{"id":"https://openalex.org/W7138794133","doi":"https://doi.org/10.1609/aaai.v40i6.42457","title":"MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images","display_name":"MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138794133","doi":"https://doi.org/10.1609/aaai.v40i6.42457"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i6.42457","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42457","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i6.42457","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102607421","display_name":"Shuaihao Han","orcid":"https://orcid.org/0009-0008-2594-1516"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaihao Han","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129668190","display_name":"Tingfa Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingfa Xu","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056239970","display_name":"Peifu Liu","orcid":"https://orcid.org/0000-0003-4018-1478"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peifu Liu","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129654645","display_name":"Jianan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianan Li","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":26.4348,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98738343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"40","issue":"6","first_page":"4574","last_page":"4582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.5975000262260437,"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"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.5975000262260437,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.1137000024318695,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.07900000363588333,"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/multispectral-image","display_name":"Multispectral image","score":0.8097000122070312},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7479000091552734},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6820999979972839},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.58160001039505},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5135999917984009},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48010000586509705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4708999991416931}],"concepts":[{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.8097000122070312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506999969482422},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7479000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.701200008392334},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6820999979972839},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5275999903678894},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3734000027179718},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.32899999618530273},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C104541649","wikidata":"https://www.wikidata.org/wiki/Q6935090","display_name":"Multispectral pattern recognition","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i6.42457","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42457","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42457","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42457","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7834638953208923,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Aerial":[0,74],"object":[1,103],"detection":[2,104],"faces":[3],"significant":[4],"challenges":[5,99],"in":[6,73],"real-world":[7],"scenarios,":[8,87],"such":[9],"as":[10],"small":[11],"objects":[12],"and":[13,81,115,144,173],"extensive":[14],"background":[15,147],"interference,":[16],"which":[17,77],"limit":[18],"the":[19,43,50,55,65],"performance":[20],"of":[21,45,57],"RGB-based":[22],"detectors":[23],"with":[24,118,170],"insufficient":[25],"discriminative":[26],"information.":[27],"Multispectral":[28,70],"images":[29,75],"(MSIs)":[30],"capture":[31],"additional":[32],"spectral":[33,114,138],"cues":[34],"across":[35,84],"multiple":[36],"bands,":[37],"offering":[38],"a":[39,89,110,123],"promising":[40],"alternative.":[41],"However,":[42],"lack":[44],"training":[46],"data":[47,91],"has":[48],"been":[49],"primary":[51],"bottleneck":[52],"to":[53,97,101,128,140],"exploiting":[54,137],"potential":[56],"MSIs.":[58],"To":[59],"address":[60],"this":[61,94],"gap,":[62],"we":[63,107],"introduce":[64],"first":[66],"large-scale":[67],"dataset":[68],"for":[69,93],"Object":[71],"Detection":[72],"(MODA),":[76],"comprises":[78],"14,041":[79],"MSIs":[80],"330,191":[82],"annotations":[83],"diverse,":[85],"challenging":[86],"providing":[88],"comprehensive":[90],"foundation":[92],"field.":[95],"Furthermore,":[96],"overcome":[98],"inherent":[100],"aerial":[102],"using":[105],"MSIs,":[106],"propose":[108],"OSSDet,":[109],"framework":[111],"that":[112,165],"integrates":[113],"spatial":[116],"information":[117],"object-aware":[119,149,160],"cues.":[120],"OSSDet":[121,166],"employs":[122],"cascaded":[124],"spectral-spatial":[125],"modulation":[126],"structure":[127],"optimize":[129],"target":[130],"perception,":[131],"aggregates":[132],"spectrally":[133],"related":[134],"features":[135],"by":[136],"similarities":[139],"reinforce":[141],"intra-object":[142],"correlations,":[143],"suppresses":[145],"irrelevant":[146],"via":[148],"masking.":[150],"Moreover,":[151],"cross-spectral":[152],"attention":[153],"further":[154],"refines":[155],"object-related":[156],"representations":[157],"under":[158],"explicit":[159],"guidance.":[161],"Extensive":[162],"experiments":[163],"demonstrate":[164],"outperforms":[167],"existing":[168],"methods":[169],"comparable":[171],"parameters":[172],"efficiency.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}