{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:01:29Z","timestamp":1780376489076,"version":"3.54.1"},"reference-count":31,"publisher":"World Scientific Pub Co Pte Ltd","issue":"11","funder":[{"name":"Social Science Achievement Evaluation Committee projects of Hunan Province","award":["XSP25YBC020"],"award-info":[{"award-number":["XSP25YBC020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2026,9,15]]},"abstract":"<jats:p>Aiming at the challenges of deploying diffusion models on mobile devices and the subjectivity of textual style descriptions, this paper proposes an end-to-end style transfer framework based on a lightweight diffusion network and joint image-text representation. A Contrastive Language-Image Pre-training (CLIP)-based cross-modal feature extraction scheme is designed to decouple style semantics and detail features from reference images, overcoming the ambiguity of pure text prompts. To enable real-time inference, a diffusion Generative Adversarial Network (GAN) hybrid architecture (UFOGen) is introduced to achieve single-step generation, replacing inefficient multi-step denoising. Furthermore, a lightweight network (FasterVAE, Faster Variational Autoencoder) is developed using separated convolution, transformer layers, key-value projection sharing, and Swish activation, significantly reducing parameters and computational cost. On a Xiaomi 14 Pro mobile device, the framework generates a [Formula: see text] stylized image in 1.45[Formula: see text]s. Experiments show that our method outperforms state-of-the-art approaches in SSIM, PSNR, and style loss. User studies also confirm its advantages in style accuracy, detail preservation, and color naturalness. This work provides a practical solution for real-time style transfer on resource-constrained platforms, advancing the deployment of diffusion models on mobile devices.<\/jats:p>","DOI":"10.1142\/s0218001426590226","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:50:03Z","timestamp":1777017003000},"source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Diffusion Network for Real-Time Style Transfer on Mobile Devices with Joint Image-Text Interaction"],"prefix":"10.1142","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9714-9904","authenticated-orcid":false,"given":"Fang","family":"Wang","sequence":"first","affiliation":[{"name":"Xiangnan University, Chenzhou, Hunan Province, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4057-5197","authenticated-orcid":false,"given":"Zhengdong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xiangnan University, Chenzhou, Hunan Province, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7046-8143","authenticated-orcid":false,"given":"Jingyi","family":"Deng","sequence":"additional","affiliation":[{"name":"Xiangnan University, Chenzhou, Hunan Province, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1866-2115","authenticated-orcid":false,"given":"Junting","family":"Liao","sequence":"additional","affiliation":[{"name":"Xiangnan University, Chenzhou, Hunan Province, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"219","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"S0218001426590226BIB001","doi-asserted-by":"publisher","DOI":"10.1145\/3635636.3664268"},{"key":"S0218001426590226BIB002","doi-asserted-by":"publisher","DOI":"10.3390\/app15052274"},{"key":"S0218001426590226BIB003","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2023.108723"},{"key":"S0218001426590226BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"S0218001426590226BIB005","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e16757"},{"key":"S0218001426590226BIB006","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00018-1"},{"key":"S0218001426590226BIB007","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"S0218001426590226BIB008","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00576"},{"key":"S0218001426590226BIB009","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-98545-4"},{"key":"S0218001426590226BIB010","doi-asserted-by":"crossref","unstructured":"S. Li\n                      et al.\n                      , Efficiency meets fidelity: A novel quantization framework for stable diffusion, preprint (2024), arXiv:2412.06661.","DOI":"10.32388\/5B8TBL"},{"key":"S0218001426590226BIB011","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2023.07.027"},{"key":"S0218001426590226BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3569700"},{"key":"S0218001426590226BIB013","unstructured":"R. Pi\n                      et al.\n                      , Image textualization: An automatic framework for creating accurate and detailed image descriptions, preprint (2024), arXiv:2406.07502."},{"key":"S0218001426590226BIB014","doi-asserted-by":"publisher","DOI":"10.15408\/jti.v17i1.37942"},{"key":"S0218001426590226BIB015","first-page":"71","volume-title":"Proc. Int. Conf. Innovations and Advances in Cognitive Systems","author":"Rayvanth N.","year":"2025"},{"key":"S0218001426590226BIB016","unstructured":"H. Shen\n                      et al.\n                      , Efficient diffusion models: A survey, preprint (2025), arXiv:2502.06805."},{"key":"S0218001426590226BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00356"},{"key":"S0218001426590226BIB018","first-page":"143","volume-title":"Proc. European Conf. Computer Vision (ECCV)","author":"Somepalli G.","year":"2024"},{"key":"S0218001426590226BIB019","unstructured":"L. Sun\n                      et al.\n                      , Improving the stability and efficiency of diffusion models for content consistent super-resolution, preprint (2023), arXiv:2401.00877."},{"key":"S0218001426590226BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00715"},{"key":"S0218001426590226BIB021","doi-asserted-by":"publisher","DOI":"10.1177\/01655515221107334"},{"key":"S0218001426590226BIB022","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592262"},{"key":"S0218001426590226BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01435"},{"key":"S0218001426590226BIB024","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"S0218001426590226BIB025","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"S0218001426590226BIB026","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00679"},{"key":"S0218001426590226BIB027","unstructured":"S. Zampini\n                      et al.\n                      , Training-free constrained generation with stable diffusion models, preprint (2025), arXiv:2502.05625."},{"key":"S0218001426590226BIB028","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126623500627"},{"key":"S0218001426590226BIB029","doi-asserted-by":"publisher","DOI":"10.1080\/0305215X.2021.2013479"},{"key":"S0218001426590226BIB030","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530736"},{"key":"S0218001426590226BIB031","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001426590226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:00:43Z","timestamp":1780372843000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001426590226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":31,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,9,15]]}},"alternative-id":["10.1142\/S0218001426590226"],"URL":"https:\/\/doi.org\/10.1142\/s0218001426590226","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"article-number":"2659022"}}