{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:47:05Z","timestamp":1777567625881,"version":"3.51.4"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Artificial Intelligence National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"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":["623B2094"],"award-info":[{"award-number":["623B2094"]}],"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":["62121002"],"award-info":[{"award-number":["62121002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3623025","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:40:16Z","timestamp":1760722816000},"page":"2078-2095","source":"Crossref","is-referenced-by-count":1,"title":["RealCustom++: Representing Images as Real Textual Word for Real-Time Customization"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9449-4491","authenticated-orcid":false,"given":"Mengqi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Ding","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingcong","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MS-diffusion: Multi-subject zero-shot image personalization with layout guidance","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Wang","year":"2025"},{"key":"ref2","article-title":"Ace: All-round creator and editor following instructions via diffusion transformer","volume-title":"Proc. 13th Int. Conf Learn. Representations","author":"Han","year":"2025"},{"key":"ref3","article-title":"Locate, assign, refine: Taming customized promptable image inpainting","author":"Pan","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref5","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref7","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3345866"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref13","first-page":"57500","article-title":"Customizable image synthesis with multiple subjects","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00774"},{"key":"ref15","article-title":"Dreamtuner: Single image is enough for subject-driven generation","author":"Hua","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref19","first-page":"30146","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref23","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref24","first-page":"36777","article-title":"Pulid: Pure and lightning ID customization via contrastive alignment","volume":"37","author":"Guo","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27891"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3618322"},{"key":"ref29","article-title":"$ p+$p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023"},{"key":"ref30","article-title":"Multiresolution textual inversion","volume-title":"Proc. NeurIPS 2022 Workshop on Score-Based Methods","author":"Daras","year":"2022"},{"key":"ref31","article-title":"DreamArtist: Towards controllable one-shot text-to-image generation via contrastive prompt-tuning","author":"Dong","year":"2022"},{"key":"ref32","article-title":"Taming encoder for zero fine-tuning image customization with text-to-image diffusion models","author":"Jia","year":"2023"},{"key":"ref33","first-page":"581","article-title":"Vico: Detail-preserving visual condition for personalized text-to-image generation","volume-title":"Proc. Int. Conf. Remote Sens., Mapping, Image Process.","volume":"13650","author":"Hao","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref38","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref40","article-title":"An image is worth multiple words: Learning object level concepts using multi-concept prompt learning","volume-title":"Proc. 41th Int. Conf. Mach. Learn.","author":"Jin","year":"2024"},{"issue":"285\u2013296","key":"ref41","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"ref43","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gu","year":"2024"},{"key":"ref44","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33187"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401036"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3360623"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17665"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.237"},{"key":"ref53","article-title":"Visualizing and understanding curriculum learning for long short-term memory networks","author":"Cirik","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"issue":"140","key":"ref55","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref59","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref61","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS 2021 Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2022"},{"key":"ref62","article-title":"Kosmos-g: Generating images in context with multimodal large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Pan","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref66","article-title":"$\\lambda$\u03bb-eclipse: Multi-concept personalized text-to-image diffusion models by leveraging clip latent space","author":"Patel","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref68","article-title":"Denoising diffusion implicit models","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref70","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11206511.pdf?arnumber=11206511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:11Z","timestamp":1768255271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11206511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":70,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3623025","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}