{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:08:43Z","timestamp":1783094923685,"version":"3.54.6"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209272","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple Subjects"],"prefix":"10.1109","author":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hebei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansong","family":"Peng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siying","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence,Hefei Comprehensive National Science Center,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00828"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02603"},{"key":"ref4","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref8","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","author":"Li","year":"2024","journal-title":"NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref10","article-title":"Kosmos-g: Generating images in context with multimodal large language models","author":"Pan","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref12","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref13","article-title":"\u03bb-eclipse: Multi-concept personalized text-to-image diffusion models by leveraging clip latent space","author":"Patel","year":"2024"},{"key":"ref14","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00630"},{"key":"ref16","article-title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance","author":"Wang","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref27","article-title":"Lw-detr: A transformer replacement to yolo for real-time detection","author":"Chen","year":"2024"},{"key":"ref28","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209272.pdf?arnumber=11209272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:40:30Z","timestamp":1761889230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209272","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}