{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:50:57Z","timestamp":1783489857052,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91959108"],"award-info":[{"award-number":["91959108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2020A1515111199"],"award-info":[{"award-number":["2020A1515111199"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3160360","type":"journal-article","created":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T20:04:00Z","timestamp":1647547440000},"page":"3409-3419","source":"Crossref","is-referenced-by-count":24,"title":["TextFace: Text-to-Style Mapping Based Face Generation and Manipulation"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8728-2842","authenticated-orcid":false,"given":"Xianxu","family":"Hou","sequence":"first","affiliation":[{"name":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4130-3078","authenticated-orcid":false,"given":"Xiaokang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudong","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1420-0815","authenticated-orcid":false,"given":"Linlin","family":"Shen","sequence":"additional","affiliation":[{"name":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref15","first-page":"887","article-title":"Learn, imagine and create: Text-to-image generation from prior knowledge","volume":"32","author":"qiao","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref59","article-title":"Conditional image generation and manipulation for user-specified content","author":"stap","year":"2020","journal-title":"IEEE\/CVF Conf Comput Vis Pattern Recognit"},{"key":"ref14","first-page":"2065","article-title":"Controllable text-to-image generation","volume":"32","author":"li","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00618"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.10.017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481026"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref45","article-title":"Blended diffusion for text-driven editing of natural images","author":"avrahami","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref44","first-page":"22020","article-title":"Lightweight generative adversarial networks for text-guided image manipulation","volume":"33","author":"li","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00342"},{"key":"ref49","article-title":"Towards open-world text-guided face image generation and manipulation","author":"xia","year":"2021","journal-title":"arXiv 2104 08910"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951463"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref4","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","first-page":"217","article-title":"Learning what and where to draw","volume":"29","author":"reed","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref5","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413505"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref34","article-title":"Invertible conditional GANs for image editing","author":"perarnau","year":"2016"},{"key":"ref37","first-page":"592","article-title":"In-domain GAN inversion for real image editing","author":"zhu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref36","article-title":"Collaborative learning for faster styleGAN embedding","author":"guan","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875194"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref1","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref39","first-page":"42","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","volume":"31","author":"nam","year":"0","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref24","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref23","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"karras","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref67","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref20","article-title":"SegAttnGAN: Text to image generation with segmentation attention","author":"gou","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00152"},{"key":"ref63","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"heusel","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"DF-GAN: Deep fusion generative adversarial networks for text-to-image synthesis","author":"tao","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3447648"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00782"},{"key":"ref29","first-page":"9841","article-title":"GANSpace: Discovering interpretable GAN controls","volume":"33","author":"h\u00e4rk\u00f6nen","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref62","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref61","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09737433.pdf?arnumber=9737433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:01:52Z","timestamp":1693245712000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9737433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3160360","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}