{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:59:35Z","timestamp":1772521175190,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["62572458"],"award-info":[{"award-number":["62572458"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Rhino-Bird Open Research Fund"},{"name":"Beijing Film Academy Research Base","award":["7000452203\/033"],"award-info":[{"award-number":["7000452203\/033"]}]},{"name":"National Science and Technology Council","award":["113-2221-E006-161-MY3"],"award-info":[{"award-number":["113-2221-E006-161-MY3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tvcg.2026.3655478","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:54:46Z","timestamp":1768856086000},"page":"2883-2897","source":"Crossref","is-referenced-by-count":0,"title":["Make-Your-Anchor+: Temporal Consistent 2D Avatar Generation via Video Diffusion Prior"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3141-9979","authenticated-orcid":false,"given":"Ziyao","family":"Huang","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3975-2483","authenticated-orcid":false,"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-1546","authenticated-orcid":false,"given":"Juan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0066-3448","authenticated-orcid":false,"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3607-2236","authenticated-orcid":false,"given":"Xiaodong","family":"Cun","sequence":"additional","affiliation":[{"name":"Great Bay University, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihang","family":"Bo","sequence":"additional","affiliation":[{"name":"Beijing Film Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6699-2944","authenticated-orcid":false,"given":"Tong-Yee","family":"Lee","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00049"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0284-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref10","first-page":"7137","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Siarohin","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547781"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01089"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00341"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref19","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref21","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref22","article-title":"Imagen Video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref23","article-title":"Make-A-Video: Text-to-video generation without text-video data","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Singer","year":"2023"},{"key":"ref24","first-page":"22680","article-title":"DreamPose: Fashion video synthesis with stable diffusion","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Karras","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref27","first-page":"8153","article-title":"Animate Anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Hu","year":"2024"},{"key":"ref28","article-title":"Dance your latents: Consistent dance generation through spatial-temporal subspace attention guided by motion flow","author":"Fang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00829"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3676165"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0292-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3115902"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3163676"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3235538"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3276973"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3352002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00668"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00870"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00452"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3449075"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_19"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref54","first-page":"6263","article-title":"MagicPose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Chang","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref56","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref65","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Guo","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref68","article-title":"ControlVideo: Training-free controllable text-to-video generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref70","article-title":"Gen-l-video: Multi-text to long video generation via temporal co-denoising","author":"Wang","year":"2023"},{"key":"ref71","article-title":"FreeNoise: Tuning-free longer video diffusion via noise rescheduling","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Qiu","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00319"},{"key":"ref73","article-title":"Classifier-free diffusion guidance","volume-title":"Workshop Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref74","first-page":"6629","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.","author":"Heusel","year":"2017"},{"key":"ref75","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref76","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11418562\/11359069.pdf?arnumber=11359069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:20:39Z","timestamp":1772518839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359069\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3655478","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":[[2026,4]]}}}