{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:11:28Z","timestamp":1766171488044,"version":"3.48.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1008903"],"award-info":[{"award-number":["2023YFA1008903"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Fundamental Research Project of Shandong Province of China","award":["ZR2023ZD33"],"award-info":[{"award-number":["ZR2023ZD33"]}]},{"name":"Taishan Scholar Project of Shandong Province of China","award":["tstp20240803"],"award-info":[{"award-number":["tstp20240803"]}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023LLZ012"],"award-info":[{"award-number":["ZR2023LLZ012"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Project of Shandong Provincial Key R&D Program","award":["2024RZB0204"],"award-info":[{"award-number":["2024RZB0204"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3643194","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:46:44Z","timestamp":1765478804000},"page":"210246-210256","source":"Crossref","is-referenced-by-count":0,"title":["Optimization Method for Controllable Image Style Transfer Based on DDPM Guided by Cross-Modal Text"],"prefix":"10.1109","volume":"13","author":[{"given":"Shengnan","family":"Ding","sequence":"first","affiliation":[{"name":"Institute for Financial Studies, School of Mathematics, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8784-8239","authenticated-orcid":false,"given":"Yufeng","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute for Financial Studies, School of Mathematics, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","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":"ref3","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia"},{"key":"ref4","article-title":"EDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv:2211.01324"},{"issue":"2","key":"ref5","first-page":"3192","article-title":"Cross-modal contrastive learning for text-guided image style transfer","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"37","author":"Zhang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref7","first-page":"11377","article-title":"StyTr2: Unbiased image style transfer with transformers","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Mou"},{"key":"ref8","first-page":"1123","article-title":"Pseudo-modal style transfer: Leveraging cross-modal supervision for consistent stylization","volume":"33","author":"Liu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref11","first-page":"17920","article-title":"Sinddm: A single image denoising diffusion model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kulikov"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342645"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/info15100588"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104445"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/sym17020290"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref19","article-title":"DiffStyler: Diffusion-based localized image style transfer","author":"Li","year":"2024","journal-title":"arXiv:2403.18461"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15169"},{"key":"ref22","article-title":"A training-free approach for music style transfer with latent diffusion models","author":"Kim","year":"2024","journal-title":"arXiv:2411.15913"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01440"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00490"},{"key":"ref25","article-title":"Semantix: An energy guided sampler for semantic style transfer","author":"He","year":"2025","journal-title":"arXiv:2503.22344"},{"key":"ref26","article-title":"Attention in diffusion model: A survey","author":"Hua","year":"2025","journal-title":"arXiv:2504.03738"},{"key":"ref27","article-title":"Style transfer: A decade survey","author":"Zhang","year":"2025","journal-title":"arXiv:2506.19278"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11110-3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00742"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-80508-w"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02080"},{"key":"ref33","article-title":"Diffusion-based image translation using disentangled style and content representation","author":"Kwon","year":"2022","journal-title":"arXiv:2209.15264"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref35","article-title":"Training-free content injection using h-space in diffusion models","author":"Jeong","year":"2023","journal-title":"arXiv:2303.15403"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02183"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-17899-x"},{"key":"ref38","article-title":"FreeStyle: Free lunch for text-guided style transfer using diffusion models","author":"He","year":"2024","journal-title":"arXiv:2401.15636"},{"key":"ref39","article-title":"Tuning-free adaptive style incorporation for structure-consistent text-driven style transfer","author":"Ge","year":"2024","journal-title":"arXiv:2404.06835"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11298142.pdf?arnumber=11298142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T18:59:52Z","timestamp":1766170792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3643194","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}