{"id":"https://openalex.org/W4317496152","doi":"https://doi.org/10.1109/tcds.2023.3238181","title":"YOLO-MS: Multispectral Object Detection via Feature Interaction and Self-Attention Guided Fusion","display_name":"YOLO-MS: Multispectral Object Detection via Feature Interaction and Self-Attention Guided Fusion","publication_year":2023,"publication_date":"2023-01-19","ids":{"openalex":"https://openalex.org/W4317496152","doi":"https://doi.org/10.1109/tcds.2023.3238181"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2023.3238181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3238181","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","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/A5021531481","display_name":"Yumin Xie","orcid":"https://orcid.org/0000-0003-1552-4598"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yumin Xie","raw_affiliation_strings":["College of Automation Science and Technology, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Automation Science and Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081573912","display_name":"Langwen Zhang","orcid":"https://orcid.org/0000-0002-1024-1399"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Langwen Zhang","raw_affiliation_strings":["College of Automation Science and Technology, the Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, and Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Automation Science and Technology, the Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, and Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827284","display_name":"Xiaoyuan Yu","orcid":"https://orcid.org/0000-0001-6234-9775"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Yu","raw_affiliation_strings":["College of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100678496","display_name":"Wei Xie","orcid":"https://orcid.org/0000-0002-7840-5652"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xie","raw_affiliation_strings":["College of Automation Science and Technology, the Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, and Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Automation Science and Technology, the Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, and Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021531481"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":6.9701,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97384395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"15","issue":"4","first_page":"2132","last_page":"2143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9997000098228455,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9997000098228455,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9990000128746033,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/computer-science","display_name":"Computer science","score":0.8122692108154297},{"id":"https://openalex.org/keywords/multispectral-image","display_name":"Multispectral image","score":0.7596151828765869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7043418884277344},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6727078557014465},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6193615794181824},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.538509726524353},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5041037797927856},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5038184523582458},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5021810531616211},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4878380596637726},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48281750082969666},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.45521965622901917},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.436331182718277},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4270237982273102},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17523548007011414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122692108154297},{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.7596151828765869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7043418884277344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6727078557014465},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6193615794181824},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.538509726524353},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5041037797927856},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5038184523582458},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5021810531616211},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4878380596637726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48281750082969666},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.45521965622901917},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.436331182718277},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4270237982273102},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17523548007011414},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2023.3238181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3238181","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1852352616","display_name":null,"funder_award_id":"2022A1515011887","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G4302718655","display_name":null,"funder_award_id":"61973125","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5375066465","display_name":null,"funder_award_id":"2022A1019","funder_id":"https://openalex.org/F4320329699","funder_display_name":"Zhongshan Science and Technology Bureau"},{"id":"https://openalex.org/G7300190550","display_name":null,"funder_award_id":"61803161","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7804127032","display_name":null,"funder_award_id":"202102020379","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320329699","display_name":"Zhongshan Science and Technology Bureau","ror":null},{"id":"https://openalex.org/F4320335480","display_name":"Guangzhou Municipal Science and Technology Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2046928368","https://openalex.org/W2522703671","https://openalex.org/W2524771588","https://openalex.org/W2589930967","https://openalex.org/W2734941396","https://openalex.org/W2741620214","https://openalex.org/W2752782242","https://openalex.org/W2782074210","https://openalex.org/W2792925809","https://openalex.org/W2798987894","https://openalex.org/W2884585870","https://openalex.org/W2912147220","https://openalex.org/W2922509574","https://openalex.org/W2952565170","https://openalex.org/W2953303055","https://openalex.org/W2955058313","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963188557","https://openalex.org/W2963579094","https://openalex.org/W2967090870","https://openalex.org/W2981689412","https://openalex.org/W3011768656","https://openalex.org/W3036931590","https://openalex.org/W3042011474","https://openalex.org/W3046194589","https://openalex.org/W3047443805","https://openalex.org/W3048631361","https://openalex.org/W3102692100","https://openalex.org/W3103294617","https://openalex.org/W3103695279","https://openalex.org/W3105639468","https://openalex.org/W3106808132","https://openalex.org/W3108042295","https://openalex.org/W3118570274","https://openalex.org/W3118589616","https://openalex.org/W3126855404","https://openalex.org/W3133700567","https://openalex.org/W3135785775","https://openalex.org/W3176482836","https://openalex.org/W3201025429","https://openalex.org/W3209540366","https://openalex.org/W4200443834","https://openalex.org/W4312594135","https://openalex.org/W6750227808","https://openalex.org/W6756834165","https://openalex.org/W6759794908","https://openalex.org/W6798274885"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3214791684","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2549658594","https://openalex.org/W2353265673","https://openalex.org/W2370195708"],"abstract_inverted_index":{"Object":[0],"detection":[1,20,32,46,186],"is":[2,14],"essential":[3],"for":[4,101],"an":[5,67],"autonomous":[6],"driving":[7],"sensing":[8],"system.":[9],"Since":[10],"the":[11,19,31,61,83,87,96,103,145,154,159,165,181],"light":[12],"condition":[13],"changed":[15],"in":[16,60],"unconstrained":[17],"scenarios,":[18],"accuracy":[21,33],"based":[22],"on":[23,153],"visible":[24,39],"images":[25],"can":[26,34,148],"be":[27,35,149],"greatly":[28],"degraded.":[29],"Although":[30],"improved":[36],"by":[37,72,95,131],"fusing":[38],"and":[40,54,77,109,119,158,176],"infrared":[41],"images,":[42],"existing":[43],"multispectral":[44],"object":[45],"(MOD)":[47],"algorithms":[48],"suffer":[49],"from":[50],"inadequate":[51],"intermodal":[52],"interaction":[53,76,98],"a":[55,74,133,140],"lack":[56],"of":[57,106,112,144],"global":[58],"dependence":[59,125],"fusion":[62,79,136,175],"approach.":[63],"Thus,":[64,139],"we":[65],"propose":[66],"MOD":[68],"framework":[69],"called":[70],"YOLO-MS":[71,167,183],"designing":[73],"feature":[75,97,135],"self-attention":[78,134],"network":[80],"(FISAFN)":[81],"as":[82],"backbone":[84],"network.":[85],"Within":[86],"FISAFN,":[88],"correlations":[89],"between":[90,126],"two":[91,127],"modalities":[92,128],"are":[93,129],"extracted":[94],"module":[99,137],"(FIM)":[100],"reconstructing":[102],"information":[104,113,124,142],"components":[105],"each":[107],"modality":[108],"enhancing":[110],"capability":[111],"exchange.":[114],"To":[115],"filter":[116],"redundant":[117],"features":[118,147],"enhance":[120],"complementary":[121],"features,":[122],"long-range":[123],"established":[130],"using":[132],"(SAFFM).":[138],"better":[141],"richness":[143],"fused":[146],"achieved.":[150],"Experimental":[151],"results":[152],"FLIR-aligned":[155],"data":[156,161],"set":[157,162],"M3FD":[160],"demonstrate":[163],"that":[164],"proposed":[166,182],"performs":[168],"favorably":[169],"against":[170],"state-of-the-art":[171],"approaches,":[172],"including":[173],"feature-level":[174],"pixel-level":[177],"fusion.":[178],"And":[179],"further,":[180],"possesses":[184],"good":[185],"performance":[187],"under":[188],"diverse":[189],"scene":[190],"conditions.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}