{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T14:38:19Z","timestamp":1777819099363,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890226","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["DreamHA: Towards High-Quality Human Animation with Image-to-Video Diffusion Models"],"prefix":"10.1109","author":[{"given":"Longran","family":"Shao","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bonan","family":"Li","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Congying","family":"Han","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzhao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiande","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianchi","family":"Xing","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinmin","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref6","article-title":"Dwnet: Dense warp-based network for pose-guided human video generation","author":"Zablotskaia","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref8","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Generating videos with scene dynamics","volume":"29","author":"Vondrick","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Advances in neural information processing systems","volume":"32","author":"Lyu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"16 761","article-title":"Hierarchical patch vae-gan: Generating diverse videos from a single sample","volume":"33","author":"Gur","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref16","article-title":"Blaze3dm: Marry triplane representation with diffusion for 3d medical inverse problem solving","author":"He","year":"2024"},{"key":"ref17","article-title":"Focus on neighbors and know the whole: Towards consistent dense multiview text-to-image generator for 3d creation","author":"Li","year":"2024"},{"key":"ref18","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref21","article-title":"Towards consistent video editing with text-to-image diffusion models","volume":"36","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","volume-title":"Forty-first International Conference on Machine Learning","author":"Chang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00498"},{"key":"ref25","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref27","article-title":"Tpc: Test-time procrustes calibration for diffusion-based human image animation","author":"Yoon","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611731"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_8"},{"key":"ref30","first-page":"13 718","article-title":"Generalized one-shot domain adaptation of generative adversarial networks","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32488"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref33","article-title":"Denoising diffusion implicit models","author":"Song","year":"2022"},{"key":"ref34","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref39","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890226.pdf?arnumber=10890226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:42Z","timestamp":1774416282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890226","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}