{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T10:07:35Z","timestamp":1784196455589,"version":"3.55.0"},"reference-count":52,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62566040"],"award-info":[{"award-number":["62566040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106090"],"award-info":[{"award-number":["62106090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106093"],"award-info":[{"award-number":["62106093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20232BAB212027"],"award-info":[{"award-number":["20232BAB212027"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20242BAB23013"],"award-info":[{"award-number":["20242BAB23013"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20252BAC200194"],"award-info":[{"award-number":["20252BAC200194"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Text\u2010driven face editing has attracted widespread interest due to its intuitive control and user\u2010friendly interaction. However, current state\u2010of\u2010the\u2010art (SOTA) methods face two main challenges: (1) they utilize unfinetuned general image\u2010text encoders for modality fusion, making it difficult to comprehend domain\u2010specific knowledge in facial attribute editing (dozens of fine\u2010grained facial attributes such as moustache and lipsticks); (2) they roughly optimize all attributes simultaneously using a cross\u2010entropy loss, leading to severe mutual interference among attributes. To this end, we propose Disentangled Multimodal Visual Adaptation for CLIP (DMV\u2010CLIP). First, DMV\u2010CLIP incorporates learnable context tokens to inject facial domain knowledge into the CLIP model via multimodal prompt learning (MPL). Second, it employs directional contrastive learning (DCL) to disentangle facial attributes and enable precise editing. Finally, DMV\u2010CLIP utilizes a vision\u2010language consistency model (VLCM) to maintain identity consistency while ensuring that the generated images strictly adhere to the semantic instructions.<\/jats:p>","DOI":"10.1111\/exsy.70345","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T11:23:03Z","timestamp":1782732183000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>DMV<\/scp>\n                    \u2010\n                    <scp>CLIP<\/scp>\n                    : Disentangled Multimodal Visual Adaptation for Text\u2010Driven Face Editing"],"prefix":"10.1111","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7698-6085","authenticated-orcid":false,"given":"Minghao","family":"Li","sequence":"first","affiliation":[{"name":"School of Software Nanchang University  Nanchang Jiangxi China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3464-5104","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Nanchang University  Nanchang Jiangxi China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0976-3381","authenticated-orcid":false,"given":"Xin","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Software Nanchang University  Nanchang Jiangxi China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence Jiangxi Normal University  Nanchang Jiangxi China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoruo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering Nanyang Technological University  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhui","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Software Nanchang University  Nanchang Jiangxi China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276390"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610287"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1227983"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2023.3247433"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310097"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70160"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"e_1_2_9_9_1","doi-asserted-by":"crossref","unstructured":"Dalva Y. K.Venkatesh andP.Yanardag.2025.\u201cFluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 232\u2013250.","DOI":"10.1109\/CVPR52734.2025.01221"},{"key":"e_1_2_9_10_1","doi-asserted-by":"crossref","unstructured":"Deng J. J.Guo N.Xue andS.Zafeiriou.2019.\u201cArcFace: Additive Angular Margin Loss for Deep Face Recognition.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 4690\u20134699.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_2_9_11_1","unstructured":"Deng Y. X.He C.Mei P.Wang andF.Tang.2025.\u201cFireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing.\u201dInProceedings of the International Conference on Machine Learning 13110\u201313128."},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70040"},{"key":"e_1_2_9_13_1","unstructured":"Goodfellow I. J. J.Pouget\u2010Abadie M.Mirza et\u00a0al.2014.\u201cGenerative Adversarial Nets.\u201dInProceedings of the Advances in Neural Information Processing Systems 2672\u20132680."},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3460180"},{"key":"e_1_2_9_15_1","unstructured":"Heusel M. H.Ramsauer T.Unterthiner B.Nessler andS.Hochreiter.2017.\u201cGANs Trained by a Two Time\u2010Scale Update Rule Converge to a Local Nash Equilibrium.\u201dInProceedings of the Advances in Neural Information Processing Systems Vol. 30 6629\u20136640."},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3347299"},{"key":"e_1_2_9_17_1","unstructured":"Karras T. T.Aila S.Laine andJ.Lehtinen.2018.\u201cProgressive Growing of GANs for Improved Quality Stability and Variation.\u201dInProceedings of the International Conference on Learning Representations 213\u2013238."},{"key":"e_1_2_9_18_1","unstructured":"Karras T. M.Aittala S.Laine et\u00a0al.2021.\u201cAlias\u2010Free Generative Adversarial Networks.\u201dInProceedings of the Advances in Neural Information Processing Systems 852\u2013863."},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"Karras T. S.Laine andT.Aila.2019.\u201cA Style\u2010Based Generator Architecture for Generative Adversarial Networks.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 4401\u20134410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_9_20_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.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 8110\u20138119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_2_9_21_1","unstructured":"Kinga D. andJ. B.Adam.2015.\u201cA Method for Stochastic Optimization.\u201dInProceedings of the International Conference on Learning Representations 801\u2013808."},{"key":"e_1_2_9_22_1","first-page":"124","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Kumar A.","year":"2024"},{"key":"e_1_2_9_23_1","doi-asserted-by":"crossref","unstructured":"Lee C. H. Z.Liu L.Wu andP.Luo.2020.\u201cMaskGAN: Towards Diverse and Interactive Facial Image Manipulation.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 5549\u20135558.","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3400861"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70165"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083484"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"Liu Z. P.Luo X.Wang andX.Tang.2015.\u201cDeep Learning Face Attributes in the Wild.\u201dInProceedings of the IEEE\/CVF International Conference on Computer Vision 3730\u20133738.","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01178-0"},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"Patashnik O. Z.Wu E.Shechtman D.Cohen\u2010Or andD.Lischinski.2021.\u201cStyleCLIP: Text\u2010Driven Manipulation of StyleGAN Imagery.\u201dInProceedings of the IEEE\/CVF International Conference on Computer Vision 2085\u20132094.","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882269"},{"key":"e_1_2_9_31_1","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford A.","year":"2021"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"e_1_2_9_33_1","unstructured":"Rout L. Y.Chen N.Ruiz C.Caramanis S.Shakkottai andW. S.Chu.2025.\u201cSemantic Image Inversion and Editing Using Rectified Stochastic Differential Equations.\u201dInProceedings of the International Conference on Learning Representations 43074\u201343099."},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70020"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141920"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70009"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"Szegedy C. V.Vanhoucke S.Ioffe J.Shlens andZ.Wojna.2016.\u201cRethinking the Inception Architecture for Computer Vision.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298721"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649889"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02088-6"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3140306"},{"key":"e_1_2_9_44_1","doi-asserted-by":"crossref","unstructured":"Xia W. Y.Yang J. H.Xue andB.Wu.2021.\u201cTediGAN: Text\u2010Guided Diverse Face Image Generation and Manipulation.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2256\u20132265.","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"e_1_2_9_45_1","unstructured":"Yoon S. H. M.Li G.Beaudouin C.Wen M. R.Azhar andM.Wang.2025.\u201cSplitFlow: Flow Decomposition for Inversion\u2010Free Text\u2010to\u2010Image Editing.\u201dInProceedings of the Advances in Neural Information Processing Systems 6905\u20136925."},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"e_1_2_9_47_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.\u201dInProceedings of the European Conference on Computer Vision 325\u2013341.","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"issue":"10","key":"e_1_2_9_49_1","article-title":"Dynamic Dual Consistency Distillation for Imbalanced Facial Attribute Editing","volume":"332","author":"Zhang F.","year":"2025","journal-title":"Knowledge\u2010Based Systems"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.70190"},{"key":"e_1_2_9_51_1","doi-asserted-by":"crossref","unstructured":"Zhou K. J.Yang C. C.Loy andZ.Liu.2022a.\u201cConditional Prompt Learning for Vision\u2010Language Models.\u201dInProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 16816\u201316825.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_2_9_53_1","first-page":"592","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Zhu J.","year":"2020"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70345","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70345","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T09:34:26Z","timestamp":1784194466000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70345"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":52,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1111\/exsy.70345"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70345","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"2026-04-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70345"}}