{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:47Z","timestamp":1784268707745,"version":"3.55.0"},"reference-count":47,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2042,62320106010"],"award-info":[{"award-number":["U21B2042,62320106010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01011","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10865-10874","source":"Crossref","is-referenced-by-count":4,"title":["LayerAnimate: Layer-Level Control for Animation"],"prefix":"10.1109","author":[{"given":"Yuxue","family":"Yang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lue","family":"Fan","sequence":"additional","affiliation":[{"name":"NLPR & MAIS, Institute of Automation, Chinese Academy of Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuzeng","family":"Lin","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"CreateAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00776"},{"key":"ref3","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"SEINE: Short-to-long video diffusion model for generative transition and prediction","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref5","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref7","article-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning","volume-title":"ICLR","author":"Guo","year":"2024"},{"key":"ref8","article-title":"Ltx-video: Realtime video latent diffusion","author":"HaCohen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"NeurIPS","volume":"30","author":"Heusel","year":"2017"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","volume":"33","author":"Ho","year":"2020"},{"key":"ref12","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"8633","article-title":"Video diffusion models","volume-title":"NeurIPS","volume":"35","author":"Ho","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3687910"},{"key":"ref16","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01973"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01695"},{"key":"ref25","article-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","year":"2023"},{"key":"ref29","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref30","article-title":"Animate-x: Universal character image animation with enhanced motion representation","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"FVD: A new metric for video generation","volume-title":"ICLR workshop","author":"Unterthiner","year":"2019"},{"key":"ref32","article-title":"Framer: Interactive frame interpolation","volume-title":"ICLR","author":"Wang","year":"2025"},{"key":"ref33","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume-title":"NeurIPS","volume":"36","author":"Wang","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3687761"},{"key":"ref36","article-title":"Make-your-video: Customized video generation using textual and structural guidance","author":"Xing","year":"2024","journal-title":"IEEE TVCG"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref39","article-title":"Easyanimate: A high-performance long video generation method based on transformer architecture","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref44","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Tora: Trajectory-oriented diffusion transformer for video generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Allegro: Open the black box of commercial-level video generation model","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"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\/11445625.pdf?arnumber=11445625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:19Z","timestamp":1777529719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01011","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}