{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:48:16Z","timestamp":1778082496337,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00951","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10207-10217","source":"Crossref","is-referenced-by-count":5,"title":["Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance"],"prefix":"10.1109","author":[{"given":"Li","family":"Hu","sequence":"first","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Shen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dechao","family":"Meng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lian","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"International conference on machine learning","author":"Arjovsky","year":"2017"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00603"},{"key":"ref7","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","year":"2023"},{"key":"ref8","article-title":"Demamba: Ai-generated video detection on million-scale genvideo benchmark","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref12","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref15","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","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02073"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_19"},{"key":"ref21","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014","author":"Kingma"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01639"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01973"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_17"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_4"},{"key":"ref28","article-title":"Moviecharacter: A tuningfree framework for controllable character video synthesis","author":"Qiu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018224"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","first-page":"234","article-title":"Unet: Convolutional networks for biomedical image segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference","author":"Ronneberger","year":"2015"},{"key":"ref33","article-title":"Invi: Object insertion in videos using off-the-shelf diffusion models","author":"Saini","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref37","article-title":"Denoising diffusion implicit models","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Song","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref39","article-title":"To-wards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","article-title":"Disco: Disentangled control for referring human dance generation in real world","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4592-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00509"},{"key":"ref47","article-title":"Anchorcrafter: Animate cyberanchors saling your products via human-object interacting video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref49","article-title":"Tpc: Test-time procrustes calibration for diffusion-based human image animation","author":"Yoon","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00690"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00534"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_13"},{"key":"ref53","article-title":"Dwnet: Dense warp-based network for pose-guided human video generation","author":"Zablotskaia","year":"2019","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref56","article-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref58","article-title":"Dormant: Defending against pose-driven human image animation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445783.pdf?arnumber=11445783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:39Z","timestamp":1777612599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445783\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00951","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}