{"id":"https://openalex.org/W4390738566","doi":"https://doi.org/10.1109/access.2024.3352601","title":"Object Detection of Remote Sensing Image Based on Multi-Scale Feature Fusion and Attention Mechanism","display_name":"Object Detection of Remote Sensing Image Based on Multi-Scale Feature Fusion and Attention Mechanism","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390738566","doi":"https://doi.org/10.1109/access.2024.3352601"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3352601","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3352601","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10388291.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10388291.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009376283","display_name":"Zhongkui Du","orcid":"https://orcid.org/0009-0003-1506-0276"},"institutions":[{"id":"https://openalex.org/I41208885","display_name":"Harbin University of Commerce","ror":"https://ror.org/03zsxkw25","country_code":"CN","type":"education","lineage":["https://openalex.org/I41208885"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuoqiang Du","raw_affiliation_strings":["School of Computer and Information Engineering, Harbin University of Commerce, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0003-1506-0276","affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Harbin University of Commerce, Harbin, China","institution_ids":["https://openalex.org/I41208885"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100390967","display_name":"Yuan Liang","orcid":"https://orcid.org/0009-0005-1426-2022"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Liang","raw_affiliation_strings":["Jinan Inspur Data Technology Company Ltd., Jinan, China"],"raw_orcid":"https://orcid.org/0009-0005-1426-2022","affiliations":[{"raw_affiliation_string":"Jinan Inspur Data Technology Company Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.805,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97457242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"8619","last_page":"8632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"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":0.9972000122070312,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9796000123023987,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9768999814987183,"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":0.8038973808288574},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.700710654258728},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.5963661074638367},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5911750197410583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5611906051635742},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5296342968940735},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5091592669487},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5052466988563538},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42291632294654846},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41784995794296265},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3608607053756714},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33311012387275696},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1658554971218109},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.12857192754745483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08464857935905457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038973808288574},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.700710654258728},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.5963661074638367},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5911750197410583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5611906051635742},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5296342968940735},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5091592669487},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5052466988563538},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42291632294654846},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41784995794296265},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3608607053756714},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33311012387275696},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1658554971218109},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.12857192754745483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08464857935905457},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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":2,"locations":[{"id":"doi:10.1109/access.2024.3352601","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3352601","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10388291.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c4aaa215616646c0a25572094c682cca","is_oa":true,"landing_page_url":"https://doaj.org/article/c4aaa215616646c0a25572094c682cca","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 8619-8632 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3352601","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3352601","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10388291.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3601016450","display_name":null,"funder_award_id":"UNPYSCT-2020212","funder_id":"https://openalex.org/F4320327728","funder_display_name":"University Nursing Program for Young Scholar with Creative Talents in Heilongjiang Province"},{"id":"https://openalex.org/G4681100502","display_name":null,"funder_award_id":"606750192","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"},{"id":"https://openalex.org/F4320327728","display_name":"University Nursing Program for Young Scholar with Creative Talents in Heilongjiang Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390738566.pdf","grobid_xml":"https://content.openalex.org/works/W4390738566.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2016461833","https://openalex.org/W2037227137","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2112796928","https://openalex.org/W2139212933","https://openalex.org/W2161969291","https://openalex.org/W2163352848","https://openalex.org/W2193145675","https://openalex.org/W2570343428","https://openalex.org/W2618530766","https://openalex.org/W2630837129","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2896732967","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963840672","https://openalex.org/W2963849369","https://openalex.org/W2964236837","https://openalex.org/W2965372422","https://openalex.org/W2966926453","https://openalex.org/W3005533314","https://openalex.org/W3016641475","https://openalex.org/W3018757597","https://openalex.org/W3034552520","https://openalex.org/W3034993937","https://openalex.org/W3042011474","https://openalex.org/W3101677789","https://openalex.org/W3106250896","https://openalex.org/W3128672628","https://openalex.org/W3134896931","https://openalex.org/W3136715451","https://openalex.org/W3177349073","https://openalex.org/W3201009223","https://openalex.org/W4200017494","https://openalex.org/W4205762292","https://openalex.org/W4293584584","https://openalex.org/W4320026650","https://openalex.org/W4379385793","https://openalex.org/W4379470079","https://openalex.org/W6696085341","https://openalex.org/W6750227808","https://openalex.org/W6766052331","https://openalex.org/W6766242540","https://openalex.org/W6777046832"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W4310746709","https://openalex.org/W3149642877","https://openalex.org/W3215923428","https://openalex.org/W4328027016","https://openalex.org/W4378677003"],"abstract_inverted_index":{"In":[0],"view":[1],"of":[2,9,28,33,54,60,67,166,176,205,212,223,232,245,276,294,308],"the":[3,26,29,34,40,46,56,61,65,142,151,156,162,167,174,182,199,210,221,233,240,246,261,266,295,301,309,312],"small":[4],"size":[5,244],"and":[6,38,93,99,160,209,226,239,242,289,311],"dense":[7],"distribution":[8],"remote":[10,255,277],"sensing":[11,256,278],"image":[12,257],"targets,":[13],"this":[14],"paper":[15],"adds":[16],"a":[17,104,131,189],"detection":[18,31,117,230,259,271,285,313],"head":[19],"P2":[20],"specifically":[21],"for":[22,115,185,194,273],"small-scale":[23,62,274],"targets":[24,275],"on":[25,198],"basis":[27],"three":[30],"layers":[32],"original":[35,296],"YOLOv5":[36],"model,":[37],"involves":[39],"shallow":[41],"high-resolution":[42],"feature":[43,49,58,77,110,163,200],"map":[44],"in":[45,64,170],"subsequent":[47],"multi-scale":[48,76],"fusion":[50,78],"module.":[51],"The":[52,84,202,229,284],"problem":[53,175],"losing":[55],"key":[57],"information":[59,114,140],"target":[63,183],"process":[66],"multiple":[68],"downsampling":[69],"is":[70,82,87,207,216,236,315],"effectively":[71,249],"avoided.":[72],"Firstly,":[73],"an":[74,122],"enhanced":[75],"pyramid":[79],"network":[80,86,116,190,225,235,247],"DSI-FPN":[81],"designed.":[83],"FPN+PAN":[85],"optimized":[88],"by":[89,219],"using":[90],"DepthwiseSparable":[91],"Convolution":[92],"Involution":[94],"operators":[95],"with":[96,112,253],"fewer":[97],"parameters":[98,241,303],"computations,":[100],"as":[101,103],"well":[102],"spatial":[105,125],"attention":[106,126],"mechanism":[107,127,133],"to":[108,137,141,172,306],"generate":[109],"graphs":[111],"richer":[113],"tasks.":[118],"Secondly,":[119],"we":[120,187],"propose":[121,188],"adaptive":[123],"channel":[124],"SCBAM,":[128],"which":[129],"introduces":[130],"self-attention":[132],"into":[134],"CBAM":[135],"module":[136],"add":[138],"non-local":[139],"interaction":[143],"that":[144,265,293],"originally":[145],"had":[146],"only":[147],"local":[148],"information,":[149],"breaks":[150],"convolution":[152],"kernel":[153],"limit,":[154],"expands":[155],"model":[157,243,302],"receptive":[158],"field,":[159],"improves":[161],"expression":[164],"ability":[165],"model.":[168,297],"Thirdly,":[169],"order":[171],"solve":[173],"insufficient":[177],"computing":[178],"power":[179],"when":[180],"deploying":[181],"detector":[184],"equipment,":[186],"knowledge":[191,299],"distillation":[192,203],"framework":[193],"joint":[195],"teachers":[196],"based":[197],"layer.":[201],"loss":[204],"teacher":[206,224],"designed,":[208],"trend":[211],"student":[213,234],"online":[214],"learning":[215],"adjusted":[217],"dynamically":[218],"balancing":[220],"contributions":[222],"truth":[227],"value.":[228],"accuracy":[231,286,314],"obviously":[237],"improved,":[238],"are":[248,304],"reduced.":[250],"Finally,":[251],"Comparing":[252],"other":[254],"object":[258],"methods,":[260],"experimental":[262],"results":[263],"show":[264],"approach":[267],"presented":[268],"has":[269],"better":[270],"effect":[272],"images":[279],"under":[280],"different":[281],"lighting":[282],"conditions.":[283],"reached":[287],"43.9%,":[288],"7.4%":[290],"higher":[291],"than":[292],"After":[298],"distillation,":[300],"reduced":[305],"1/3":[307],"original,":[310],"40.2%.":[316]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}