{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:25:21Z","timestamp":1782318321790,"version":"3.54.5"},"reference-count":51,"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\/iccv51701.2025.01304","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14051-14060","source":"Crossref","is-referenced-by-count":1,"title":["I2VControl: Disentangled and Unified Video Motion Synthesis Control"],"prefix":"10.1109","author":[{"given":"Wanquan","family":"Feng","sequence":"first","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Qi","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Liu","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhen","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CASIA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengqi","family":"Tu","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxiang","family":"Ma","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Dai","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songtao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[{"name":"Intelligent Creation Team ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Bao","year":"2024","journal-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models"},{"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":"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","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref6","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Seine: Short-to-long video diffusion model for generative transition and prediction","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2023"},{"key":"ref8","article-title":"I2vcontrol-camera: Precise video camera control with adjustable motion strength","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Seedance 1.0: Exploring the boundaries of video generation models","author":"Gao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref14","author":"Haitao","year":"2024","journal-title":"Trackgo: A flexible and efficient method for controllable video generation"},{"key":"ref15","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00772"},{"key":"ref21","article-title":"Berg, Wan-Yen Lo, Piotr Doll\u00e1r, and Ross Girshick","author":"Kirillov","year":"2023","journal-title":"Segment anything. arXiv:2304.02643"},{"key":"ref22","volume-title":"Kling","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26094"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref28","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref29","volume-title":"Runway. Gen2","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref31","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","volume-title":"Wan: Open and advanced large-scale video generative models","year":"2025"},{"key":"ref33","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"International Conference on Learning Representations","author":"Villegas","year":"2022"},{"key":"ref34","article-title":"Predicting video with vqvae","author":"Walker","year":"2021","journal-title":"arXiv preprint"},{"key":"ref35","volume-title":"Boximator: Generating rich and controllable motions for video synthesis","author":"Wang","year":"2024"},{"key":"ref36","article-title":"Magicvideo-v2: Multistage high-aesthetic video generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Magicvideo-v2: Multistage high-aesthetic video generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref39","first-page":"6537","article-title":"Dreamvideo: Composing your dream videos with customized subject and motion","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wei","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref41","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref44","article-title":"Dynamicrafter: Animating open-domain images with video diffusion priors","author":"Xing","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref46","author":"Yin","year":"2023","journal-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"ref48","first-page":"8850","article-title":"Make pixels dance: Highdynamic video generation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zeng","year":"2024"},{"key":"ref49","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref51","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\/11445770.pdf?arnumber=11445770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:49Z","timestamp":1777612609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445770\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01304","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}