{"id":"https://openalex.org/W7124946832","doi":"https://doi.org/10.1109/access.2026.3656179","title":"A Lightweight Multi-Scale Attention Model for Small Object Detection in UAV Imagery","display_name":"A Lightweight Multi-Scale Attention Model for Small Object Detection in UAV Imagery","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124946832","doi":"https://doi.org/10.1109/access.2026.3656179"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3656179","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3656179","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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://doi.org/10.1109/access.2026.3656179","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123372107","display_name":"Dung Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095101","display_name":"Hue University","ror":"https://ror.org/00qaa6j11","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210095101"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dung Nguyen","raw_affiliation_strings":["University of Sciences, Hue University, Hue, Vietnam"],"raw_orcid":"https://orcid.org/0009-0000-4510-7504","affiliations":[{"raw_affiliation_string":"University of Sciences, Hue University, Hue, Vietnam","institution_ids":["https://openalex.org/I4210095101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123417481","display_name":"Van-Dung Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148201","display_name":"Ho Chi Minh City University of Technology and Engineering","ror":"https://ror.org/05hzn5427","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210148201"]},{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van-Dung Hoang","raw_affiliation_strings":["Faculty of Information Technology, Ho Chi Minh City University of Technology and Engineering, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0000-0001-7554-1707","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Ho Chi Minh City University of Technology and Engineering, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210148201","https://openalex.org/I47265099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105938018","display_name":"Van-Tuong-Lan Le","orcid":"https://orcid.org/0000-0002-0538-8425"},"institutions":[{"id":"https://openalex.org/I4210095101","display_name":"Hue University","ror":"https://ror.org/00qaa6j11","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210095101"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van-Tuong-Lan Le","raw_affiliation_strings":["Department of Academic and Students’ Affairs, Hue University, Hue, Vietnam"],"raw_orcid":"https://orcid.org/0009-0008-2687-5346","affiliations":[{"raw_affiliation_string":"Department of Academic and Students’ Affairs, Hue University, Hue, Vietnam","institution_ids":["https://openalex.org/I4210095101"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":7.2709,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93292732,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"14","issue":null,"first_page":"12579","last_page":"12593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9297000169754028,"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":0.9297000169754028,"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/T11133","display_name":"UAV Applications and Optimization","score":0.026799999177455902,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.0044999998062849045,"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":0.7648000121116638},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5978999733924866},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5613999962806702},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5411999821662903},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5286999940872192},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5019000172615051},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43939998745918274},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43720000982284546},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597000241279602},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7648000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6717000007629395},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43720000982284546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3481999933719635},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3418000042438507},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2775935494","wikidata":"https://www.wikidata.org/wiki/Q741964","display_name":"Search and rescue","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3656179","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3656179","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3656179","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3656179","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7379395961761475,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2962858109","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963346150","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2982220924","https://openalex.org/W2982770724","https://openalex.org/W2987761193","https://openalex.org/W2989611864","https://openalex.org/W2990763144","https://openalex.org/W3018757597","https://openalex.org/W3035396860","https://openalex.org/W3096609285","https://openalex.org/W3107867277","https://openalex.org/W3172752666","https://openalex.org/W3205100603","https://openalex.org/W3208645658","https://openalex.org/W3210586215","https://openalex.org/W4214627427","https://openalex.org/W4289752563","https://openalex.org/W4366598917","https://openalex.org/W4386076325","https://openalex.org/W4401246713","https://openalex.org/W4402754006","https://openalex.org/W4403770406","https://openalex.org/W4413222410","https://openalex.org/W4413277254","https://openalex.org/W4413816109","https://openalex.org/W4414404778","https://openalex.org/W4414499292","https://openalex.org/W4415178482"],"related_works":[],"abstract_inverted_index":{"Object":[0],"detection":[1,38,197,241],"in":[2,128,244],"Unmanned":[3],"Aerial":[4],"Vehicle":[5],"(UAV)":[6],"imagery":[7],"remains":[8],"a":[9,32,42,54,138,154,161,184,189,204,213],"challenging":[10,175],"task":[11],"due":[12],"to":[13,164],"the":[14,50,78,107,148,166,174,180,200,228],"presence":[15],"of":[16,61,80,169,186,191,208,217],"small":[17,124,247],"targets,":[18],"complex":[19],"backgrounds,":[20],"and":[21,34,70,83,104,188,211,234,248],"dense":[22],"object":[23,37,240],"distributions.":[24],"To":[25,132],"address":[26],"these":[27],"challenges,":[28],"this":[29],"study":[30],"introduces":[31],"lightweight":[33],"efficient":[35,236],"end-to-end":[36],"framework":[39,76],"enhanced":[40],"with":[41,114,147],"multi-scale":[43,112],"attention":[44],"mechanism.":[45],"The":[46],"proposed":[47,181,201,229],"architecture":[48],"enhances":[49],"backbone":[51],"by":[52,160],"integrating":[53],"multi-stage":[55],"attention-based":[56],"feature":[57],"refinement":[58],"strategy,":[59],"composed":[60],"Context":[62],"Modeling":[63],"Attention":[64,68,72],"(CMA),":[65],"Lightweight":[66],"Channel":[67],"(LCA),":[69],"Spatial":[71],"(SA).":[73],"This":[74],"hybrid":[75],"strengthens":[77],"representation":[79],"salient":[81],"regions":[82],"enriches":[84],"channel-wise":[85],"semantics":[86],"through":[87],"global":[88],"context":[89],"modeling,":[90],"while":[91],"simultaneously":[92],"suppressing":[93],"redundant":[94],"background":[95],"noise.":[96],"By":[97],"sequentially":[98],"refining":[99],"features":[100],"along":[101],"both":[102],"channel":[103],"spatial":[105],"dimensions,":[106],"network":[108],"captures":[109],"more":[110],"discriminative,":[111],"information":[113],"minimal":[115],"computational":[116,206],"overhead,":[117],"which":[118],"is":[119],"particularly":[120,243],"effective":[121,233],"for":[122,238],"detecting":[123],"or":[125],"occluded":[126],"objects":[127],"cluttered":[129],"UAV":[130,196],"environments.":[131],"enhance":[133],"model":[134,182],"generalization,":[135],"we":[136],"employ":[137],"robust":[139],"training":[140],"pipeline":[141],"that":[142,179,227],"integrates":[143],"advanced":[144],"data":[145],"augmentation":[146],"AdamW":[149],"optimizer.":[150],"We":[151],"also":[152],"implement":[153],"cosine":[155],"learning":[156],"rate":[157],"schedule,":[158],"preceded":[159],"warm-up":[162],"phase,":[163],"stabilize":[165],"early":[167],"stages":[168],"training.":[170],"Experimental":[171],"results":[172],"on":[173,220],"VisDrone2019":[176],"dataset":[177],"demonstrate":[178],"achieves":[183,212],"mAP@0.5":[185],"47.4%":[187],"mAP":[190],"29.0%,":[192],"outperforming":[193],"existing":[194],"state-of-the-art":[195],"models.":[198],"Additionally,":[199],"method":[202],"maintains":[203],"low":[205],"cost":[207],"28.566G":[209],"FLOPs":[210],"real-time":[214],"inference":[215],"speed":[216],"101":[218],"FPS":[219],"an":[221,232],"RTX":[222],"4090.":[223],"These":[224],"findings":[225],"confirm":[226],"approach":[230],"provides":[231],"computationally":[235],"solution":[237],"UAV-based":[239],"tasks,":[242],"scenarios":[245],"involving":[246],"densely":[249],"distributed":[250],"objects.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-21T00:00:00"}