{"id":"https://openalex.org/W4400491496","doi":"https://doi.org/10.1109/cscwd61410.2024.10580205","title":"MF-YOLO: Multimodal Fusion for Remote Sensing Object Detection Based on YOLOv5s","display_name":"MF-YOLO: Multimodal Fusion for Remote Sensing Object Detection Based on YOLOv5s","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4400491496","doi":"https://doi.org/10.1109/cscwd61410.2024.10580205"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd61410.2024.10580205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd61410.2024.10580205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5100363910","display_name":"Wenqiang Li","orcid":"https://orcid.org/0000-0003-3696-1893"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Li","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016226762","display_name":"Aimin Li","orcid":"https://orcid.org/0000-0003-3687-4378"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aimin Li","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091303936","display_name":"Xiaotong Kong","orcid":"https://orcid.org/0000-0002-3540-6233"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotong Kong","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009874821","display_name":"Yuechen Zhang","orcid":"https://orcid.org/0009-0000-9112-0216"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuechen Zhang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079169706","display_name":"Zhiyao Li","orcid":"https://orcid.org/0009-0004-0137-6760"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyao Li","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7218,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86098872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"897","last_page":"903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.7903000116348267,"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":0.7903000116348267,"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":0.7771000266075134,"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"}},{"id":"https://openalex.org/T13890","display_name":"Remote Sensing and Land Use","score":0.6837000250816345,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833138465881348},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6551113128662109},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5941150784492493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5597965717315674},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5538071990013123},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5373861193656921},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.4652230441570282},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4635763466358185},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41969603300094604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2495722472667694},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13811573386192322},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10137847065925598}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833138465881348},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6551113128662109},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5941150784492493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5597965717315674},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5538071990013123},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5373861193656921},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4652230441570282},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4635763466358185},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41969603300094604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2495722472667694},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13811573386192322},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10137847065925598},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd61410.2024.10580205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd61410.2024.10580205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W639708223","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2176924101","https://openalex.org/W2193145675","https://openalex.org/W2531409750","https://openalex.org/W2752782242","https://openalex.org/W2962834855","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964979676","https://openalex.org/W2982770724","https://openalex.org/W3018757597","https://openalex.org/W3034971973","https://openalex.org/W3042011474","https://openalex.org/W3106250896","https://openalex.org/W3106808132","https://openalex.org/W3122050197","https://openalex.org/W3208154594","https://openalex.org/W3208826636","https://openalex.org/W4289752563","https://openalex.org/W4293584584","https://openalex.org/W4313007055","https://openalex.org/W4327785494","https://openalex.org/W4386075524","https://openalex.org/W6620707391","https://openalex.org/W6750227808","https://openalex.org/W6777046832","https://openalex.org/W6796538260","https://openalex.org/W6802878479"],"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/W2095903272","https://openalex.org/W2353265673"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,14,118],"object":[2,80,119],"detection":[3,71,81,133,196,218],"has":[4,205],"flourished":[5],"at":[6],"a":[7,103,153],"rapid":[8],"rate":[9],"of":[10,78,86,170,186],"development.":[11],"In":[12,58,135,201],"remote":[13,117],"images":[15,115],"(RSI),":[16],"most":[17],"algorithms":[18],"perform":[19,28],"well":[20],"in":[21,41,63],"detecting":[22,55],"medium":[23],"and":[24,45,112,151,175,181],"large":[25,56],"objects":[26,37],"but":[27,90],"poorly":[29],"on":[30,172],"small":[31,36,79],"objects.":[32,57],"This":[33],"is":[34,48,179,198],"because":[35],"occupy":[38],"fewer":[39,206],"pixels":[40],"the":[42,46,60,64,76,84,87,91,98,139,147,159,168,173,192,195],"entire":[43],"image,":[44],"detector":[47],"more":[49,128],"likely":[50],"to":[51,145,157,213],"be":[52],"biased":[53],"towards":[54],"addition,":[59,136,202],"huge":[61],"background":[62],"image":[65],"also":[66],"introduces":[67],"noise,":[68],"causing":[69],"many":[70],"failures.":[72],"Most":[73],"approaches":[74],"solve":[75,97],"problem":[77],"by":[82],"increasing":[83],"depth":[85],"neural":[88],"network,":[89],"results":[92,165],"are":[93],"not":[94],"satisfactory.":[95],"To":[96],"above":[99],"problems,":[100],"we":[101,125,137],"propose":[102],"new":[104,154],"method,":[105],"MF-YOLO,":[106],"that":[107,167],"utilizes":[108],"fused":[109],"infrared":[110],"(IR)":[111],"red-green-blue":[113],"(RGB)":[114],"for":[116],"detection.":[120],"Through":[121],"multimodal":[122],"fusion":[123],"(MF),":[124],"can":[126],"obtain":[127],"positive":[129],"information,":[130],"thereby":[131],"improving":[132],"accuracy.":[134],"introduced":[138],"Bi-Level":[140],"Routing":[141],"Attention":[142],"(BRA)":[143],"module":[144],"improve":[146],"YOLOv5s":[148],"model":[149,204],"structure,":[150],"proposed":[152],"loss":[155],"function":[156],"enhance":[158],"model\u2019s":[160],"learning":[161],"discrimination":[162],"ability.":[163],"Experimental":[164],"show":[166],"accuracy":[169,197],"MF-YOLO":[171],"VEDAI":[174],"NWPU":[176],"VHR-10":[177],"datasets":[178],"76.62%":[180],"91.63%":[182],"respectively":[183],"(in":[184],"terms":[185],"mAP<inf":[187],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">@0.5</inf>).":[189],"Compared":[190],"with":[191],"existing":[193],"state-of-the-art,":[194],"significantly":[199],"improved.":[200],"our":[203],"weight":[207],"parameters":[208],"than":[209],"YOLOv5s,":[210],"allowing":[211],"it":[212],"achieve":[214],"relatively":[215],"high":[216],"near-real-time":[217],"speed.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}