{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:05:17Z","timestamp":1782281117376,"version":"3.54.5"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Key Laboratory of Next Generation Interactive Media Innovative Technology, China","award":["ZDSYS20210623092001004"],"award-info":[{"award-number":["ZDSYS20210623092001004"]}]},{"name":"National Science and Technology Council, Taiwan","award":["114-2221-E-006-114-MY3"],"award-info":[{"award-number":["114-2221-E-006-114-MY3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tvcg.2025.3647628","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T18:30:48Z","timestamp":1766514648000},"page":"4959-4972","source":"Crossref","is-referenced-by-count":0,"title":["ArtCrafter: Text-Image Aligning Artistic Attribute Transfer via Embedding Reframing"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-6584","authenticated-orcid":false,"given":"Nisha","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaer","family":"Huang","sequence":"additional","affiliation":[{"name":"Lenovo, Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0404-1737","authenticated-orcid":false,"given":"Yifan","family":"Pu","sequence":"additional","affiliation":[{"name":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangshan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Guo","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqiang","family":"Yan","sequence":"additional","affiliation":[{"name":"Lenovo, Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6699-2944","authenticated-orcid":false,"given":"Tong-Yee","family":"Lee","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref4","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00823"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00662"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28570"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"ref13","article-title":"CreativeSynth: Creative blending and synthesis of visual arts based on multimodal diffusion","author":"Huang","year":"2024"},{"key":"ref14","article-title":"StyleCrafter: Enhancing stylized text-to-video generation with style adapter","author":"Liu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_2"},{"key":"ref16","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3610614"},{"key":"ref18","article-title":"InstantStyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4095"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91838-4_4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342645"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00581"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref27","article-title":"CSGO: Content-style composition in text-to-image generation","author":"Xing","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref29","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088914"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00359"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612363"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2920"},{"key":"ref37","article-title":"Visual style prompting with swapping self-attention","author":"Jeong","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref39","article-title":"Realistic-vision-v4.0-novae","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref42","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","first-page":"36479","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ho","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref46","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref47","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref49","article-title":"Wikiart website","author":"Contributors","year":"2024"},{"key":"ref50","article-title":"V1 LAION-Aesthetics","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref52","article-title":"Diode: A dense indoor and outdoor depth dataset","author":"Vasiljevic","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11575570\/11313674.pdf?arnumber=11313674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:25:43Z","timestamp":1782278743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11313674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":54,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3647628","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}