{"id":"https://openalex.org/W4327521163","doi":"https://doi.org/10.1145/3573428.3573449","title":"Multi-scale Fusion based Multi-stage Small Object Detection in Aerial Images \u2217","display_name":"Multi-scale Fusion based Multi-stage Small Object Detection in Aerial Images \u2217","publication_year":2022,"publication_date":"2022-10-21","ids":{"openalex":"https://openalex.org/W4327521163","doi":"https://doi.org/10.1145/3573428.3573449"},"language":"en","primary_location":{"id":"doi:10.1145/3573428.3573449","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","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/A5084821708","display_name":"Mingrui Yang","orcid":"https://orcid.org/0000-0003-2995-9808"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210091786","display_name":"State Key Laboratory on Integrated Optoelectronics","ror":"https://ror.org/00g102351","country_code":"CN","type":"facility","lineage":["https://openalex.org/I194450716","https://openalex.org/I19820366","https://openalex.org/I4210091786","https://openalex.org/I4210149211","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Yang","raw_affiliation_strings":["State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, China"],"raw_orcid":"https://orcid.org/0000-0003-2995-9808","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, China","institution_ids":["https://openalex.org/I4210091786","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101553529","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-5597-9074"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210091786","display_name":"State Key Laboratory on Integrated Optoelectronics","ror":"https://ror.org/00g102351","country_code":"CN","type":"facility","lineage":["https://openalex.org/I194450716","https://openalex.org/I19820366","https://openalex.org/I4210091786","https://openalex.org/I4210149211","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, China"],"raw_orcid":"https://orcid.org/0000-0001-5597-9074","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, China","institution_ids":["https://openalex.org/I4210091786","https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101494067","display_name":"Xindong Zhang","orcid":"https://orcid.org/0000-0001-6840-9222"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210091786","display_name":"State Key Laboratory on Integrated Optoelectronics","ror":"https://ror.org/00g102351","country_code":"CN","type":"facility","lineage":["https://openalex.org/I194450716","https://openalex.org/I19820366","https://openalex.org/I4210091786","https://openalex.org/I4210149211","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xindong Zhang","raw_affiliation_strings":["State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, China"],"raw_orcid":"https://orcid.org/0000-0001-6840-9222","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, China","institution_ids":["https://openalex.org/I4210091786","https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15849235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.998199999332428,"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":0.9966999888420105,"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/object-detection","display_name":"Object detection","score":0.8204950094223022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7884662747383118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7796890735626221},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.7090014219284058},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6716951727867126},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6324182748794556},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.597644567489624},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5541967153549194},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.5476239919662476},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5395902395248413},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5221866965293884},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5174142122268677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48458826541900635},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.46183112263679504},{"id":"https://openalex.org/keywords/aerial-imagery","display_name":"Aerial imagery","score":0.45623186230659485},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39105069637298584},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.13896775245666504},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0875958502292633},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07664120197296143},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06445097923278809}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8204950094223022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884662747383118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7796890735626221},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.7090014219284058},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6716951727867126},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6324182748794556},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.597644567489624},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5541967153549194},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.5476239919662476},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5395902395248413},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5221866965293884},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5174142122268677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48458826541900635},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.46183112263679504},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.45623186230659485},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39105069637298584},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.13896775245666504},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0875958502292633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07664120197296143},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06445097923278809},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573428.3573449","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","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":16,"referenced_works":["https://openalex.org/W2601564443","https://openalex.org/W2613718673","https://openalex.org/W2769221444","https://openalex.org/W2896122241","https://openalex.org/W2946948417","https://openalex.org/W2962677013","https://openalex.org/W2963351448","https://openalex.org/W2990268359","https://openalex.org/W2992240579","https://openalex.org/W3092220690","https://openalex.org/W4234552385","https://openalex.org/W4301409532","https://openalex.org/W6735463952","https://openalex.org/W6743731764","https://openalex.org/W6750227808","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2922421953","https://openalex.org/W2557461402","https://openalex.org/W2095705906","https://openalex.org/W2975200075","https://openalex.org/W1971759388","https://openalex.org/W2223320490","https://openalex.org/W2129974284","https://openalex.org/W2021186063","https://openalex.org/W2404567486","https://openalex.org/W3160733999"],"abstract_inverted_index":{"In":[0,134],"aerial":[1,41,57,81,148,164],"images,":[2],"the":[3,15,25,32,65,137,158],"objects":[4,11,30,106],"are":[5],"mostly":[6],"small.":[7],"The":[8,35],"number":[9],"of":[10,27,38,67],"is":[12,17,21,43,83,111,122],"large":[13],"and":[14,62,95,129],"scale":[16,29],"diverse,":[18],"so":[19],"it":[20,47],"difficult":[22,48],"to":[23,49,56,100,113,125],"extract":[24],"features":[26,116],"multiple":[28],"at":[31],"same":[33],"time.":[34],"location":[36],"distribution":[37],"object":[39,59,76,143,160],"in":[40,85,131,163],"images":[42,82,165],"usually":[44],"dense,":[45],"making":[46],"locate.":[50],"These":[51],"factors":[52],"bring":[53],"great":[54],"challenges":[55],"image":[58,149],"feature":[60,92],"extraction,":[61],"then":[63],"reduce":[64,126],"performance":[66,104],"detection.":[68],"Therefore,":[69],"a":[70],"multi-scale":[71,115],"fusion":[72],"based":[73],"multi-stage":[74],"small":[75,159],"detection":[77,103,120,128,144,161],"method":[78],"(MSMSD)":[79],"for":[80],"proposed":[84,138],"this":[86,132],"paper.":[87],"MSMSD":[88,139,155],"adopts":[89],"EfficientNet":[90],"as":[91],"extraction":[93],"backbone":[94],"add":[96],"deformable":[97],"convolution":[98],"blocks":[99],"achieve":[101],"better":[102],"on":[105,146],"with":[107],"irregular":[108],"shapes.":[109],"NAS-FPN":[110],"leveraged":[112],"fuse":[114],"effectively.":[117],"A":[118],"cascade":[119],"mechanism":[121],"also":[123],"designed":[124],"noisy":[127],"mis-detection":[130],"task.":[133],"experiment":[135],"section,":[136],"outperforms":[140],"five":[141],"benchmark":[142],"algorithms":[145],"two":[147],"datasets.":[150],"Experimental":[151],"results":[152],"demonstrate":[153],"that":[154],"can":[156],"handle":[157],"task":[162],"efficiently.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}