{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:06:11Z","timestamp":1770743171507,"version":"3.49.0"},"reference-count":65,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82121003"],"award-info":[{"award-number":["82121003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tvcg.2025.3638700","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:37:55Z","timestamp":1764959875000},"page":"2300-2311","source":"Crossref","is-referenced-by-count":0,"title":["Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0086-4958","authenticated-orcid":false,"given":"Yanqi","family":"Ge","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2153-8411","authenticated-orcid":false,"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1249-2826","authenticated-orcid":false,"given":"Qingnan","family":"Fan","sequence":"additional","affiliation":[{"name":"VIVO, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2675-2023","authenticated-orcid":false,"given":"Xi","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5668-5529","authenticated-orcid":false,"given":"Ye","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Qin","sequence":"additional","affiliation":[{"name":"VIVO, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Gu","sequence":"additional","affiliation":[{"name":"VIVO, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-8594","authenticated-orcid":false,"given":"Wen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0723-4016","authenticated-orcid":false,"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref10","article-title":"Prompt-to-prompt image editing with cross-attention control","author":"Hertz","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref14","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023"},{"key":"ref15","article-title":"T2I-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","author":"Huang","year":"2023"},{"key":"ref16","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref18","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref19","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref20","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref21","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"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref24","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.","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02078"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00109"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240655"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00391"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00811"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00824"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3605548"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00457"},{"key":"ref43","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref44","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref45","article-title":"Wasserstein style transfer","author":"Mroueh","year":"2019"},{"key":"ref46","article-title":"Domain generalization with mixstyle","author":"Zhou","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/310"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2921336"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00787"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref53","first-page":"5644","article-title":"What the DAAM: Interpreting stable diffusion using cross attention","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Tang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_12"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00662"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342645"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"ref58","article-title":"Realistic-V4","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"key":"ref60","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref64","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.","author":"Schuhmann"},{"key":"ref65","article-title":"106 styles for stable diffusion XL model","year":"2023"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11373710\/11281533.pdf?arnumber=11281533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T00:33:43Z","timestamp":1770683623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11281533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3638700","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":[[2026,2]]}}}