{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:22Z","timestamp":1777889842425,"version":"3.51.4"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["12125104,12426313,623B2084"],"award-info":[{"award-number":["12125104,12426313,623B2084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["xzy022025047"],"award-info":[{"award-number":["xzy022025047"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01625","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17496-17505","source":"Crossref","is-referenced-by-count":0,"title":["Wasserstein Style Distribution Analysis and Transform for Stylized Image Generation"],"prefix":"10.1109","author":[{"given":"Xi","family":"Yu","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Xi'an Jiaotong University,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xi'an Jiaotong University,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xi'an Jiaotong University,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xi'an Jiaotong University,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref2","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00823"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00662"},{"key":"ref8","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref11","article-title":"Image style transfer using convolutional neural networks","author":"Leon","year":"2016","journal-title":"CVPR"},{"key":"ref12","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref17","article-title":"Visual style prompting with swapping selfattention","author":"Jeong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Trainingfree style transfer emerges from h -space in diffusion models","author":"Jeong","year":"2024","journal-title":"WACV"},{"key":"ref19","article-title":"Learning multiple layers of features from tiny images","volume-title":"Master\u2019s thesis, University of Tront","author":"Krizhevsky","year":"2009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"ref22","article-title":"Learning from uncertain curves: The 2 -wasserstein metric for gaussian processes","author":"Mallasto","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01217"},{"key":"ref25","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"issue":"140","key":"ref28","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":"JMLR"},{"key":"ref29","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref32","article-title":"Rb-modulation: Training-free personalization of diffusion models using stochastic optimal control","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref34","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref35","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref37","article-title":"Styledrop: Text-to-image generation in any style","author":"Sohn","year":"2023","journal-title":"NeurIPS"},{"key":"ref38","article-title":"D2 styler: Advancing arbitrary style transfer with discrete diffusion methods","author":"Susladkar","year":"2025","journal-title":"ICPR"},{"key":"ref39","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"issue":"3","key":"ref40","first-page":"66","article-title":"Topics in optimal transportation.(books)","volume":"30","author":"Villani","year":"2003","journal-title":"OR\/MS Today"},{"key":"ref41","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02253-x"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01435"},{"key":"ref45","article-title":"Csgo: Content-style composition in text-to-image generation","author":"Xing","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref48","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28570"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446247.pdf?arnumber=11446247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:32Z","timestamp":1777612892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01625","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}