{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:55:34Z","timestamp":1780318534853,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Innovative Research Program of the International Research Center of Big Data for Sustainable Development Goals","award":["CBAS2022IRP04"],"award-info":[{"award-number":["CBAS2022IRP04"]}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences (CAS) World Academy of Sciences (TWAS) Centre of Excellence on Space Technology for Disaster Mitigation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tgrs.2023.3312479","type":"journal-article","created":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T17:28:31Z","timestamp":1694021311000},"page":"1-12","source":"Crossref","is-referenced-by-count":27,"title":["Multistep Question-Driven Visual Question Answering for Remote Sensing"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9621-4879","authenticated-orcid":false,"given":"Meimei","family":"Zhang","sequence":"first","affiliation":[{"name":"International Research Center of Big Data for Sustainable Development Goals, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-2584","authenticated-orcid":false,"given":"Fang","family":"Chen","sequence":"additional","affiliation":[{"name":"International Research Center of Big Data for Sustainable Development Goals, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"International Research Center of Big Data for Sustainable Development Goals, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Show, ask, attend, and answer: A strong baseline for visual question answering","author":"kazemi","year":"2017","journal-title":"arXiv 1704 03162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00437"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3599-y"},{"key":"ref11","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.538"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.08.001"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.02.031"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"ref48","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"arXiv 1606 00061"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref42","article-title":"MultiModalQA: Complex question answering over text, tables and images","author":"talmor","year":"2021","journal-title":"arXiv 2104 06039"},{"key":"ref41","first-page":"20346","article-title":"Human-adversarial visual question answering","volume":"34","author":"sheng","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.agsy.2018.10.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9821275"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113560"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.geomorph.2016.07.032"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3173811"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref37","article-title":"How to find a good image-text embedding for remote sensing visual question answering?","author":"chappuis","year":"2021","journal-title":"arXiv 2109 11848"},{"key":"ref36","article-title":"Change detection meets visual question answering","author":"yuan","year":"2021","journal-title":"arXiv 2112 06343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00592"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00048"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090981"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/S1471068422000229"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/rs12152460"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF03326080"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref23","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"arXiv 1805 07932"},{"key":"ref26","article-title":"LRTA: A transparent neural-symbolic reasoning framework with modular supervision for visual question answering","author":"liang","year":"2020","journal-title":"arXiv 2011 10731"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref20","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","volume":"2","author":"gao","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_14"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_26"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/10242124.pdf?arnumber=10242124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T18:58:22Z","timestamp":1696877902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10242124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2023.3312479","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}