{"id":"https://openalex.org/W4399837196","doi":"https://doi.org/10.48550/arxiv.2406.12384","title":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","display_name":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399837196","doi":"https://doi.org/10.48550/arxiv.2406.12384"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.12384","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12384","pdf_url":"https://arxiv.org/pdf/2406.12384","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.12384","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100701417","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0003-0517-3894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101382777","display_name":"Jian Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085089542","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0001-9659-1551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elhoseiny, Mohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9606999754905701,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9606999754905701,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9535999894142151,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7788572907447815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.651070237159729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5867927074432373},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5650160908699036},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5094996094703674},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.42207399010658264},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1856445074081421},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.1544310450553894}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7788572907447815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.651070237159729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867927074432373},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5650160908699036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5094996094703674},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.42207399010658264},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1856445074081421},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1544310450553894}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.12384","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12384","pdf_url":"https://arxiv.org/pdf/2406.12384","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2406.12384","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.12384","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.12384","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12384","pdf_url":"https://arxiv.org/pdf/2406.12384","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399837196.pdf","grobid_xml":"https://content.openalex.org/works/W4399837196.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,104],"introduce":[1],"a":[2,57,95],"new":[3],"benchmark":[4,69,111],"designed":[5],"to":[6,29,38,127,130],"advance":[7],"the":[8,87,131,138],"development":[9,132],"of":[10,91,98,133,140],"general-purpose,":[11],"large-scale":[12],"vision-language":[13,21,59,92,114,135],"models":[14,93,108,136],"for":[15,61,112],"remote":[16,24,99,141],"sensing":[17,25,100],"images.":[18],"Although":[19],"several":[20],"datasets":[22,34],"in":[23,137],"have":[26],"been":[27],"proposed":[28],"pursue":[30],"this":[31,110],"goal,":[32],"existing":[33],"are":[35],"typically":[36],"tailored":[37],"single":[39],"tasks,":[40],"lack":[41],"detailed":[42,76],"object":[43,79],"information,":[44],"or":[45],"suffer":[46],"from":[47],"inadequate":[48],"quality":[49],"control.":[50],"Exploring":[51],"these":[52],"improvement":[53],"opportunities,":[54],"we":[55],"present":[56],"Versatile":[58],"Benchmark":[60],"Remote":[62],"Sensing":[63],"image":[64,101,116],"understanding,":[65],"termed":[66],"VRSBench.":[67],"This":[68],"comprises":[70],"29,614":[71,74],"images,":[72],"with":[73],"human-verified":[75],"captions,":[77],"52,472":[78],"references,":[80],"and":[81,89,120,145],"123,221":[82],"question-answer":[83],"pairs.":[84],"It":[85],"facilitates":[86],"training":[88],"evaluation":[90],"across":[94],"broad":[96],"spectrum":[97],"understanding":[102],"tasks.":[103],"further":[105],"evaluated":[106],"state-of-the-art":[107],"on":[109],"three":[113],"tasks:":[115],"captioning,":[117],"visual":[118,121],"grounding,":[119],"question":[122],"answering.":[123],"Our":[124],"work":[125],"aims":[126],"significantly":[128],"contribute":[129],"advanced":[134],"field":[139],"sensing.":[142],"The":[143],"data":[144],"code":[146],"can":[147],"be":[148],"accessed":[149],"at":[150],"https://github.com/lx709/VRSBench.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":9}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2024-06-20T00:00:00"}