{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:50:00Z","timestamp":1783738200852,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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","award":["62206137"],"award-info":[{"award-number":["62206137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206200"],"award-info":[{"award-number":["62206200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276257"],"award-info":[{"award-number":["62276257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Young Talents of Science and Technology in Universities","award":["NJYT23105"],"award-info":[{"award-number":["NJYT23105"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557683","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:59:13Z","timestamp":1743710353000},"page":"3082-3091","source":"Crossref","is-referenced-by-count":3,"title":["Multi-View User Preference Modeling for Personalized Text-to-Image Generation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3183-9218","authenticated-orcid":false,"given":"Huaiwen","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0347-2517","authenticated-orcid":false,"given":"Tianci","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1791-3159","authenticated-orcid":false,"given":"Yinwei","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00634"},{"key":"ref4","first-page":"132238","article-title":"Scene graph generation with role-playing large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Chen","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475665"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02106-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611919"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00823"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645633"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00738"},{"key":"ref22","first-page":"1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref23","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00802"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref28","first-page":"30146","article-title":"BLIP-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume":"36","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref31","first-page":"79858","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Fan","year":"2024"},{"key":"ref32","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref33","first-page":"58348","article-title":"Token-level direct preference optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng","year":"2024"},{"key":"ref34","first-page":"124198","article-title":"Simpo: Simple preference optimization with a reference-free reward","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Meng","year":"2024"},{"key":"ref35","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239183"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681444"},{"key":"ref39","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref42","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref43","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657719"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref48","first-page":"66923","article-title":"Optimizing prompts for text-to-image generation","volume":"36","author":"Hao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948278.pdf?arnumber=10948278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:54Z","timestamp":1748539854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557683","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}