{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:51:16Z","timestamp":1776441076920,"version":"3.51.2"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/fg52635.2021.9666791","type":"proceedings-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T05:34:23Z","timestamp":1643175263000},"page":"01-08","source":"Crossref","is-referenced-by-count":10,"title":["Generative Adversarial Network for Text-to-Face Synthesis and Manipulation with Pretrained BERT Model"],"prefix":"10.1109","author":[{"given":"Yutong","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Nobutaka","family":"Shimada","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref33","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref32","article-title":"Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis","author":"tao","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101169"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451236"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00342"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01480"},{"key":"ref40","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref15","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00538"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"ref27","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.07.019"},{"key":"ref7","article-title":"Cogview: Mastering text-to-image generation via transformers","author":"ding","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1345"},{"key":"ref9","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481026"},{"key":"ref20","article-title":"Investigating the effectiveness of representations based on pretrained transformer-based language models in active learning for labelling text datasets","author":"lu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2019.00-42"},{"key":"ref21","article-title":"Text-adaptive generative adversarial networks: manipulating images with natural language","author":"nam","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2930512"},{"key":"ref24","first-page":"2085","article-title":"Styleclip: Text-driven manipulation of stylegan imagery","author":"patashnik","year":"0","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref26","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/744"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"}],"event":{"name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","location":"Jodhpur, India","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9666787\/9666788\/09666791.pdf?arnumber=9666791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:28Z","timestamp":1652201728000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9666791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/fg52635.2021.9666791","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}