{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:23:08Z","timestamp":1791566588434,"version":"4.3.4"},"reference-count":74,"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":"crossref","award":["62572458"],"award-info":[{"award-number":["62572458"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Innovation Funding of Institute of Computing Technology, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["E561090"],"award-info":[{"award-number":["E561090"]}],"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":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3639082","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:25:50Z","timestamp":1764613550000},"page":"5453-5466","source":"Crossref","is-referenced-by-count":1,"title":["MoAnimate: Bridging the Motion-Oriented Latent Representation Gaps in Human Video Animation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1192-7714","authenticated-orcid":false,"given":"Haipeng","family":"Fang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3573-2407","authenticated-orcid":false,"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4018-6194","authenticated-orcid":false,"given":"Zhihao","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3141-9979","authenticated-orcid":false,"given":"Ziyao","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-1546","authenticated-orcid":false,"given":"Juan","family":"Cao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3975-2483","authenticated-orcid":false,"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref2","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref6","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3539832"},{"key":"ref8","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Ho"},{"key":"ref9","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv:2211.13221"},{"key":"ref10","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531390"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3470888"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3548728"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531917"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref18","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref22","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Geyer"},{"key":"ref23","article-title":"FLATTEN: Optical flow-guided attention for consistent text-to-video editing","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Cong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00196"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02602"},{"key":"ref26","article-title":"MotionAgent: Fine-grained controllable video generation via motion field agent","author":"Liao","year":"2025","journal-title":"arXiv:2502.03207"},{"key":"ref27","article-title":"Scaling autoregressive video models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Weissenborn"},{"key":"ref28","article-title":"Stochastic variational video prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Babaeizadeh"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3447648"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref34","article-title":"ControlVideo: Training-free controllable text-to-video generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref35","first-page":"7594","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref37","first-page":"7135","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Siarohin"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232330"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref42","article-title":"MagicPose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","author":"Chang","year":"2023","journal-title":"arXiv:2311.12052"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref44","article-title":"MimicMotion: high-quality human motion video generation with confidence-aware pose guidance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4592-3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3529123"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3386836"},{"key":"ref49","article-title":"Make-A-Video: Text-to-video generation without text-video data","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Singer"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref53","article-title":"FreeNoise: Tuning-free longer video diffusion via noise rescheduling","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Qiu"},{"key":"ref54","article-title":"CoNo: Consistency noise injection for tuning-free long video diffusion","author":"Wang","year":"2024","journal-title":"arXiv:2406.05082"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00398"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612191"},{"key":"ref59","article-title":"FreeInit: Bridging initialization gap in video diffusion models","author":"Wu","year":"2023","journal-title":"arXiv:2312.07537"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/212094.212141"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref69","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv:1812.01717"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref71","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":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00517"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11271671.pdf?arnumber=11271671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:04:08Z","timestamp":1775592248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271671\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":74,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3639082","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}