{"id":"https://openalex.org/W4402979044","doi":"https://doi.org/10.1109/icme57554.2024.10687493","title":"MISTA: A Large-Scale Dataset for Multi-Modal Instruction Tuning on Aerial Images","display_name":"MISTA: A Large-Scale Dataset for Multi-Modal Instruction Tuning on Aerial Images","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979044","doi":"https://doi.org/10.1109/icme57554.2024.10687493"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5100658091","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0003-3041-2922"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Wu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072833759","display_name":"Ke L\u00fc","orcid":"https://orcid.org/0000-0003-0176-3088"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085287554","display_name":"Yuqiu Li","orcid":"https://orcid.org/0009-0009-4060-9092"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqiu Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025522422","display_name":"Junhao Huang","orcid":"https://orcid.org/0000-0002-0074-2851"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763213","display_name":"Jian Xue","orcid":"https://orcid.org/0000-0002-9460-802X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Xue","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100658091"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54254935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.867900013923645,"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":0.867900013923645,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7675999999046326,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7457585334777832},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6728373765945435},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6069808602333069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5455911755561829},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38933998346328735},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10119104385375977},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09723815321922302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457585334777832},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6728373765945435},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6069808602333069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5455911755561829},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38933998346328735},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10119104385375977},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09723815321922302},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2963518342","https://openalex.org/W3012111773","https://openalex.org/W3095319910","https://openalex.org/W3165084071","https://openalex.org/W3168972675","https://openalex.org/W3201797941","https://openalex.org/W4225991573","https://openalex.org/W4395091069","https://openalex.org/W4402727764"],"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":{"This":[0],"paper":[1],"introduces":[2],"MISTA,":[3],"a":[4,42,122,130,142],"novel":[5],"dataset":[6,46,118],"for":[7,48,121,133,148],"visual":[8,127],"instruction":[9,82],"tuning":[10],"on":[11],"aerial":[12,29,106],"imagery,":[13],"designed":[14],"to":[15,71],"enhance":[16],"large":[17],"multi-modal":[18,134],"model":[19,135],"applications":[20,153],"in":[21,97,137,154],"remote":[22,49,98,138],"sensing.":[23],"Originating":[24],"from":[25],"the":[26,94,114,117,146,155],"renowned":[27],"DOTA-v2.0":[28],"object":[30],"detection":[31],"benchmark,":[32],"MISTA":[33,140],"uniformly":[34],"processes":[35],"high-resolution":[36],"images":[37,107],"into":[38,108],"2048\u00d72048":[39],"pixels,":[40],"creating":[41],"detailed":[43,87],"and":[44,69,74,89,119,151],"complex":[45,90],"tailored":[47],"sensing":[50,99],"analysis.":[51],"To":[52],"craft":[53],"this":[54],"dataset,":[55],"we":[56],"design":[57],"an":[58],"automated":[59],"annotation":[60],"pipeline,":[61],"employing":[62],"advanced":[63],"language":[64],"models":[65],"such":[66],"as":[67],"GPT-4":[68],"LLaVA-1.5,":[70],"generate":[72],"diverse":[73],"specialized":[75],"instruction-following":[76],"data.":[77],"The":[78,101],"annotations":[79],"include":[80],"various":[81],"types":[83],"like":[84],"multi-turn":[85],"conversation,":[86],"description,":[88],"reasoning,":[91],"each":[92],"reflecting":[93],"intricacies":[95],"inherent":[96],"tasks.":[100],"innovative":[102],"approach":[103],"of":[104,116,126],"subdividing":[105],"individually":[109],"annotated":[110],"sub-patches":[111],"significantly":[112],"enhances":[113],"richness":[115],"allows":[120],"more":[123],"granular":[124],"analysis":[125],"content.":[128],"As":[129],"robust":[131],"foundation":[132],"development":[136],"sensing,":[139],"represents":[141],"significant":[143],"advancement,":[144],"setting":[145],"stage":[147],"future":[149],"research":[150],"further":[152],"field.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}