{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:24:54Z","timestamp":1785212694592,"version":"3.55.0"},"reference-count":56,"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"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key Research and Development Program of China Stem Cell and Translational Research","doi-asserted-by":"publisher","award":["2018YFB0505401"],"award-info":[{"award-number":["2018YFB0505401"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41771452"],"award-info":[{"award-number":["41771452"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013251","name":"Institute of Remote Sensing and Digital Earth","doi-asserted-by":"publisher","award":["Y5SJ1500CX"],"award-info":[{"award-number":["Y5SJ1500CX"]}],"id":[{"id":"10.13039\/501100013251","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/jstars.2021.3070872","type":"journal-article","created":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T20:53:41Z","timestamp":1617656021000},"page":"4284-4297","source":"Crossref","is-referenced-by-count":142,"title":["A Deep Semantic Alignment Network for the Cross-Modal Image-Text Retrieval in Remote Sensing"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6713-7544","authenticated-orcid":false,"given":"Qimin","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2592-7120","authenticated-orcid":false,"given":"Yuzhuo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1568-1518","authenticated-orcid":false,"given":"Peng","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref33","first-page":"12655","article-title":"IMRAM: Iterative matching with recurrent attention memory for cross-modal image-text retrieval","author":"chen","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref37","article-title":"Multiple object recognition with visual attention","author":"ba","year":"0","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref36","first-page":"1","article-title":"Recurrent models of visual attention","volume":"3","author":"mnih","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"VSE: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"0","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref34","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc 31st Int Conf Mach Learn (ICML)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2949220"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3013818"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2018.2832985"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","first-page":"1618","article-title":"Pairwise relationship guided deep hashing for cross-modal retrieval","author":"yang","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2916838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref23","first-page":"1","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"964","DOI":"10.3390\/rs10060964","article-title":"Performance evaluation of single-label and multi-label remote sensing image retrieval using a dense labeling dataset","volume":"10","author":"shao","year":"2018","journal-title":"Remote Sens"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref52","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.02.006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PRRS.2018.8486338"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2979273"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325045"},{"key":"ref15","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"Comput Sci"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539928"},{"key":"ref17","first-page":"1360","article-title":"Learning hash functions for cross-view similarity search","author":"kumar","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291290"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2756911"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3021390"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2961634"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900431"},{"key":"ref8","article-title":"Grounded compositional semantics for finding and describing images with sentences","author":"socher","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref9","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume":"3","author":"karpathy","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref42","first-page":"887","article-title":"Gradient descent: Second order momentum and saturating error","volume":"4","author":"pearlmutter","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"19","article-title":"Online learning for matrix factorization and sparse coding","volume":"11","author":"mairal","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref43","first-page":"1","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4609443\/9314330\/09395191.pdf?arnumber=9395191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:21Z","timestamp":1639770981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9395191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/jstars.2021.3070872","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}