{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T05:05:18Z","timestamp":1782536718558,"version":"3.54.5"},"reference-count":57,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032006,62472098"],"award-info":[{"award-number":["62032006,62472098"]}],"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\/iccv51701.2025.01191","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12822-12831","source":"Crossref","is-referenced-by-count":2,"title":["MotionFollower: Editing Video Motion via Score-Guided Diffusion"],"prefix":"10.1109","author":[{"given":"Shuyuan","family":"Tu","sequence":"first","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dai","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicheng","family":"Xie","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Qi","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Luo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xintong","family":"Han","sequence":"additional","affiliation":[{"name":"Tencent Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref5","article-title":"Flatten: optical flowguided attention for consistent text-to-video editing","author":"Cong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","volume-title":"Videdit: Zero-shot and spatially aware text-driven video editing","author":"Couairon","year":"2023"},{"key":"ref7","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref10","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"ICLR","author":"Guo","year":"2024"},{"key":"ref11","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"NeurIPS","author":"Heusel","year":"2017"},{"key":"ref12","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref13","article-title":"Cascaded diffusion models for high fidelity image generation","volume-title":"JMLR","author":"Ho","year":"2022"},{"key":"ref14","article-title":"Video diffusion models","volume-title":"NeurIPS","author":"Ho","year":"2022"},{"key":"ref15","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"ICLR","author":"Hong","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00233"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref20","article-title":"Soundini: Sound-guided diffusion for natural video editing","author":"Lee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01126"},{"key":"ref22","article-title":"Human motionformer: Transferring human motions with vision transformers","volume-title":"ICLR","author":"Liu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref25","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref27","article-title":"Dragondiffusion: Enabling drag-style manipulation on diffusion models","volume-title":"ICLR","author":"Mou","year":"2024"},{"key":"ref28","article-title":"Nichol and Prafulla Dhariwal. Improved denoising diffusion probabilistic models","volume-title":"ICML","author":"Quinn","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","article-title":"First order motion model for image animation","volume-title":"NeurIPS","author":"Siarohin","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref34","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","year":"2023"},{"key":"ref35","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref36","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01788"},{"key":"ref38","article-title":"Unigen: Enhanced training & test-time strategies for unified multimodal understanding and generation","author":"Tian","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531365"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01965"},{"key":"ref42","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Disco: Disentangled control for referring human dance generation in real world","volume-title":"CVPR","author":"Wang","year":"2024"},{"key":"ref44","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2003.819861"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00735"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01973"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref56","article-title":"Controlvideo: Training-free controllable text-to-video generation","volume-title":"ICLR","author":"Zhang","year":"2024"},{"key":"ref57","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\/11444217.pdf?arnumber=11444217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:18Z","timestamp":1777529898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01191","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}