{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T05:06:36Z","timestamp":1789621596661,"version":"build-2803163510"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["92270114"],"award-info":[{"award-number":["92270114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tcsvt.2024.3485236","type":"journal-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T13:52:04Z","timestamp":1729691524000},"page":"1318-1330","source":"Crossref","is-referenced-by-count":12,"title":["Prior Preserved Text-to-Image Personalization Without Image Regularization"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6781-3442","authenticated-orcid":false,"given":"Zhicai","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4967-9680","authenticated-orcid":false,"given":"Ouxiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6916-3009","authenticated-orcid":false,"given":"Longhui","family":"Wei","sequence":"additional","affiliation":[{"name":"Huawei Corporation, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-1566","authenticated-orcid":false,"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6148-6329","authenticated-orcid":false,"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Corporation, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref2","article-title":"DisCo: Disentangled control for realistic human dance generation","author":"Wang","year":"2023","journal-title":"arXiv:2307.00040"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3298811"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274228"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29371"},{"key":"ref8","article-title":"HyperDreamBooth: HyperNetworks for fast personalization of text-to-image models","author":"Ruiz","year":"2023","journal-title":"arXiv:2307.06949"},{"key":"ref9","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref11","first-page":"6437","article-title":"Countering language drift with seeded iterated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1447"},{"key":"ref13","article-title":"Custom-edit: Text-guided image editing with customized diffusion models","author":"Choi","year":"2023","journal-title":"arXiv:2305.15779"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00202"},{"key":"ref15","volume-title":"Stable Diffusion","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3347971"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286841"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326293"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3329220"},{"key":"ref23","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv:2209.14792"},{"key":"ref24","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref25","first-page":"1","article-title":"Dreamfusion: Text-to-3D using 2D diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Poole"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00037"},{"key":"ref27","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref28","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2204","journal-title":"arXiv:2204.06125"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref30","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Rombach"},{"key":"ref31","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv:2307.10373"},{"key":"ref32","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023","journal-title":"arXiv:2302.12192"},{"key":"ref33","article-title":"Null-text inversion for editing real images using guided diffusion models","author":"Mokady","year":"2022","journal-title":"arXiv:2211.09794"},{"key":"ref34","article-title":"LEDITS: Real image editing with DDPM inversion and semantic guidance","author":"Tsaban","year":"2023","journal-title":"arXiv:2307.00522"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394850"},{"key":"ref37","article-title":"PhotoMaker: Customizing realistic human photos via stacked ID embedding","author":"Li","year":"2023","journal-title":"arXiv:2312.04461"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref40","article-title":"StyleDrop: Text-to-image generation in any style","author":"Sohn","year":"2023","journal-title":"arXiv:2306.00983"},{"key":"ref41","article-title":"Style aligned image generation via shared attention","author":"Hertz","year":"2023","journal-title":"arXiv:2312.02133"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref43","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","author":"Qiu","year":"2023","journal-title":"arXiv:2306.07280"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref45","article-title":"Cones: Concept neurons in diffusion models for customized generation","author":"Liu","year":"2023","journal-title":"arXiv:2303.05125"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref48","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA","author":"Seale Smith","year":"2023","journal-title":"arXiv:2304.06027"},{"key":"ref49","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"ref52","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref54","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref55","volume-title":"Low-Rank Adaptation for Fast Text-to-Image Diffusion Fine-Tuning","year":"2023"},{"key":"ref56","volume-title":"Clip-vit-large-patch14","year":"2022"},{"key":"ref57","article-title":"Demystifying MMD GANs","author":"Bi\u0142kowski","year":"2018","journal-title":"arXiv:1801.01401"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"ref59","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref60","volume-title":"Dreambooth on Stable Diffusion","year":"2022"},{"key":"ref61","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095167"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10885778\/10731957.pdf?arnumber=10731957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:45Z","timestamp":1767638505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10731957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3485236","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}