{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:52:59Z","timestamp":1780318379116,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004745","name":"Research Center of College of Computer and Information Sciences, Deanship of Scientific Research, King Saud University, Riyadh, Saudi Arabia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004745","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tgrs.2022.3192460","type":"journal-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T19:25:35Z","timestamp":1658258735000},"page":"1-11","source":"Crossref","is-referenced-by-count":73,"title":["Bi-Modal Transformer-Based Approach for Visual Question Answering in Remote Sensing Imagery"],"prefix":"10.1109","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9287-0596","authenticated-orcid":false,"given":"Yakoub","family":"Bazi","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4467-650X","authenticated-orcid":false,"given":"Mohamad Mahmoud Al","family":"Rahhal","sequence":"additional","affiliation":[{"name":"Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed Lamine","family":"Mekhalfi","sequence":"additional","affiliation":[{"name":"Digital Industry Center, Fondazione Bruno Kessler, Technologies of Vision, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2490-5739","authenticated-orcid":false,"given":"Mansour Abdulaziz Al","family":"Zuair","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9745-3732","authenticated-orcid":false,"given":"Farid","family":"Melgani","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2018.2819694"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2020.102065"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2019.2953119"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2019.2951636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2020.2980933"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2020.3044054"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2020.3009243"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/app10248931"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref13","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.499"},{"key":"ref16","first-page":"1","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3097180"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2020.2988782"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3079918"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/igarss47720.2021.9553307"},{"key":"ref23","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app11093974"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/rs13030516"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/rs13030498"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3095166"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2021.3085139"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09294-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref31","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref32","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref33","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref34","volume-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/9633014\/09832935.pdf?arnumber=9832935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:31:42Z","timestamp":1706769102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9832935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2022.3192460","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}