{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:04:15Z","timestamp":1784531055979,"version":"3.55.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.imavis.2026.106088","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:34:48Z","timestamp":1781739288000},"page":"106088","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TuckerDreamer: Subject-driven text-to-image generation via Tucker-based frequency-domain fine-tuning"],"prefix":"10.1016","volume":"173","author":[{"given":"Yuze","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106088_bb0005","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6007","article-title":"Imagic: Text-based real image editing with diffusion models","author":"Kawar","year":"2023"},{"key":"10.1016\/j.imavis.2026.106088_bb0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8543","article-title":"Instantbooth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2024"},{"key":"10.1016\/j.imavis.2026.106088_bb0015","doi-asserted-by":"crossref","first-page":"30286","DOI":"10.52202\/075280-1318","article-title":"Subject-driven text-to-image generation via apprenticeship learning","volume":"36","author":"Chen","year":"2023","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.106088_bb0020","doi-asserted-by":"crossref","first-page":"39869","DOI":"10.52202\/079017-1259","article-title":"Attndreambooth: Towards text-aligned personalized text-to-image generation","volume":"37","author":"Pang","year":"2024","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.106088_bb0025","series-title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22500","author":"Ruiz","year":"2023"},{"key":"10.1016\/j.imavis.2026.106088_bb0030","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"7323","article-title":"Svdiff: Compact parameter space for diffusion fine-tuning","author":"Han","year":"2023"},{"key":"10.1016\/j.imavis.2026.106088_bb0035","article-title":"Flora: Low-rank core space for n-dimension","volume":"10","author":"Si","year":"2024","journal-title":"arXiv Preprint arXiv:240514739"},{"key":"10.1016\/j.imavis.2026.106088_bb0040","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv Preprint arXiv:220801618"},{"issue":"8","key":"10.1016\/j.imavis.2026.106088_bb0045","doi-asserted-by":"crossref","first-page":"6860","DOI":"10.1109\/TCSVT.2024.3369757","article-title":"DisenDreamer: Subject-driven text-to-image generation with sample-aware disentangled tuning","volume":"34","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.imavis.2026.106088_bb0050","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"3568","article-title":"Infusion: Preventing customized text-to-image diffusion from overfitting","author":"Zeng","year":"2024"},{"key":"10.1016\/j.imavis.2026.106088_bb0055","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.106088_bb0060","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.imavis.2026.106088_bb0065","first-page":"10124","article-title":"Scaling up gans for text-to-image synthesis","author":"Kang","year":"2023","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.1016\/j.imavis.2026.106088_bb0070","first-page":"4401","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.1016\/j.imavis.2026.106088_bb0075","series-title":"Zero-shot text-to-image generation","first-page":"8821","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.imavis.2026.106088_bb0080","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022","journal-title":"arXiv Preprint arXiv:220610789"},{"key":"10.1016\/j.imavis.2026.106088_bb0085","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"Pmlr, International Conference on Machine Learning"},{"key":"10.1016\/j.imavis.2026.106088_bb0090","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11315","article-title":"Maskgit: Masked generative image transformer","author":"Chang","year":"2022"},{"key":"10.1016\/j.imavis.2026.106088_bb0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123231","article-title":"Explaining generative diffusion models via visual analysis for interpretable decision-making process","volume":"248","author":"Park","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.imavis.2026.106088_bb0100","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.1016\/j.imavis.2026.106088_bb0105","series-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"volume 1","author":"Devlin","year":"2019"},{"key":"10.1016\/j.imavis.2026.106088_bb0110","series-title":"Learning transferable visual models from natural language supervision. International conference on machine learning","first-page":"8748","author":"Radford","year":"2021"},{"key":"10.1016\/j.imavis.2026.106088_bb0115","first-page":"3836","article-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang","year":"2023","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"10.1016\/j.imavis.2026.106088_bb0120","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22592","article-title":"Magicfusion: Boosting text-to-image generation performance by fusing diffusion models","author":"Zhao","year":"2023"},{"key":"10.1016\/j.imavis.2026.106088_bb0125","doi-asserted-by":"crossref","first-page":"36479","DOI":"10.52202\/068431-2643","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.106088_bb0130","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv Preprint arXiv:220406125"},{"key":"10.1016\/j.imavis.2026.106088_bb0135","doi-asserted-by":"crossref","first-page":"25278","DOI":"10.52202\/068431-1833","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.106088_bb0140","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125747","article-title":"Diff-TST: Diffusion model for one-shot text-image style transfer","volume":"263","author":"Pang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.imavis.2026.106088_bb0145","doi-asserted-by":"crossref","unstructured":"Dong Z, Wei P, Lin L. Dreamartist: Towards controllable one-shot text-to-image generation via contrastive prompt-tuning (2022). 2025.","DOI":"10.1007\/s11263-025-02526-z"},{"key":"10.1016\/j.imavis.2026.106088_bb0150","series-title":"Prefix-tuning: Optimizing continuous prompts for generation, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing\u00a0 (Volume 1: Long Papers)","first-page":"4582","author":"Li","year":"2021"},{"key":"10.1016\/j.imavis.2026.106088_bb0155","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.imavis.2026.106088_bb0160","first-page":"1931","article-title":"Multi-concept customization of text-to-image diffusion","author":"Kumari","year":"2023","journal-title":"Proceed. IEEE\/CVF Conf. Comp. Vision Pattern Recogn."},{"key":"10.1016\/j.imavis.2026.106088_bb0165","first-page":"30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.106088_bb0170","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF02289464","article-title":"Some mathematical notes on three-mode factor analysis","volume":"31","author":"Tucker","year":"1966","journal-title":"Psychometrika"},{"key":"10.1016\/j.imavis.2026.106088_bb0175","doi-asserted-by":"crossref","first-page":"79320","DOI":"10.52202\/075280-3472","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","volume":"36","author":"Qiu","year":"2023","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.106088_bb0180","first-page":"909","article-title":"Decoupled textual embeddings for customized image generation","volume":"38","author":"Cai","year":"2024","journal-title":"Proceed. AAAI Conf. Artific. Intell."},{"key":"10.1016\/j.imavis.2026.106088_bb0185","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv Preprint arXiv:201011929"},{"key":"10.1016\/j.imavis.2026.106088_bb0190","article-title":"Clip-td: Clip targeted distillation for vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv Preprint arXiv:220105729"},{"key":"10.1016\/j.imavis.2026.106088_bb0195","article-title":"Vico: Plug-and-play visual condition for personalized text-to-image generation","author":"Hao","year":"2023","journal-title":"arXiv Preprint arXiv:230600971"},{"key":"10.1016\/j.imavis.2026.106088_bb0200","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"12480","article-title":"DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching","author":"Aiello","year":"2025"},{"key":"10.1016\/j.imavis.2026.106088_bb0205","first-page":"6786","article-title":"Jedi: Joint-image diffusion models for finetuning-free personalized text-to-image generation","author":"Zeng","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"10.1016\/j.imavis.2026.106088_bb0210","series-title":"ACM SIGGRAPH 2024 Conference Papers","first-page":"1","article-title":"Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuning","author":"Ma","year":"2024"},{"key":"10.1016\/j.imavis.2026.106088_bb0215","first-page":"8069","article-title":"Ssr-encoder: Encoding selective subject representation for subject-driven generation","author":"Zhang","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"10.1016\/j.imavis.2026.106088_bb0220","series-title":"DreamBlend: Advancing personalized fine-tuning of text-to-image diffusion models","author":"Ram","year":"2025"},{"key":"10.1016\/j.imavis.2026.106088_bb0225","series-title":"European Conference on Computer Vision","first-page":"252","article-title":"Bootpig: Bootstrapping zero-shot personalized image generation capabilities in pretrained diffusion models","author":"Purushwalkam","year":"2025"},{"key":"10.1016\/j.imavis.2026.106088_bb0230","first-page":"9182","article-title":"Customization assistant for text-to-image generation","author":"Zhou","year":"2024","journal-title":"Proceed. IEEE\/CVF Confer. Comp. Vision Patt. Recogn."},{"key":"10.1016\/j.imavis.2026.106088_bb0235","article-title":"Toffee: Efficient million-scale dataset construction for subject-driven text-to-image generation","author":"Zhou","year":"2024","journal-title":"arXiv Preprint arXiv:240609305"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001952?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001952?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T06:26:45Z","timestamp":1784528805000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626001952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":47,"alternative-id":["S0262885626001952"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106088","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TuckerDreamer: Subject-driven text-to-image generation via Tucker-based frequency-domain fine-tuning","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106088","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106088"}}