{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:14Z","timestamp":1777865474072,"version":"3.51.4"},"reference-count":46,"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 Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62402417, 62273302, 62036009, 61936006"],"award-info":[{"award-number":["62402417, 62273302, 62036009, 61936006"]}],"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\/iccv51701.2025.01183","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12737-12746","source":"Crossref","is-referenced-by-count":3,"title":["Magicid: Hybrid Preference Optimization for Id-Consistent and Dynamic-Preserved Video Customization"],"prefix":"10.1109","author":[{"given":"Hengjia","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[{"name":"University of Alabama at Birmingham,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Alabama at Birmingham,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Yi","sequence":"additional","affiliation":[{"name":"Hedra AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boxi","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"ref2","volume-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref3","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref7","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_19"},{"key":"ref9","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref10","article-title":"Pulid: Pure and lightning id customization via contrastive alignment","author":"Guo","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref11","article-title":"Id-animator: Zero-shot identity-preserving human video generation","author":"He","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF02418571"},{"key":"ref15","article-title":"Huvidpo: Enhancing video generation through direct preference optimization for human-centric alignment","author":"Jiang","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007665907178"},{"key":"ref17","article-title":"sdpo: Don\u2019t use your data all at once","author":"Kim","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref18","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01721"},{"key":"ref21","article-title":"Few-shot hybrid domain adaptation of image generator","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li","year":"2023"},{"key":"ref22","article-title":"Unihda: Towards universal hybrid domain adaptation of image generators","author":"Li","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref23","article-title":"Gca-3d: Towards generalized and consistent domain adaptation of 3d generators","author":"Li","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref24","article-title":"Personalvideo: High id-fidelity video customization without dynamic and semantic degradation","author":"Li","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00750"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92808-6_2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref30","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref33","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref37","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref38","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref39","article-title":"Dreamvideo-2: Zero-shot subjectdriven video customization with precise motion control","author":"Wei","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref40","article-title":"Customcrafter: Customized video generation with preserving motion and concept composition abilities","author":"Wu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref42","article-title":"Is dpo superior to ppo for 11 m alignment? a comprehensive study","author":"Xu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref43","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref44","article-title":"Identitypreserving text-to-video generation by frequency decomposition","author":"Yuan","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref45","article-title":"Dreamdpo: Aligning text-to-3d generation with human preferences via direct preference optimization","author":"Zhou","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref46","first-page":"1","volume-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2020"}],"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\/11445391.pdf?arnumber=11445391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:37:45Z","timestamp":1777531065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01183","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}