{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:30:44Z","timestamp":1780057844239,"version":"3.54.0"},"reference-count":52,"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\/iccv51701.2025.01334","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14380-14389","source":"Crossref","is-referenced-by-count":2,"title":["Perception-as-Control: Fine-Grained Controllable Image Animation with 3D-Aware Motion Representation"],"prefix":"10.1109","author":[{"given":"Yingjie","family":"Chen","sequence":"first","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifang","family":"Men","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miaomiao","family":"Cui","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"I2vcontrol-camera: Precise video camera control with adjustable motion strength","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"I2vcontrol: Disentangled and unified video motion synthesis control","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218"},{"key":"ref7","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref9","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","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":"ref11","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref16","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02602"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00859"},{"key":"ref20","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref22","article-title":"Follow-your-click: Open-domain regional image animation via short prompts","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Follow-your-click: Open-domain regional image animation via short prompts","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Mimo: Controllable character video synthesis with spatial decomposed modeling","author":"Men","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"issue":"2","key":"ref27","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref30","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref33","article-title":"Unknown","volume-title":"PySceneDetect","year":"2024"},{"key":"ref34","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01165"},{"key":"ref36","first-page":"1761","article-title":"Tartanvo: A generalizable learning-based vo","volume-title":"In Conference on Robot Learning","author":"Wang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref40","article-title":"Trajectory attention for fine-grained video motion control","author":"Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Camco: Camera-controllable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref43","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Ipadapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref49","article-title":"Tora: Trajectory-oriented diffusion transformer for video generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"ref51","article-title":"Cami2v: Camera-controlled image-to-video diffusion model","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"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\/11443510.pdf?arnumber=11443510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:37Z","timestamp":1777613317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01334","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}