","timestamp":1775509229385,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62322608"],"award-info":[{"award-number":["62322608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506180"],"award-info":[{"award-number":["62506180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771522"],"award-info":[{"award-number":["2025M771522"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Huawei\u2019s AI Hundred Schools Program and was Carried out Using Huawei Ascend AI Technology Stack"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3676251","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:52:55Z","timestamp":1774554775000},"page":"3369-3380","source":"Crossref","is-referenced-by-count":0,"title":["High-Fidelity and Lip-Synced Talking Face Synthesis via Landmark-Based Diffusion Model"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-4691","authenticated-orcid":false,"given":"Weizhi","family":"Zhong","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8717-8351","authenticated-orcid":false,"given":"Junfan","family":"Lin","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peixin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1843-3180","authenticated-orcid":false,"given":"Feng","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475318"},{"key":"ref2","article-title":"DialogueNeRF: Towards realistic avatar face-to-face conversation video generation","author":"Zhou","year":"2022","journal-title":"arXiv:2203.07931"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01227"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613753"},{"key":"ref7","article-title":"GeneFace: Generalized and high-fidelity audio-driven 3D talking face synthesis","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Ye"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/184"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref22","article-title":"GAIA: Data-driven zero-shot talking avatar generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"He"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref24","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref26","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00590"},{"key":"ref29","article-title":"DiffSketcher: Text guided vector sketch synthesis through latent diffusion models","author":"Xing","year":"2023","journal-title":"arXiv:2306.14685"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00672"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25313"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref35","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hertz"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"ref38","article-title":"Advancing pose-guided image synthesis with progressive conditional diffusion models","author":"Shen","year":"2023","journal-title":"arXiv:2310.06313"},{"key":"ref39","article-title":"DifFace: Blind face restoration with diffused error contraction","author":"Yue","year":"2022","journal-title":"arXiv:2212.06512"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00521"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104911"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357808"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024","journal-title":"arXiv:2406.08801"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref54","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12010218"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref58","article-title":"MediaPipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv:1906.08172"},{"key":"ref59","volume-title":"Latent-Diffusion","author":"Rombach","year":"2022"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11456857.pdf?arnumber=11456857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:59:18Z","timestamp":1775505558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11456857\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3676251","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}