{"id":"https://openalex.org/W4386232111","doi":"https://doi.org/10.1109/lsp.2023.3309578","title":"Multi-Scale Aggregation Transformers for Multispectral Object Detection","display_name":"Multi-Scale Aggregation Transformers for Multispectral Object Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386232111","doi":"https://doi.org/10.1109/lsp.2023.3309578"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3309578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3309578","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101970689","display_name":"Shuai You","orcid":"https://orcid.org/0000-0002-8095-8141"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuai You","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications (NJUPT), Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications (NJUPT), Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077126423","display_name":"Xuedong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuedong Xie","raw_affiliation_strings":["School of Computer Science, NJUPT, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, NJUPT, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083814325","display_name":"Yujian Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujian Feng","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications (NJUPT), Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications (NJUPT), Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041393995","display_name":"Chaojun Mei","orcid":"https://orcid.org/0009-0003-6823-2377"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaojun Mei","raw_affiliation_strings":["School of Computer Science, NJUPT, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, NJUPT, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053206926","display_name":"Yimu Ji","orcid":"https://orcid.org/0000-0001-7019-3942"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimu Ji","raw_affiliation_strings":["School of Computer Science, NJUPT, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, NJUPT, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101970689"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":2.8634,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92660838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1172","last_page":"1176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983000159263611,"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":0.9980000257492065,"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/discriminative-model","display_name":"Discriminative model","score":0.7454036474227905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7385355830192566},{"id":"https://openalex.org/keywords/multispectral-image","display_name":"Multispectral image","score":0.6490631103515625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5916928052902222},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4653279185295105},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.41889074444770813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3966776430606842},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3883119523525238},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36197441816329956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3440285921096802}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7454036474227905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385355830192566},{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.6490631103515625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916928052902222},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4653279185295105},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41889074444770813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3966776430606842},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3883119523525238},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36197441816329956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3440285921096802},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3309578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3309578","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1623347460","display_name":null,"funder_award_id":"62076139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G575655210","display_name":null,"funder_award_id":"62176264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":39,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1910108985","https://openalex.org/W2752782242","https://openalex.org/W2920991918","https://openalex.org/W2963351448","https://openalex.org/W2964093967","https://openalex.org/W2982770724","https://openalex.org/W3036931590","https://openalex.org/W3083388823","https://openalex.org/W3106250896","https://openalex.org/W3116967329","https://openalex.org/W3118570274","https://openalex.org/W3130394099","https://openalex.org/W3133696297","https://openalex.org/W3164576087","https://openalex.org/W3164802490","https://openalex.org/W3171583481","https://openalex.org/W3174002518","https://openalex.org/W3185043317","https://openalex.org/W3187910480","https://openalex.org/W3201025429","https://openalex.org/W3207919963","https://openalex.org/W4200631567","https://openalex.org/W4210621820","https://openalex.org/W4285099087","https://openalex.org/W4288773267","https://openalex.org/W4293584584","https://openalex.org/W4307899054","https://openalex.org/W4312302306","https://openalex.org/W4312549624","https://openalex.org/W4313007055","https://openalex.org/W4313291151","https://openalex.org/W4320036619","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6750227808","https://openalex.org/W6759794908","https://openalex.org/W6785652829","https://openalex.org/W6790690058"],"related_works":["https://openalex.org/W2073139667","https://openalex.org/W2729514902","https://openalex.org/W2024160000","https://openalex.org/W2773500201","https://openalex.org/W2061273563","https://openalex.org/W2956043259","https://openalex.org/W4287995534","https://openalex.org/W2743258233","https://openalex.org/W2285052147","https://openalex.org/W1966028303"],"abstract_inverted_index":{"Multispectral":[0],"object":[1,27],"detection":[2],"for":[3],"autonomous":[4],"driving":[5,93],"is":[6,181,208],"multi-object":[7],"localization":[8],"and":[9,14,33,85,88,113,127,141,166],"classification":[10],"task":[11],"on":[12,49,62,187,192],"visible":[13],"thermal":[15],"modalities.":[16],"In":[17,95],"this":[18,96],"scenario,":[19],"modality":[20,32,177],"differences":[21],"lead":[22],"to":[23,70,129,146,162,171,183],"the":[24,34,92,114,123,148,179],"lack":[25,149],"of":[26,36,106,125,150],"information":[28,47,77,133,151,186],"in":[29,73,91,152],"a":[30,50,100,153,158],"single":[31,51,154],"misalignment":[35,174],"cross-modality":[37],"information.":[38],"To":[39],"alleviate":[40,172],"these":[41,58],"problems,":[42],"most":[43],"existing":[44],"methods":[45,59],"extract":[46,130,163],"based":[48],"scale":[52],"(":[53,78],"<italic":[54,79],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55,80,212],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e.g</i>":[56,81],".,":[57,82],"mainly":[60],"focus":[61],"detecting":[63],"significant":[64],"cars":[65],"or":[66],"pedestrians),":[67],"which":[68,120],"leads":[69],"insufficient":[71],"performance":[72],"capturing":[74],"multi-scale":[75],"discriminative":[76],"small":[83],"bicycles":[84],"blurred":[86],"pedestrians)":[87],"safety":[89],"hazards":[90],"process.":[94],"paper,":[97],"we":[98,156],"propose":[99],"Multi-Scale":[101,109],"Aggregation":[102,110],"Network":[103],"(MSANet)":[104],"consisting":[105],"two":[107,135,193],"parts":[108],"Transformer":[111,126],"(MSAT)":[112],"Cross-modal":[115],"Merging":[116],"Fusion":[117],"Mechanism":[118],"(CMFM),":[119],"combined":[121],"with":[122],"advantages":[124],"CNN":[128],"rich":[131,164],"image":[132],"from":[134,168],"modalities":[136],"by":[137,176],"mining":[138],"both":[139],"local":[140],"global":[142],"context":[143],"dependencies.":[144],"Firstly,":[145],"reduce":[147],"modality,":[155],"design":[157],"novel":[159],"MSAT":[160],"module":[161],"details":[165],"texture":[167],"multi-scale.":[169],"Secondly,":[170],"feature":[173],"caused":[175],"differences,":[178],"CMFM":[180],"utilized":[182],"aggregate":[184],"complementary":[185],"multiple":[188],"levels.":[189],"Comprehensive":[190],"experiments":[191],"benchmarks":[194],"demonstrate":[195],"that":[196],"our":[197],"approach":[198],"shows":[199],"better":[200],"results":[201],"than":[202],"several":[203],"state-of-the-art":[204],"methods.":[205],"The":[206],"code":[207],"available":[209],"at":[210],"<uri":[211],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ysh-strive/MSANet</uri>":[213],".":[214]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}