{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:16:32Z","timestamp":1772644592160,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Technological Innovation Projects of Hubei Province","award":["2018AAA062"],"award-info":[{"award-number":["2018AAA062"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61562025"],"award-info":[{"award-number":["61562025"]}],"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":["61972298"],"award-info":[{"award-number":["61972298"]}],"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":["61962019"],"award-info":[{"award-number":["61962019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese Association for Artificial Intelligence, CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3061927","type":"journal-article","created":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T20:44:00Z","timestamp":1614977040000},"page":"3499-3512","source":"Crossref","is-referenced-by-count":39,"title":["A Novel Visual Representation on Text Using Diverse Conditional GAN for Visual Recognition"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6586-231X","authenticated-orcid":false,"given":"Tao","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1584-7290","authenticated-orcid":false,"given":"Chengjiang","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4526-6297","authenticated-orcid":false,"given":"Chunxia","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00152"},{"key":"ref38","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01272"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref30","article-title":"A hybrid attention mechanism for weakly-supervised temporal action localization","author":"islam","year":"2021","journal-title":"arXiv 2101 00545"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref36","article-title":"FTGAN: A fully-trained generative adversarial networks for text to face generation","author":"chen","year":"2019","journal-title":"arXiv 1904 05729"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00816"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00473"},{"key":"ref28","first-page":"1","article-title":"Attention-via-attention neural machine translation","author":"zhao","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref27","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.323"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_59"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.373"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.325"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.153"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.524"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0834-9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2682082"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref54","first-page":"5852","article-title":"On GANs and GMMs","author":"richardson","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref53","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref52","article-title":"Nearest neighbour radial basis function solvers for deep neural networks","author":"meyer","year":"2018","journal-title":"arXiv 1705 09780v3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref11","first-page":"42","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","author":"nam","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-0305-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126720"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.525"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984068"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1052"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"ref18","article-title":"Utilizing large scale vision and text datasets for image segmentation from referring expressions","author":"hu","year":"2016","journal-title":"arXiv 1608 08305"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2759265"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.443"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.525"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00176"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref45","article-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"wah","year":"2011"},{"key":"ref48","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"heusel","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","first-page":"24","article-title":"MGAN: Training generative adversarial nets with multiple generators","author":"hoang","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref44","article-title":"Multichannel variable-size convolution for sentence classification","author":"yin","year":"2016","journal-title":"arXiv 1603 04513"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09371392.pdf?arnumber=9371392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:09Z","timestamp":1652194209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9371392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3061927","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}