{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:51Z","timestamp":1777890231668,"version":"3.51.4"},"reference-count":55,"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\/iccv51701.2025.01336","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14399-14408","source":"Crossref","is-referenced-by-count":0,"title":["UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization"],"prefix":"10.1109","author":[{"given":"Junjie","family":"He","sequence":"first","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Geng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari","year":"2021","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","first-page":"950","article-title":"Idadapter: Learning mixed features for tuning-free personalization of text-toimage models","author":"Cui","year":"2024","journal-title":"CVPR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref7","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref8","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref9","first-page":"36","article-title":"Mix-of-show: Decentralized lowrank adaptation for multi-concept customization of diffusion models","author":"Gu","year":"2024","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Pulid: Pure and lightning id customization via contrastive alignment","author":"Guo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","first-page":"30","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref14","article-title":"LoRA: Low-rank adaptation of large language models","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref17","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref18","first-page":"100895","article-title":"Identity decoupling for multi-subject personalization of text-to-image models","volume":"37","author":"Jang","year":"2024","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Instantfamily: Masked attention for zero-shot multi-id image generation","author":"Kim","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"Omg: Occlusion-friendly personalized multiconcept generation in diffusion models","author":"Kong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00848"},{"key":"ref23","first-page":"36","article-title":"Blip-diffusion: Pretrained subject representation for controllable text-to-image generation and editing","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00213"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00612"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref31","article-title":"Cones 2: Customizable image synthesis with multiple subjects","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuning","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Moa: Mixture-of-attention for subject-context disentanglement in personalized image generation","author":"Ostashev","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00624"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref40","volume-title":"Laion-aesthetics","author":"Schuhmann","year":"2022"},{"key":"ref41","article-title":"Laion-400 m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref42","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref45","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Styleadapter: A single-pass lora-free model for stylized image generation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref48","article-title":"Infinite-id: Identity-preserved personalization via id-semantics decoupling paradigm","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Fastcomposer: Tuning-free multisubject image generation with localized attention","author":"Xiao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Facestudio: Put your face everywhere in seconds","author":"Yan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref52","volume-title":"Reference-only controlnet","author":"Zhang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","article-title":"Flashface: Human image personalization with high-fidelity identity preservation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","article-title":"Storymaker: Towards holistic consistent characters in text-to-image generation","author":"Zhou","year":"2024","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\/11445366.pdf?arnumber=11445366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:01Z","timestamp":1777613521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01336","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}