{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T14:57:27Z","timestamp":1772981847655,"version":"3.50.1"},"reference-count":30,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC 114\u20102221\u2010E\u2010197\u2010005\u2010MY3"],"award-info":[{"award-number":["NSTC 114\u20102221\u2010E\u2010197\u2010005\u2010MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>In recent years, with the rapid advancement of information and communications technology, consumer demands in the beauty and fashion industry have become increasingly diverse and personalised. To address real\u2010world application challenges, makeup transfer models must be capable of adapting to variations in head poses to ensure accurate makeup transfer across different angles and poses. In response to these challenges, we propose a new progressive makeup transfer model based on spatial style features and feature maps, termed progressive makeup transfer based on style features and feature maps (PMT\u2010SM). The PMT\u2010SM model is built upon a vision transformer (ViT) backbone and integrates several key components: feature pyramid network (FPN), makeup feature localiser (MFL), makeup style extractor (MSE) and progressive makeup generator (PMGen). This framework is designed to effectively handle large variations in head poses while ensuring precise and adaptable makeup transfer for real\u2010world applications. According to the experimental results, PMT\u2010SM model achieves scores of 0.94, 0.95 and 7.93 in ArcFace similarity, structural similarity index (SSIM) and Fr\u00e9chet inception distance (FID), respectively, demonstrating superior ability to preserve identity and background information compared with existing makeup transfer models. In addition, the images generated by the proposed model achieve a best\u2010selected ratio (BSR) of 25.00%, indicating that the PMT\u2010SM model provides significant advantages in terms of visual quality and naturalness over other makeup transfer methods in the user study.<\/jats:p>","DOI":"10.1111\/exsy.70197","type":"journal-article","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T07:16:49Z","timestamp":1767770209000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Generative Adversarial Network Based on Spatial Style for Makeup Transfer"],"prefix":"10.1111","volume":"43","author":[{"given":"Liang\u2010Ying","family":"Ke","sequence":"first","affiliation":[{"name":"Department of Engineering Science National Cheng Kung University  Tainan Taiwan"}]},{"given":"Zih\u2010Ching","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center  Santa Clara California USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2665-0821","authenticated-orcid":false,"given":"Chih\u2010Hsien","family":"Hsia","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering National Ilan University  Yilan Taiwan"},{"name":"Office of Research and Industry\u2010Academia Development Chaoyang University of Technology  Taichung Taiwan"}]}],"member":"311","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3579407"},{"key":"e_1_2_10_3_1","doi-asserted-by":"crossref","unstructured":"Deng H. C.Han H.Cai G.Han andS.He.2021.\u201cSpatially\u2010Invariant Style\u2010Codes Controlled Makeup Transfer.\u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition 6549\u20136557.","DOI":"10.1109\/CVPR46437.2021.00648"},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","unstructured":"Deng J. J.Guo N.Xue andS.Zafeiriou.2019.\u201cArcFace: Additive Angular Margin Loss for Deep Face Recognition.\u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 4690\u20134699.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_2_10_5_1","unstructured":"Goodfellow J. J.Pouget\u2010Abadie M.Mirza et\u00a0al.2014.\u201cGenerative Adversarial Networks.\u201dpreprint arXiv 1406.2661."},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","unstructured":"Gu Q. G.Wang M. T.Chiu Y.\u2010W.Tai andC.\u2010K.Tang.2019.\u201cLADN: Local Adversarial Disentangling Network for Facial Makeup and de\u2010Makeup.\u201dIEEE\/CVF International Conference on Computer Vision 10481\u201310490.","DOI":"10.1109\/ICCV.2019.01058"},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","unstructured":"Huang X. andS.Belongie.2017.\u201cArbitrary Style Transfer in Real\u2010Time With Adaptive Instance Normalization.\u201dIEEE International Conference on Computer Vision 1501\u20131510.","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"Jiang W. S.Liu C.Gao et\u00a0al.2020.\u201cPSGAN: Pose and Expression Robust Spatial\u2010Aware GAN for Customizable Makeup Transfer.\u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition 5194\u20135202.","DOI":"10.1109\/CVPR42600.2020.00524"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"Johnson J. A.Alahi andF.\u2010F.Li.2016.\u201cPerceptual Losses for Real\u2010Time Style Transfer and Super\u2010Resolution.\u201dEuropean Conference on Computer Vision 694\u2013711.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","unstructured":"Karras T. S.Laine M.Aittala J.Hellsten J.Lehtinen andT.Aila.2020.\u201cAnalyzing and Improving the Image Quality of StyleGAN.\u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition 8110\u20138119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"Ke L.\u2010Y. C.\u2010C.Hsiao andC.\u2010H.Hsia.2024.\u201cProgressive Latent Fusion Mapper for Hairstyle Transfer.\u201dIET International Conference on Engineering Technologies and Applications 63\u201364.","DOI":"10.1049\/icp.2024.4167"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"Ke L.\u2010Y. W.\u2010L.Lan H.\u2010Y.Lin andC.\u2010H.Hsia.2023.\u201cSpatial\u2010Based Generative Adversarial Network for Makeup Transfer.\u201dIET International Conference on Engineering Technologies and Applications 148\u2013149.","DOI":"10.1049\/icp.2023.3249"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312790"},{"key":"e_1_2_10_14_1","doi-asserted-by":"crossref","unstructured":"Li T. R.Qian C.Dong et\u00a0al.2018.\u201cBeautyGAN: Instance\u2010Level Facial Makeup Transfer With Deep Generative Adversarial Network.\u201dACM International Conference on Multimedia 645\u2013653.","DOI":"10.1145\/3240508.3240618"},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","unstructured":"Lin T.\u2010Y. P.Dollar R.Girshick K.He B.Hariharan andS.Belongie.2017.\u201cFeature Pyramid Networks for Object Detection.\u201dIEEE Conference on Computer Vision and Pattern Recognition 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083484"},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","unstructured":"Rombach R. A.Blattmann D.Lorenz P.Esser andB.Ommer.2022.\u201cHigh\u2010Resolution Image Synthesis With Latent Diffusion Models.\u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","unstructured":"Ruan B.\u2010K. andH.\u2010H.Shuai.2025.\u201cMAD: Makeup All\u2010In\u2010One With Cross\u2010Domain Diffusion Model \u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops 749\u2013758.","DOI":"10.1109\/CVPRW67362.2025.00079"},{"key":"e_1_2_10_19_1","unstructured":"Sarfraz M. S. C.Seibold H.Khalid andR.Stiefelhagen.2019.\u201cContent and Colour Distillation for Learning Image Translations With the Spatial Profile Loss.\u201dpreprint arXiv 1908.00274."},{"key":"e_1_2_10_20_1","doi-asserted-by":"crossref","unstructured":"Sun Z. Y.Chen andS.Xiong.2022.\u201cSSAT: A Symmetric Semantic\u2010Aware Transformer Network for Makeup Transfer and Removal.\u201dAAAI Conference on Artificial Intelligence 36 2 2325\u20132334.","DOI":"10.1609\/aaai.v36i2.20131"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3332065"},{"key":"e_1_2_10_22_1","doi-asserted-by":"crossref","unstructured":"Sun Z. S.Xiong Y.Chen andY.Rong.2024.\u201cContent\u2010Style Decoupling for Unsupervised Makeup Transfer Without Generating Pseudo Ground Truth.\u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition 7601\u20137610.","DOI":"10.1109\/CVPR52733.2024.00726"},{"key":"e_1_2_10_23_1","first-page":"5998","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"Wan Z. H.Chen J.An W.Jiang C.Yao andJ.Luo.2022.\u201cFacial Attribute Transformers for Precise and Robust Makeup Transfer.\u201dIEEE\/CVF Winter Conference on Applications of Computer Vision 1717\u20131726.","DOI":"10.1109\/WACV51458.2022.00317"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2025.3598867"},{"key":"e_1_2_10_26_1","doi-asserted-by":"crossref","unstructured":"Yan Q. C.Guo J.Zhao Y.Dai C. C.Loy andC.Li.2023.\u201cBeautyREC: Robust Efficient and Component\u2010Specific Makeup Transfer.\u201dIEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops 1102\u20131110.","DOI":"10.1109\/CVPRW59228.2023.00117"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"Yang C. W.He Y.Xu andY.Gao.2022.\u201cEleGANt: Exquisite and Locally Editable GAN for Makeup Transfer.\u201dEuropean Conference on Computer Vision 737\u2013754.","DOI":"10.1007\/978-3-031-19787-1_42"},{"key":"e_1_2_10_28_1","doi-asserted-by":"crossref","unstructured":"Yu C. J.Wang C.Peng C.Gao G.Yu andN.Sang.2018.\u201cBiSeNet: Bilateral Segmentation Network for Real\u2010Time Semantic Segmentation.\u201dEuropean Conference on Computer Vision 325\u2013341.","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","unstructured":"Zhang Y. Y.Yuan Y.Song andJ.Liu.2025.\u201cStable\u2010Makeup: When Real\u2010World Makeup Transfer Meets Diffusion Model.\u201dSpecial Interest Group on Computer Graphics and Interactive Techniques Conference 1\u20139.","DOI":"10.1145\/3721238.3730702"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"Zhao H. J.Shi X.Qi X.Wang andJ.Jia.2017.\u201cPyramid Scene Parsing Network.\u201dIEEE Conference on Computer Vision and Pattern Recognition 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"Zhu J.\u2010Y. T.Park P.Isola andA. A.Efros.2017.\u201cUnpaired Image\u2010To\u2010Image Translation Using Cycle\u2010Consistent Adversarial Networks.\u201dIEEE International Conference on Computer Vision 2223\u20132232.","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70197","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70197","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T08:31:30Z","timestamp":1772958690000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70197"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1111\/exsy.70197"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70197","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]},"assertion":[{"value":"2025-10-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70197"}}