{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:00Z","timestamp":1777888740222,"version":"3.51.4"},"reference-count":41,"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\/iccv51701.2025.02385","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25712-25721","source":"Crossref","is-referenced-by-count":0,"title":["From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos"],"prefix":"10.1109","author":[{"given":"Chenjian","family":"Gao","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihe","family":"Ding","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Han","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanpeng","family":"Huang","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zibin","family":"Wang","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianfan","family":"Xue","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01799"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00045"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3687984"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/3610548.3618178","article-title":"Intrinsic harmonization for illumination-aware compositing","volume-title":"Proc. SIGGRAPH Asia","author":"Careaga","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01792"},{"key":"ref7","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref9","article-title":"Lora-edit: Controllable first-frameguided video editing via mask-aware lora fine-tuning","author":"Gao","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01610"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3207091"},{"key":"ref12","article-title":"Neursf: Neural shading field for image harmonization","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref13","volume-title":"Ebsynth: Fast example-based image synthesis and style transfer","author":"Jamriska","year":"2018"},{"key":"ref14","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","volume-title":"Proc.","author":"Karaev","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601209"},{"key":"ref18","article-title":"Anyv2v: A plug-and-play framework for any video-to-video editing tasks","author":"Ku","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1090-6"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00083"},{"key":"ref23","article-title":"Revideo: Remake a video with motion and content control","volume-title":"NeurIPS","author":"Mou","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687656"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360616"},{"key":"ref28","article-title":"Consisti2v: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730647"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276485"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00574"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3375"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01350"},{"key":"ref41","article-title":"Controlcom: Controllable image composition using diffusion model","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"}],"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\/11445626.pdf?arnumber=11445626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:56:04Z","timestamp":1777611364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445626\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02385","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}