{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:32:25Z","timestamp":1770226345824,"version":"3.49.0"},"reference-count":48,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071361"],"award-info":[{"award-number":["62071361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2017YFE0104100"],"award-info":[{"award-number":["2017YFE0104100"]}]},{"name":"China Research Project","award":["6141B07270429"],"award-info":[{"award-number":["6141B07270429"]}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FL-170100117"],"award-info":[{"award-number":["FL-170100117"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP-180103424"],"award-info":[{"award-number":["DP-180103424"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3055062","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T06:15:09Z","timestamp":1612332909000},"page":"2798-2809","source":"Crossref","is-referenced-by-count":55,"title":["Multi-Sentence Auxiliary Adversarial Networks for Fine-Grained Text-to-Image Synthesis"],"prefix":"10.1109","volume":"30","author":[{"given":"Yanhua","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5535-0898","authenticated-orcid":false,"given":"De","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3247","authenticated-orcid":false,"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"ref32","first-page":"286","article-title":"Image super-resolution using very deep residual channel attention networks","author":"zhang","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865280"},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref37","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878956"},{"key":"ref10","first-page":"2065","article-title":"Controllable text-to-image generation","author":"li","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref13","article-title":"The Caltech-UCSD birds-200–2011 dataset","author":"wah","year":"2011","journal-title":"Proc CVPR Workshop Fine-Grained Vis Categorization"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1378\/chest.124.5.1694"},{"key":"ref16","article-title":"Generating images from captions with attention","author":"mansimov","year":"2015","journal-title":"arXiv 1511 02793"},{"key":"ref17","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"oord","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107384"},{"key":"ref28","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref27","first-page":"805","article-title":"Multi-attention multi-class constraint for fine-grained image recognition","author":"sun","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951463"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953753"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01060"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref1","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018312"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01305-2"},{"key":"ref45","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref22","article-title":"TAC-GAN–text conditioned auxiliary classifier generative adversarial network","author":"dash","year":"2017","journal-title":"arXiv 1703 06412"},{"key":"ref47","first-page":"885","article-title":"Learn, imagine and create: Text-to-image generation from prior knowledge","author":"qiao","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref21","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"key":"ref42","first-page":"2226","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013272"},{"key":"ref41","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref23","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","author":"odena","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref44","first-page":"6626","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":"ref26","article-title":"Weighted transformer network for machine translation","author":"ahmed","year":"2017","journal-title":"arXiv 1711 02132"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09345477.pdf?arnumber=9345477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:08Z","timestamp":1652194268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9345477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3055062","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}