{"id":"https://openalex.org/W4360930321","doi":"https://doi.org/10.1109/jstars.2023.3261361","title":"Visual Question Generation From Remote Sensing Images","display_name":"Visual Question Generation From Remote Sensing Images","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4360930321","doi":"https://doi.org/10.1109/jstars.2023.3261361"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2023.3261361","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2023.3261361","pdf_url":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10081015.pdf","source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10081015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064445451","display_name":"Laila Bashmal","orcid":null},"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":"Laila Bashmal","raw_affiliation_strings":["Computer Engineering, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yakoub Bazi","raw_affiliation_strings":["Computer Engineering, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9287-0596","affiliations":[{"raw_affiliation_string":"Computer Engineering, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","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 Computer Science and Information Engineering, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9745-3732","affiliations":[{"raw_affiliation_string":"Department Computer Science and Information Engineering, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004777179","display_name":"Riccardo Ricci","orcid":"https://orcid.org/0000-0002-2128-7456"},"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":"Riccardo Ricci","raw_affiliation_strings":["Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2128-7456","affiliations":[{"raw_affiliation_string":"Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103158262","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 M. Al Rahhal","raw_affiliation_strings":["College of Applied Computer Sciences, King Saud University, Riyadh, Saudi Arabia","College of Applied computer Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4467-650X","affiliations":[{"raw_affiliation_string":"College of Applied Computer Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Applied computer Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","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 Zuair","raw_affiliation_strings":["Computer Engineering, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-2490-5739","affiliations":[{"raw_affiliation_string":"Computer Engineering, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064445451"],"corresponding_institution_ids":["https://openalex.org/I28022161"],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":2.3164,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90245206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"16","issue":null,"first_page":"3279","last_page":"3293"},"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":0.9959999918937683,"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":0.9904999732971191,"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":0.85025954246521},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6214866042137146},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.6091577410697937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5871004462242126},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5613162517547607},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5273959040641785},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5138283371925354},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4992249011993408},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.47079387307167053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.469562292098999},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4598162770271301},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38009271025657654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3405168950557709},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.255159854888916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85025954246521},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6214866042137146},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6091577410697937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871004462242126},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5613162517547607},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5273959040641785},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5138283371925354},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4992249011993408},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.47079387307167053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.469562292098999},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4598162770271301},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38009271025657654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3405168950557709},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.255159854888916},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jstars.2023.3261361","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2023.3261361","pdf_url":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10081015.pdf","source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b49cde89939c4b998ccfc39786ac1561","is_oa":true,"landing_page_url":"https://doaj.org/article/b49cde89939c4b998ccfc39786ac1561","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 16, Pp 3279-3293 (2023)","raw_type":"article"},{"id":"pmh:oai:iris.unitn.it:11572/400702","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/400702","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2023.3261361","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2023.3261361","pdf_url":"https://ieeexplore.ieee.org/ielx7/4609443/4609444/10081015.pdf","source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321145","display_name":"King Saud University","ror":"https://ror.org/02f81g417"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4360930321.pdf","grobid_xml":"https://content.openalex.org/works/W4360930321.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1980038761","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2510520237","https://openalex.org/W2515866431","https://openalex.org/W2561296180","https://openalex.org/W2592962403","https://openalex.org/W2603566245","https://openalex.org/W2607059968","https://openalex.org/W2626107033","https://openalex.org/W2779054585","https://openalex.org/W2808021740","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2949555952","https://openalex.org/W2962749812","https://openalex.org/W2963051286","https://openalex.org/W2963087285","https://openalex.org/W2963351776","https://openalex.org/W2963976294","https://openalex.org/W2964065333","https://openalex.org/W2973586224","https://openalex.org/W2974722004","https://openalex.org/W2979924880","https://openalex.org/W2997056851","https://openalex.org/W3004137323","https://openalex.org/W3011916860","https://openalex.org/W3012111773","https://openalex.org/W3015625772","https://openalex.org/W3034858767","https://openalex.org/W3038038411","https://openalex.org/W3046260628","https://openalex.org/W3094502228","https://openalex.org/W3096826274","https://openalex.org/W3097754216","https://openalex.org/W3098351727","https://openalex.org/W3100245404","https://openalex.org/W3105577662","https://openalex.org/W3117344638","https://openalex.org/W3138516171","https://openalex.org/W3157509826","https://openalex.org/W3168972675","https://openalex.org/W3195299381","https://openalex.org/W3196922338","https://openalex.org/W3203031838","https://openalex.org/W3207071456","https://openalex.org/W4225991573","https://openalex.org/W4305005880","https://openalex.org/W4307321662","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6728274705","https://openalex.org/W6730782440","https://openalex.org/W6768632716","https://openalex.org/W6784333009","https://openalex.org/W6802006682","https://openalex.org/W6802726400","https://openalex.org/W6845668075"],"related_works":["https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W3009270862","https://openalex.org/W3113264705","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W4213176082"],"abstract_inverted_index":{"Visual":[0],"question":[1],"generation":[2],"(VQG)":[3],"is":[4,74,115,208],"a":[5,27,58,63,77,81,95,122,146],"fundamental":[6],"task":[7],"in":[8,35,87,91,104,141,175,195],"vision-language":[9],"understanding":[10],"that":[11],"aims":[12],"to":[13,61,79,97,120],"generate":[14,62,121],"relevant":[15,125],"questions":[16,34,90,126,162,174,201],"about":[17,38],"the":[18,69,92,99,105,110,112,128,169,173,188],"given":[19],"input":[20],"image.":[21,70,130],"In":[22],"this":[23,72],"paper,":[24],"we":[25,56,144],"propose":[26],"paragraph-based":[28],"VQG":[29,156,193],"approach":[30],"for":[31,151,154],"generating":[32,88,196],"intelligent":[33],"natural":[36],"language":[37,53,113],"remote":[39],"sensing":[40],"(RS)":[41],"images.":[42,204],"Specifically,":[43],"our":[44,133,155,191],"proposed":[45,192],"framework":[46],"consists":[47,160],"of":[48,94,124,161,172,190],"two":[49,136],"transformer-based":[50],"vision":[51],"and":[52,184,199],"models.":[54],"First,":[55],"employ":[57],"swin-transformer":[59],"encoder":[60],"multi-scale":[64],"representative":[65],"visual":[66,101,137],"feature":[67,73],"from":[68,127,202],"Then,":[71],"used":[75],"as":[76],"prefix":[78],"guide":[80],"generative":[82],"pre-trained":[83],"transformer-2":[84],"(GPT-2)":[85],"decoder":[86,114],"multiple":[89],"form":[93],"paragraph":[96],"cover":[98],"abundant":[100],"information":[102],"contained":[103],"RS":[106,118,129,203],"scene.":[107],"To":[108],"train":[109],"model,":[111],"fine-tuned":[116],"on":[117,135],"dataset":[119,148,159,207],"set":[123],"We":[131],"evaluate":[132],"model":[134,194],"question-answering":[138],"(VQA)":[139],"datasets":[140],"RS.":[142],"Additionally,":[143],"construct":[145],"new":[147],"termed":[149],"TextRS-VQA":[150,206],"better":[152],"evaluation":[153],"model.":[157],"This":[158],"completely":[163],"annotated":[164],"by":[165],"humans":[166],"which":[167],"addresses":[168],"high":[170],"redundancy":[171],"prior":[176],"VQA":[177],"datasets.":[178],"Extensive":[179],"experiments":[180],"using":[181],"several":[182],"accuracy":[183],"diversity":[185],"metrics":[186],"demonstrate":[187],"effectiveness":[189],"meaningful,":[197],"valid,":[198],"diverse":[200],"The":[205],"available":[209],"at:":[210],"<uri":[211],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[212],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/yakoubbazi/TextRS</uri>":[213],".":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}