{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:27:21Z","timestamp":1780057641213,"version":"3.54.0"},"reference-count":73,"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\/501100010787","name":"Institute of Information & Communications Technology Planning & Evaluation (IITP)","doi-asserted-by":"publisher","award":["IITP-2026-RS-2022-00156353"],"award-info":[{"award-number":["IITP-2026-RS-2022-00156353"]}],"id":[{"id":"10.13039\/501100010787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF)","doi-asserted-by":"publisher","award":["RS-202300209125"],"award-info":[{"award-number":["RS-202300209125"]}],"id":[{"id":"10.13039\/501100003725","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\/iccv51701.2025.01342","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14464-14474","source":"Crossref","is-referenced-by-count":1,"title":["MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers"],"prefix":"10.1109","author":[{"given":"Yuechen","family":"Zhang","sequence":"first","affiliation":[{"name":"CUHK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoyang","family":"Liu","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Xia","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohao","family":"Peng","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zexin","family":"Yan","sequence":"additional","affiliation":[{"name":"CMU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Lo","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume":"5","journal-title":"Mixkit: Free assets for your next video project"},{"key":"ref2","journal-title":"Pexels: Free 4k stock videos full hd video clips to download"},{"key":"ref3","author":"Beniaguev","year":"2022","journal-title":"Synthetic faces high quality (sfhq) dataset"},{"key":"ref4","article-title":"Improving image generation with better captions","volume-title":"Technical report, OpenAI","author":"Betker","year":"2023"},{"key":"ref5","author":"Chen","year":"2023","journal-title":"Photoverse: Tuning-free image customization with text-to-image diffusion models"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102479"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"ref8","article-title":"Diffdock: Diffusion steps, twists, and turns for molecular docking","volume-title":"ICLR","author":"Corso","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref14","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"ICLR","author":"Gal","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_73162"},{"key":"ref16","article-title":"Diffuseq: Sequence to sequence text generation with diffusion models","volume-title":"ICLR","author":"Gong","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"ICLR","author":"Guo","year":"2024"},{"key":"ref19","article-title":"Pulid: Pure and lightning id customization via contrastive alignment","author":"Guo","year":"2024","journal-title":"NeurIPS"},{"key":"ref20","author":"He","year":"2024","journal-title":"Id-animator: Zero-shot identity-preserving human video generation"},{"key":"ref21","author":"He","year":"2022","journal-title":"Latent video diffusion models for high-fidelity long video generation"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","first-page":"8633","article-title":"Video diffusion models","volume":"35","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3652557"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref26","first-page":"24240","article-title":"Torsional diffusion for molecular conformer generation","volume":"35","author":"Jing","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref29","first-page":"21696","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"ref31","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref32","first-page":"4328","article-title":"Diffusion-lm improves controllable text generation","volume":"35","author":"Li","year":"2022","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref35","author":"Lin","year":"2024","journal-title":"Open-sora plan: Open-source large video generation model"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref37","volume-title":"Video ocean - filmmaking for everyone","author":"LuChen"},{"key":"ref38","author":"Ma","year":"2024","journal-title":"Latte: Latent diffusion transformer for video generation"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92808-6_2"},{"key":"ref40","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"PMLR"},{"key":"ref41","journal-title":"Video generation models as world simulators"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref43","author":"Peng","year":"2024","journal-title":"Controlnext: Powerful and efficient control for image and video generation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref45","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref46","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref51","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref52","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"issue":"FZJ-2022-00923","key":"ref53","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"NeurIPS Workshop Datacentric AI","author":"Schuhmann","year":"2021"},{"issue":"11","key":"ref54","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref55","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref56","author":"Wang","year":"2024","journal-title":"Instantid: Zero-shot identity-preserving generation in seconds"},{"key":"ref57","author":"Wang","year":"2023","journal-title":"Cogvlm: Visual expert for pretrained language models"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730604"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref63","author":"Xu","year":"2024","journal-title":"Easyanimate: A high-performance long video generation method based on transformer architecture"},{"key":"ref64","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref65","author":"Ye","year":"2023","journal-title":"Ip-adapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01422"},{"issue":"3","key":"ref67","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume-title":"ICLR","volume":"2","author":"Yu","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.32388\/o51iwn"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref72","author":"Zhang","year":"2025","journal-title":"Training-free efficient video generation via dynamic token carving"},{"key":"ref73","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"}],"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\/11444806.pdf?arnumber=11444806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:27:44Z","timestamp":1777530464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01342","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}