{"id":"https://openalex.org/W4405030229","doi":"https://doi.org/10.1109/iccv51701.2025.00670","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","display_name":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405030229","doi":"https://doi.org/10.1109/iccv51701.2025.00670"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.19325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071342791","display_name":"Muhammad Sohail Danish","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Muhammad Sohail Danish","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037593408","display_name":"Muhammad Akhtar Munir","orcid":"https://orcid.org/0000-0002-9642-0936"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Akhtar Munir","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078723133","display_name":"Syed Roshaan Ali Shah","orcid":"https://orcid.org/0000-0001-9517-5142"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Roshaan Ali Shah","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093367695","display_name":"Kartik Kuckreja","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Kartik Kuckreja","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062702059","display_name":"Paolo Fraccaro","orcid":"https://orcid.org/0000-0002-5213-7071"},"institutions":[{"id":"https://openalex.org/I4210121844","display_name":"IBM (United Kingdom)","ror":"https://ror.org/02wat9f69","country_code":"GB","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210121844"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paolo Fraccaro","raw_affiliation_strings":["IBM Research Europe,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe,UK","institution_ids":["https://openalex.org/I4210121844"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040248599","display_name":"Alexandre Lacoste","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167039","display_name":"ServiceNow (United States)","ror":"https://ror.org/05xr0bc04","country_code":"US","type":"company","lineage":["https://openalex.org/I4210167039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandre Lacoste","raw_affiliation_strings":["ServiceNow Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ServiceNow Research","institution_ids":["https://openalex.org/I4210167039"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101483979","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-2905-1755"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5071342791"],"corresponding_institution_ids":["https://openalex.org/I4210113480"],"apc_list":null,"apc_paid":null,"fwci":8.1591,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96621464,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7132","last_page":"7142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.979200005531311,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.979200005531311,"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"}},{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9053999781608582,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/benchmarking","display_name":"Benchmarking","score":0.8416702747344971},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.8153133392333984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6038109064102173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3942638039588928},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.33157193660736084},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32359299063682556},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.22545075416564941},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.08414387702941895}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8416702747344971},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.8153133392333984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6038109064102173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3942638039588928},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.33157193660736084},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32359299063682556},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.22545075416564941},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.08414387702941895},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.19325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19325","pdf_url":"https://arxiv.org/pdf/2411.19325","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2411.19325","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.19325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.19325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19325","pdf_url":"https://arxiv.org/pdf/2411.19325","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967"],"abstract_inverted_index":{"While":[0],"numerous":[1],"recent":[2],"benchmarks":[3,24],"focus":[4],"on":[5,89,129,163],"evaluating":[6],"generic":[7],"Vision-Language":[8],"Models":[9],"(VLMs),":[10],"they":[11,141],"do":[12],"not":[13,26],"effectively":[14],"address":[15],"the":[16,30,52,150,156,173],"specific":[17],"challenges":[18,50,143],"of":[19,32],"geospatial":[20,33,53,90],"applications.":[21],"Generic":[22],"VLM":[23],"are":[25],"designed":[27,85],"to":[28,86,126],"handle":[29],"complexities":[31],"data,":[34],"an":[35],"essential":[36],"component":[37],"for":[38,152],"applications":[39],"such":[40],"as":[41],"environmental":[42],"monitoring,":[43],"urban":[44],"planning,":[45],"and":[46,65,101,112,119],"disaster":[47],"management.":[48],"Key":[49],"in":[51,70],"domain":[54],"include":[55],"temporal":[56,102],"change":[57],"detection,":[58,64],"large-scale":[59],"object":[60,63,95,117],"counting,":[61,96],"tiny":[62],"understanding":[66],"relationships":[67],"between":[68],"entities":[69],"remote":[71],"sensing":[72],"imagery.":[73],"To":[74],"bridge":[75],"this":[76],"gap,":[77],"we":[78],"present":[79],"GEOBench-VLM,":[80],"a":[81],"comprehensive":[82],"benchmark":[83,105,178],"specifically":[84],"evaluate":[87,122],"VLMs":[88,125,138],"tasks,":[91,148],"including":[92],"scene":[93],"understanding,":[94],"localization,":[97],"fine-grained":[98],"categorization,":[99],"segmentation,":[100],"analysis.":[103],"Our":[104,177],"features":[106],"over":[107],"10,000":[108],"manually":[109],"verified":[110],"instructions":[111],"spanning":[113],"diverse":[114],"visual":[115],"conditions,":[116],"types,":[118],"scales.":[120],"We":[121],"several":[123],"state-of-the-art":[124],"assess":[127],"performance":[128],"geospatial-specific":[130,147],"challenges.":[131],"The":[132],"results":[133],"indicate":[134],"that":[135],"although":[136],"existing":[137],"demonstrate":[139],"potential,":[140],"face":[142],"when":[144],"dealing":[145],"with":[146],"highlighting":[149],"room":[151],"further":[153],"improvements.":[154],"Notably,":[155],"best-performing":[157],"LLaVa-OneVision":[158],"achieves":[159],"only":[160],"41.7%":[161],"accuracy":[162],"MCQs,":[164],"slightly":[165],"more":[166],"than":[167],"GPT-4o,":[168],"which":[169],"is":[170,179],"approximately":[171],"double":[172],"random":[174],"guess":[175],"performance.":[176],"publicly":[180],"available":[181],"at":[182],"https://github.com/The-AI-Alliance/GEO-Bench-VLM":[183],".":[184]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}