{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:19:07Z","timestamp":1780355947856,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41701508"],"award-info":[{"award-number":["41701508"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2942154","type":"journal-article","created":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T20:00:27Z","timestamp":1568836827000},"page":"137355-137364","source":"Crossref","is-referenced-by-count":50,"title":["VAA: Visual Aligning Attention Model for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2383-7738","authenticated-orcid":false,"given":"Zhengyuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhui","family":"Diao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menglong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref32","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2015","journal-title":"arXiv 1412 6632"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref36","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref34","article-title":"Learning a recurrent visual representation for image caption generation","author":"chen","year":"2014","journal-title":"arXiv 1411 5654"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922438"},{"key":"ref13","first-page":"1990","article-title":"Learning to segment object candidates","author":"pinheiro","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref18","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2627801"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"ref29","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"arXiv 1409 1556"},{"key":"ref9","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"141","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref22","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.298"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref44","first-page":"4133","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0840-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_35"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08843891.pdf?arnumber=8843891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:40:44Z","timestamp":1628624444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8843891\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2942154","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}