{"id":"https://openalex.org/W4285818301","doi":"https://doi.org/10.1109/tgrs.2022.3192460","title":"Bi-Modal Transformer-Based Approach for Visual Question Answering in Remote Sensing Imagery","display_name":"Bi-Modal Transformer-Based Approach for Visual Question Answering in Remote Sensing Imagery","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285818301","doi":"https://doi.org/10.1109/tgrs.2022.3192460"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2022.3192460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2022.3192460","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054237841","display_name":"Yakoub Bazi","orcid":"https://orcid.org/0000-0001-9287-0596"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Yakoub Bazi","raw_affiliation_strings":["Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9287-0596","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mohamad Mahmoud Al Rahhal","orcid":"https://orcid.org/0000-0002-4467-650X"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohamad Mahmoud Al Rahhal","raw_affiliation_strings":["Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4467-650X","affiliations":[{"raw_affiliation_string":"Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078980808","display_name":"Mohamed Lamine Mekhalfi","orcid":"https://orcid.org/0000-0002-4295-0974"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mohamed Lamine Mekhalfi","raw_affiliation_strings":["Digital Industry Center, Fondazione Bruno Kessler, Technologies of Vision, Trento, Italy","Technologies of Vision, Digital Industry Center, Fondazione Bruno Kessler, via Sommarive 18, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Industry Center, Fondazione Bruno Kessler, Technologies of Vision, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Technologies of Vision, Digital Industry Center, Fondazione Bruno Kessler, via Sommarive 18, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001185870","display_name":"Mansour Zuair","orcid":"https://orcid.org/0000-0003-2490-5739"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mansour Abdulaziz Al Zuair","raw_affiliation_strings":["Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-2490-5739","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021389231","display_name":"Farid Melgani","orcid":"https://orcid.org/0000-0001-9745-3732"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Farid Melgani","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9745-3732","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054237841"],"corresponding_institution_ids":["https://openalex.org/I28022161"],"apc_list":null,"apc_paid":null,"fwci":6.3952,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.97651392,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"60","issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8510046005249023},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6525697112083435},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6448058485984802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6277843117713928},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5274215936660767},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5141134858131409},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.49697402119636536},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.43668773770332336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43562859296798706},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4236689805984497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39111655950546265},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3221732974052429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510046005249023},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6525697112083435},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6448058485984802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6277843117713928},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5274215936660767},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5141134858131409},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.49697402119636536},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.43668773770332336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43562859296798706},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4236689805984497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39111655950546265},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3221732974052429},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tgrs.2022.3192460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2022.3192460","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/373008","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/373008","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334937","display_name":"Research Center of the College of Computer and Information Sciences, King Saud University","ror":"https://ror.org/02f81g417"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1933349210","https://openalex.org/W2802874102","https://openalex.org/W2899663614","https://openalex.org/W2899771611","https://openalex.org/W2963191264","https://openalex.org/W2964138343","https://openalex.org/W2964220823","https://openalex.org/W2994928934","https://openalex.org/W2995904231","https://openalex.org/W3004137323","https://openalex.org/W3004492228","https://openalex.org/W3008900036","https://openalex.org/W3012111773","https://openalex.org/W3015625772","https://openalex.org/W3017628311","https://openalex.org/W3035422918","https://openalex.org/W3042724941","https://openalex.org/W3046675509","https://openalex.org/W3091588028","https://openalex.org/W3098351727","https://openalex.org/W3109643012","https://openalex.org/W3111501160","https://openalex.org/W3117344638","https://openalex.org/W3128592650","https://openalex.org/W3128776197","https://openalex.org/W3159705445","https://openalex.org/W3166396011","https://openalex.org/W3168972675","https://openalex.org/W3169323098","https://openalex.org/W3180045188","https://openalex.org/W3185066916","https://openalex.org/W3206799531","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6719057275","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6780226713","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2113687551","https://openalex.org/W2112752961","https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Recently,":[0],"vision-language":[1],"models":[2],"based":[3,50],"on":[4,51,134,153],"transformers":[5],"are":[6],"gaining":[7],"popularity":[8,68],"for":[9,46,89],"joint":[10],"modeling":[11],"of":[12,100,130,137,149],"visual":[13,41,101],"and":[14,32,94,102,116,159],"textual":[15,103],"modalities.":[16],"In":[17,35,142,162],"particular,":[18,163],"they":[19],"show":[20],"impressive":[21],"results":[22,172],"when":[23],"transferred":[24],"to":[25,58,61,110,178],"several":[26],"downstream":[27],"tasks":[28],"such":[29],"as":[30],"zero":[31],"few-shot":[33],"classification.":[34],"this":[36],"paper,":[37],"we":[38,80,106,121,145,164],"propose":[39],"a":[40,98],"question":[42,95],"answering":[43],"(VQA)":[44],"approach":[45,152,168],"remote":[47,73],"sensing":[48,74],"images":[49],"these":[52,118],"models.":[53],"The":[54],"VQA":[55,65],"task":[56],"attempts":[57],"provide":[59],"answers":[60],"image-related":[62],"questions.":[63],"While":[64],"has":[66],"gained":[67],"in":[69,72],"computer":[70],"vision,":[71],"it":[75],"is":[76],"not":[77],"widespread.":[78],"First,":[79],"use":[81],"the":[82,91,112,123,128,135,138,143,147,150,179],"contrastive":[83],"language":[84],"image":[85,92],"pre-training":[86],"(CLIP)":[87],"network":[88],"embedding":[90],"patches":[93],"words":[96],"into":[97],"sequence":[99],"representations.":[104,119,141],"Then,":[105],"learn":[107],"attention":[108],"mechanisms":[109],"capture":[111],"intra-and-inter":[113],"dependencies":[114],"within":[115],"between":[117],"Afterward,":[120],"generate":[122],"final":[124],"answer":[125],"by":[126],"averaging":[127],"predictions":[129],"two":[131,154],"classifiers":[132],"mounted":[133],"top":[136],"resulting":[139],"contextual":[140],"experiments,":[144],"study":[146],"performance":[148],"proposed":[151],"datasets":[155],"acquired":[156],"with":[157,173],"Sentinel-2":[158],"aerial":[160],"sensors.":[161],"demonstrate":[165],"that":[166],"our":[167],"can":[169],"achieve":[170],"better":[171],"reduced":[174],"training":[175],"size":[176],"compared":[177],"recent":[180],"state-of-the-art.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":13}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-10-10T00:00:00"}