{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T06:10:50Z","timestamp":1781763050619,"version":"3.54.5"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the Peopleapos;s Republic of China","doi-asserted-by":"publisher","award":["2018AAA0102003"],"award-info":[{"award-number":["2018AAA0102003"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976040"],"award-info":[{"award-number":["61976040"]}],"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":["U19B2039"],"award-info":[{"award-number":["U19B2039"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OIA-1946231"],"award-info":[{"award-number":["OIA-1946231"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Foundation of Dalian","award":["2018J11CY010"],"award-info":[{"award-number":["2018J11CY010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3060291","type":"journal-article","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T11:35:56Z","timestamp":1613820956000},"page":"832-845","source":"Crossref","is-referenced-by-count":40,"title":["Cross-Modal Semantic Matching Generative Adversarial Networks for Text-to-Image Synthesis"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6915-8736","authenticated-orcid":false,"given":"Hongchen","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1712-6083","authenticated-orcid":false,"given":"Xiuping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-9489","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","article-title":"Generating multiple objects at spatially distinct locations","author":"tobias","year":"0","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref32","first-page":"2741","article-title":"Character-aware neural language models","author":"kim","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref31","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume":"1","author":"zhang","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref30","first-page":"2042","article-title":"Convolutional neural network architectures for matching natural language sentences","volume":"2","author":"hu","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref34","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"mikolov","year":"2013","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref28","first-page":"11380","article-title":"Sim-real joint reinforcement transfer for 3d indoor navigation","author":"fengda","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref2","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume":"48","author":"reed","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref1","first-page":"2672","article-title":"Generative adversarial nets","volume":"2","author":"goodfellow","year":"0","journal-title":"Proc Conf Neu Inf Process Syst"},{"key":"ref20","article-title":"The Caltech-UCSD Birds-200-2011 dataset","author":"wah","year":"2011","journal-title":"Comput Neural Syst"},{"key":"ref22","article-title":"Auto-Encoding variational bayes","year":"2013"},{"key":"ref21","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref24","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier gans","volume":"70","author":"odena","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref23","article-title":"Conditional generative adversarial nets","author":"mehdi","year":"2014"},{"key":"ref26","first-page":"706","article-title":"Adversarial learning with local coordinate coding","author":"cao","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref25","article-title":"Memory networks","author":"jason","year":"0","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref50","first-page":"6738","article-title":"SphereFace: Deep hypersphere embedding for face recognition","author":"weiyan","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref11","article-title":"VSE++: Improved visual-semantic embeddings with hard negatives","author":"faghri","year":"0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref15","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume":"7","author":"jonas","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1104"},{"key":"ref18","first-page":"1576","article-title":"Multi-perspective sentence similarity modeling with convolutional neural networks","author":"h","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref19","article-title":"Text understanding from scratch","author":"xiang","year":"2015"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","article-title":"StackGAN++: Realistic image synthesis with stacked generative adversarial networks","volume":"41","author":"han","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref8","first-page":"5802","article-title":"DM-GAN: Dynamic memory generative adversarial networks for text-to-image synthesis","author":"minfeng","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref49","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","author":"liu","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref46","first-page":"5769","article-title":"Improved training of wasserstein gans","author":"ishaan","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref45","article-title":"BEGAN: Boundary equilibrium generative adversarial networks","author":"david","year":"2017"},{"key":"ref48","first-page":"5077","article-title":"Stacked generative adversarial networks","author":"liqian","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.202"},{"key":"ref42","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","author":"heusel","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"2234","article-title":"Improved techniques for training GANS","author":"salimans","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref44","first-page":"42","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","author":"nam","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09359527.pdf?arnumber=9359527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T21:04:36Z","timestamp":1650920676000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9359527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3060291","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}