{"id":"https://openalex.org/W4395041667","doi":"https://doi.org/10.3390/rs16091477","title":"RS-LLaVA: A Large Vision-Language Model for Joint Captioning and Question Answering in Remote Sensing Imagery","display_name":"RS-LLaVA: A Large Vision-Language Model for Joint Captioning and Question Answering in Remote Sensing Imagery","publication_year":2024,"publication_date":"2024-04-23","ids":{"openalex":"https://openalex.org/W4395041667","doi":"https://doi.org/10.3390/rs16091477"},"language":"en","primary_location":{"id":"doi:10.3390/rs16091477","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16091477","pdf_url":"https://www.mdpi.com/2072-4292/16/9/1477/pdf?version=1713858844","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/16/9/1477/pdf?version=1713858844","any_repository_has_fulltext":true},"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":["Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9287-0596","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","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":false,"raw_author_name":"Laila Bashmal","raw_affiliation_strings":["Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071736181","display_name":"Mohamad Mahmoud Al Rahhal","orcid":"https://orcid.org/0000-0002-8105-9746"},"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 11543, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-8105-9746","affiliations":[{"raw_affiliation_string":"Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh 11543, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"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":["Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2128-7456","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"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, 38123 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, 38123 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":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":15.1308,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.9948076,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"9","first_page":"1477","last_page":"1477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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":0.987500011920929,"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":0.6587400436401367},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6576223969459534},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5294955372810364},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49989914894104004},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4262947738170624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3810308575630188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3556699752807617},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19338169693946838},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1645316779613495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6587400436401367},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6576223969459534},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5294955372810364},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49989914894104004},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4262947738170624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3810308575630188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3556699752807617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19338169693946838},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1645316779613495},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/rs16091477","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16091477","pdf_url":"https://www.mdpi.com/2072-4292/16/9/1477/pdf?version=1713858844","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bbac3265f861430b919250d8f8f2e523","is_oa":false,"landing_page_url":"https://doaj.org/article/bbac3265f861430b919250d8f8f2e523","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 16, Iss 9, p 1477 (2024)","raw_type":"article"},{"id":"pmh:oai:iris.unitn.it:11572/437938","is_oa":true,"landing_page_url":"https://www.mdpi.com/2072-4292/16/9/1477","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:10.3390/rs16091477","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16091477","pdf_url":"https://www.mdpi.com/2072-4292/16/9/1477/pdf?version=1713858844","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321145","display_name":"King Saud University","ror":"https://ror.org/02f81g417"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4395041667.pdf"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1980038761","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2779054585","https://openalex.org/W2911584214","https://openalex.org/W2919929126","https://openalex.org/W2962749812","https://openalex.org/W2973586224","https://openalex.org/W2979924880","https://openalex.org/W2997056851","https://openalex.org/W3004137323","https://openalex.org/W3012111773","https://openalex.org/W3015625772","https://openalex.org/W3016776421","https://openalex.org/W3038038411","https://openalex.org/W3046260628","https://openalex.org/W3046675509","https://openalex.org/W3047058320","https://openalex.org/W3097754216","https://openalex.org/W3098351727","https://openalex.org/W3100245404","https://openalex.org/W3117344638","https://openalex.org/W3135367836","https://openalex.org/W3143320354","https://openalex.org/W3147394685","https://openalex.org/W3194015448","https://openalex.org/W3196922338","https://openalex.org/W4200272616","https://openalex.org/W4206028074","https://openalex.org/W4211112734","https://openalex.org/W4213157969","https://openalex.org/W4213449032","https://openalex.org/W4214587440","https://openalex.org/W4220716465","https://openalex.org/W4225991573","https://openalex.org/W4229439310","https://openalex.org/W4285285988","https://openalex.org/W4285744637","https://openalex.org/W4285818301","https://openalex.org/W4289537913","https://openalex.org/W4292968451","https://openalex.org/W4293508747","https://openalex.org/W4312236199","https://openalex.org/W4312272867","https://openalex.org/W4312389717","https://openalex.org/W4312513332","https://openalex.org/W4312920811","https://openalex.org/W4313021481","https://openalex.org/W4318718936","https://openalex.org/W4322707256","https://openalex.org/W4360930321","https://openalex.org/W4387402974","https://openalex.org/W4387546267","https://openalex.org/W4388752343","https://openalex.org/W4391136447","https://openalex.org/W6682631176","https://openalex.org/W6793754592","https://openalex.org/W6800139171","https://openalex.org/W6800425103","https://openalex.org/W6808332095","https://openalex.org/W6809415072","https://openalex.org/W6810294919","https://openalex.org/W6810920957","https://openalex.org/W6840231355","https://openalex.org/W6841412193","https://openalex.org/W6842763721","https://openalex.org/W6846740492","https://openalex.org/W6847457641","https://openalex.org/W6847648138","https://openalex.org/W6847672632","https://openalex.org/W6857440174"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"In":[0,47],"this":[1],"paper,":[2],"we":[3,49,78],"delve":[4],"into":[5],"the":[6,22,55,75,80,102,110],"innovative":[7],"application":[8],"of":[9,24,54,112],"large":[10,17],"language":[11],"models":[12,19,115],"(LLMs)":[13],"and":[14,42,58,96],"their":[15,33],"extension,":[16],"vision-language":[18],"(LVLMs),":[20],"in":[21],"field":[23],"remote":[25],"sensing":[26],"(RS)":[27],"image":[28,40,118],"analysis.":[29,119],"We":[30],"particularly":[31],"emphasize":[32],"multi-tasking":[34],"potential":[35],"with":[36],"a":[37,69,83,106],"focus":[38],"on":[39],"captioning":[41,95],"visual":[43],"question":[44],"answering":[45],"(VQA).":[46],"particular,":[48],"introduce":[50],"an":[51],"improved":[52],"version":[53],"Large":[56],"Language":[57],"Vision":[59],"Assistant":[60],"Model":[61],"(LLaVA),":[62],"specifically":[63],"adapted":[64],"for":[65,116],"RS":[66,117],"imagery":[67],"through":[68],"low-rank":[70],"adaptation":[71],"approach.":[72],"To":[73],"evaluate":[74],"model":[76],"performance,":[77],"create":[79],"RS-instructions":[81],"dataset,":[82],"comprehensive":[84],"benchmark":[85],"dataset":[86],"that":[87],"integrates":[88],"four":[89],"diverse":[90],"single-task":[91],"datasets":[92],"related":[93],"to":[94],"VQA.":[97],"The":[98],"experimental":[99],"results":[100],"confirm":[101],"model\u2019s":[103],"effectiveness,":[104],"marking":[105],"step":[107],"forward":[108],"toward":[109],"development":[111],"efficient":[113],"multi-task":[114]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":6}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}
