{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:10:52Z","timestamp":1761894652094,"version":"build-2065373602"},"reference-count":35,"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\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","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\/icme59968.2025.11209771","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":0,"title":["InterID: Improving Multi-ID Interaction for Personalized Image Generation"],"prefix":"10.1109","author":[{"given":"Siting","family":"Chen","sequence":"first","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijie","family":"Chen","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiji","family":"Tang","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongsheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"issue":"2","key":"ref2","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","year":"2023","author":"Ye","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00733"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"ref16","article-title":"Visual programming for step-by-step text-to-image generation and evaluation","volume":"36","author":"Cho","year":"2024","journal-title":"NeurIPS"},{"key":"ref17","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"article-title":"Instantid: Zero-shot identity-preserving generation in seconds","year":"2024","author":"Wang","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref23","first-page":"57500","article-title":"Cones 2: Customizable image synthesis with multiple subjects","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"article-title":"Cones: Concept neurons in diffusion models for customized generation","year":"2023","author":"Liu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"2","key":"ref27","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref28"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref29"},{"article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","year":"2021","author":"Schuhmann","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","year":"2023","author":"Bai","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","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\/11209771.pdf?arnumber=11209771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:33Z","timestamp":1761888753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209771","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}