{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:15:20Z","timestamp":1774721720024,"version":"3.50.1"},"reference-count":51,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3075579","type":"journal-article","created":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T21:20:44Z","timestamp":1619472044000},"page":"64918-64928","source":"Crossref","is-referenced-by-count":60,"title":["Text to Image Synthesis for Improved Image Captioning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1212-4652","authenticated-orcid":false,"given":"Md. Zakir","family":"Hossain","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1557-4907","authenticated-orcid":false,"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[]},{"given":"Mohd Fairuz","family":"Shiratuddin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-7510","authenticated-orcid":false,"given":"Hamid","family":"Laga","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132920"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref1","volume":"783","author":"white","year":"2018","journal-title":"Neural Representations of Natural Language"},{"key":"ref20","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref24","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00862"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852118"},{"key":"ref11","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref14","first-page":"682","article-title":"On pre-trained image features and synthetic images for deep learning","author":"hinterstoisser","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref16","article-title":"Applying domain randomization to synthetic data for object category detection","author":"borrego","year":"2018","journal-title":"arXiv 1807 09834"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2200\/S00822ED1V01Y201712COV015"},{"key":"ref6","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref5","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8946003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3115432"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_13"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09416431.pdf?arnumber=9416431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:48Z","timestamp":1639770948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9416431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3075579","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}