{"id":"https://openalex.org/W7148491217","doi":"https://doi.org/10.1093/jcde/qwag037","title":"UMS-DET: A frequency-enhanced transformer-based UAV multi-scale small object detector for aerial imagery","display_name":"UMS-DET: A frequency-enhanced transformer-based UAV multi-scale small object detector for aerial imagery","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148491217","doi":"https://doi.org/10.1093/jcde/qwag037"},"language":"en","primary_location":{"id":"doi:10.1093/jcde/qwag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jcde/qwag037","pdf_url":null,"source":{"id":"https://openalex.org/S2485147958","display_name":"Journal of Computational Design and Engineering","issn_l":"2288-4300","issn":["2288-4300","2288-5048"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Design and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/jcde/qwag037","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015720040","display_name":"Wenxiu Hu","orcid":"https://orcid.org/0000-0001-6215-6527"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Hu","raw_affiliation_strings":["School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications , No. 10 Xitucheng Road, Haidian District, Beijing 100876 ,"],"raw_orcid":"https://orcid.org/0009-0003-5591-2103","affiliations":[{"raw_affiliation_string":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications , No. 10 Xitucheng Road, Haidian District, Beijing 100876 ,","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022412408","display_name":"Feixiang Du","orcid":"https://orcid.org/0000-0002-2769-5418"},"institutions":[{"id":"https://openalex.org/I4210159152","display_name":"Tongling University","ror":"https://ror.org/04kqvjg13","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210159152"]},{"id":"https://openalex.org/I96413208","display_name":"Swinburne University of Technology Sarawak Campus","ror":"https://ror.org/014cjmc76","country_code":"MY","type":"education","lineage":["https://openalex.org/I57093077","https://openalex.org/I96413208"]}],"countries":["CN","MY"],"is_corresponding":true,"raw_author_name":"Feixiang Du","raw_affiliation_strings":["Faculty of Engineering, Computing and Science, Swinburne University of Technology , Sarawak Campus, Kuching 93350 ,","School of Electrical Engineering, Tongling University , No.1335 Cuihu 4th Road, Tongling, Anhui 244061 ,"],"raw_orcid":"https://orcid.org/0000-0002-2769-5418","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Computing and Science, Swinburne University of Technology , Sarawak Campus, Kuching 93350 ,","institution_ids":["https://openalex.org/I96413208"]},{"raw_affiliation_string":"School of Electrical Engineering, Tongling University , No.1335 Cuihu 4th Road, Tongling, Anhui 244061 ,","institution_ids":["https://openalex.org/I4210159152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132820618","display_name":"Xiaodong Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodong Qin","raw_affiliation_strings":["School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications , No. 10 Xitucheng Road, Haidian District, Beijing 100876 ,"],"raw_orcid":"https://orcid.org/0009-0003-9353-7658","affiliations":[{"raw_affiliation_string":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications , No. 10 Xitucheng Road, Haidian District, Beijing 100876 ,","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132779952","display_name":"Joel C M Than","orcid":null},"institutions":[{"id":"https://openalex.org/I96413208","display_name":"Swinburne University of Technology Sarawak Campus","ror":"https://ror.org/014cjmc76","country_code":"MY","type":"education","lineage":["https://openalex.org/I57093077","https://openalex.org/I96413208"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Joel C M Than","raw_affiliation_strings":["Faculty of Engineering, Computing and Science, Swinburne University of Technology , Sarawak Campus, Kuching 93350 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Computing and Science, Swinburne University of Technology , Sarawak Campus, Kuching 93350 ,","institution_ids":["https://openalex.org/I96413208"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015720040","https://openalex.org/A5022412408","https://openalex.org/A5132779952","https://openalex.org/A5132820618"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210159152","https://openalex.org/I96413208"],"apc_list":{"value":1650,"currency":"USD","value_usd":1650},"apc_paid":{"value":1650,"currency":"USD","value_usd":1650},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38312279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"4","first_page":"290","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6692000031471252,"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":0.6692000031471252,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.025100000202655792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.021700000390410423,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/robustness","display_name":"Robustness (evolution)","score":0.7494000196456909},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5997999906539917},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5891000032424927},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5081999897956848},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4986000061035156},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42579999566078186},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4131999909877777}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7494000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7264999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6075000166893005},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5997999906539917},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5891000032424927},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4986000061035156},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4490000009536743},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C86369673","wikidata":"https://www.wikidata.org/wiki/Q1203659","display_name":"Simultaneous localization and mapping","level":4,"score":0.2912999987602234},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/jcde/qwag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jcde/qwag037","pdf_url":null,"source":{"id":"https://openalex.org/S2485147958","display_name":"Journal of Computational Design and Engineering","issn_l":"2288-4300","issn":["2288-4300","2288-5048"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Design and Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1093/jcde/qwag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jcde/qwag037","pdf_url":null,"source":{"id":"https://openalex.org/S2485147958","display_name":"Journal of Computational Design and Engineering","issn_l":"2288-4300","issn":["2288-4300","2288-5048"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Design and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7120321393013,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4176370834","display_name":null,"funder_award_id":"No.2024AH051852","funder_id":"https://openalex.org/F4320335406","funder_display_name":"University Natural Science Research Project of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320335406","display_name":"University Natural Science Research Project of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W3210720059","https://openalex.org/W4210598935","https://openalex.org/W4220834484","https://openalex.org/W4313591362","https://openalex.org/W4389977645","https://openalex.org/W4393185921","https://openalex.org/W4401630652","https://openalex.org/W4401887491","https://openalex.org/W4401894250","https://openalex.org/W4403193080","https://openalex.org/W4404523069","https://openalex.org/W4406610484","https://openalex.org/W4413972565","https://openalex.org/W4414318847","https://openalex.org/W4415749638","https://openalex.org/W4416098845","https://openalex.org/W7138942089"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Small":[1,120],"object":[2,50,194],"detection":[3],"in":[4,52,159,191],"UAV":[5,53,206],"(Unmanned":[6,34],"Aerial":[7,35,160],"Vehicle)":[8],"aerial":[9],"imagery":[10],"faces":[11],"significant":[12],"challenges,":[13],"including":[14],"insufficient":[15],"feature":[16,66],"representation,":[17],"severe":[18],"background":[19,107],"noise":[20,108],"interference,":[21],"and":[22,48,73,109,149,154,172,189,196,202],"inadequate":[23],"multi-scale":[24,46,65,137],"fusion.":[25],"To":[26],"address":[27],"these":[28],"issues,":[29],"this":[30],"study":[31],"proposes":[32],"UMS-DET":[33,143],"Vehicle":[36],"Multi-scale":[37],"Small-object":[38],"Detector),":[39],"a":[40,174],"specialized":[41],"framework":[42],"engineered":[43],"to":[44,104,131],"optimize":[45],"representation":[47,67],"small":[49,114,193],"discrimination":[51],"views.":[54],"Firstly,":[55],"we":[56,85,117],"design":[57],"the":[58,81,87,119,152,166],"Multi-Scale":[59],"Context-Gated":[60],"Network":[61],"backbone,":[62],"which":[63,126],"strengthens":[64],"through":[68],"hierarchical":[69],"context":[70],"synergy":[71],"aggregation":[72],"adaptive":[74],"gated":[75],"fusion":[76],"mechanisms,":[77],"all":[78],"while":[79],"reducing":[80],"parameter":[82],"count.":[83],"Subsequently,":[84],"introduce":[86],"Sparse":[88],"Hierarchical":[89],"Frequency":[90],"Feature":[91,123],"Interaction":[92],"encoder.":[93],"This":[94],"module":[95],"integrates":[96],"sparse":[97],"window":[98],"attention":[99],"with":[100],"frequency-domain":[101],"enhancement":[102],"techniques":[103],"effectively":[105],"suppress":[106],"improve":[110],"discriminative":[111],"capability":[112],"for":[113,156,205],"targets.":[115],"Furthermore,":[116],"propose":[118],"Object-Focused":[121],"Cross-scale":[122],"Fusion":[124],"module,":[125],"leverages":[127],"high-resolution":[128],"shallow":[129],"features":[130],"preserve":[132],"fine-grained":[133],"details,":[134],"facilitating":[135],"effective":[136],"integration.":[138],"Experimental":[139],"results":[140],"demonstrate":[141],"that":[142],"achieves":[144,173],"AP$_{50}$":[145],"improvements":[146],"of":[147,178],"5.2%":[148],"3.0%":[150],"on":[151],"VisDrone":[153],"Dataset":[155],"Object":[157],"deTection":[158],"images":[161],"(DOTA)":[162],"datasets,":[163],"respectively.":[164],"Notably,":[165],"model":[167],"reduces":[168],"parameters":[169],"by":[170],"22.1%":[171],"real-time":[175],"inference":[176],"speed":[177],"67.3":[179],"Frames":[180],"Per":[181],"Second.":[182],"The":[183],"proposed":[184],"method":[185],"exhibits":[186],"superior":[187],"accuracy":[188],"robustness":[190],"dense":[192],"scenarios":[195],"complex":[197],"environments,":[198],"offering":[199],"an":[200],"efficient":[201],"practical":[203],"solution":[204],"intelligent":[207],"perception":[208],"systems.":[209]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-04-03T00:00:00"}