{"id":"https://openalex.org/W4415680042","doi":"https://doi.org/10.1007/s11554-026-01898-w","title":"LEA-DETR: A Lightweight and Efficient Attention-Enhanced Model for UAV Object Detection","display_name":"LEA-DETR: A Lightweight and Efficient Attention-Enhanced Model for UAV Object Detection","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4415680042","doi":"https://doi.org/10.1007/s11554-026-01898-w"},"language":"en","primary_location":{"id":"doi:10.1007/s11554-026-01898-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11554-026-01898-w","pdf_url":null,"source":{"id":"https://openalex.org/S11282291","display_name":"Journal of Real-Time Image Processing","issn_l":"1861-8200","issn":["1861-8200","1861-8219"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Real-Time Image Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.preprints.org/frontend/manuscript/35124fe643cc108be6c369ecd9a499a7/download_pub","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092385184","display_name":"Ma Haohao","orcid":"https://orcid.org/0009-0001-6964-2357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohao Ma","raw_affiliation_strings":["State Key Laboratory of Submarine Geoscience, Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Submarine Geoscience, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098769848","display_name":"Mingliang Zuo","orcid":"https://orcid.org/0009-0005-0416-5907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingliang Zuo","raw_affiliation_strings":["State Key Laboratory of Submarine Geoscience, Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Submarine Geoscience, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113272535","display_name":"Qiqi Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiqi Ge","raw_affiliation_strings":["State Key Laboratory of Submarine Geoscience, Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Submarine Geoscience, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5113272535"],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2802147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.876800000667572,"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":0.876800000667572,"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":0.05550000071525574,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.009600000455975533,"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/object-detection","display_name":"Object detection","score":0.8015000224113464},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6588000059127808},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6446999907493591},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5332000255584717},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5252000093460083},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46779999136924744},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43070000410079956}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8015000224113464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626000046730042},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6588000059127808},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6446999907493591},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5332000255584717},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5252000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4440000057220459},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.3815000057220459},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3763999938964844},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C53073257","wikidata":"https://www.wikidata.org/wiki/Q7075021","display_name":"Object-oriented design","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11554-026-01898-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11554-026-01898-w","pdf_url":null,"source":{"id":"https://openalex.org/S11282291","display_name":"Journal of Real-Time Image Processing","issn_l":"1861-8200","issn":["1861-8200","1861-8219"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Real-Time Image Processing","raw_type":"journal-article"},{"id":"doi:10.20944/preprints202510.2237.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202510.2237.v1","pdf_url":"https://www.preprints.org/frontend/manuscript/35124fe643cc108be6c369ecd9a499a7/download_pub","source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202510.2237.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202510.2237.v1","pdf_url":"https://www.preprints.org/frontend/manuscript/35124fe643cc108be6c369ecd9a499a7/download_pub","source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415680042.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Object":[0],"detection":[1,53,67,201],"in":[2,175,202],"UAV":[3,36,65],"scenarios":[4],"has":[5],"emerged":[6],"as":[7,22],"a":[8,61,121,193],"highly":[9],"significant":[10],"yet":[11],"challenging":[12],"research":[13],"topic.":[14],"UAV-captured":[15],"images":[16],"often":[17],"suffer":[18],"from":[19],"issues":[20],"such":[21],"tiny":[23],"object":[24,30,66,111,200],"sizes":[25],"with":[26],"indistinct":[27],"features,":[28],"dense":[29],"distributions,":[31],"and":[32,45,51,63,144,159,168,195],"frequent":[33],"occlusions.":[34],"Additionally,":[35],"platforms":[37],"are":[38],"constrained":[39],"by":[40],"limited":[41],"onboard":[42],"computing":[43],"power":[44],"storage":[46],"capacity,":[47],"which":[48,128],"necessitates":[49],"lightweight":[50,62],"efficient":[52,64,98,196],"algorithms.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,75,95,119],"propose":[59],"LEA-DETR,":[60],"model":[68],"based":[69],"on":[70,147],"the":[71,85,130,148,156,164,183],"DETR":[72],"framework.":[73],"Specifically,":[74],"design":[76,120],"an":[77,97],"adaptive":[78],"sparse-dense":[79],"attention":[80],"fusion":[81],"module":[82],"to":[83,88,91,102],"enhance":[84],"model's":[86],"ability":[87],"selectively":[89],"attend":[90],"critical":[92],"features.":[93],"Furthermore,":[94],"introduce":[96],"multi-scale":[99],"convolutional":[100],"FPN":[101],"effectively":[103],"integrate":[104],"low-level":[105],"semantic":[106],"information,":[107],"particularly":[108],"for":[109,137,198],"small":[110],"detection.":[112],"To":[113],"further":[114],"improve":[115],"local":[116],"representation":[117],"capability,":[118],"novel":[122],"gated":[123],"inverted":[124],"bottleneck":[125],"convolution":[126],"module,":[127],"forms":[129],"core":[131],"of":[132,166],"our":[133],"newly":[134],"proposed":[135,157],"PG-Backbone":[136],"feature":[138],"extraction.":[139],"We":[140],"conduct":[141],"extensive":[142],"ablation":[143,152],"comparison":[145],"experiments":[146],"VisDrone2019":[149],"dataset.":[150],"The":[151],"results":[153],"demonstrate":[154],"that":[155,180],"LEA-DETR-S":[158],"LEA-DETR-M":[160],"models":[161],"significantly":[162],"reduce":[163],"number":[165],"parameters":[167],"computational":[169],"overhead":[170],"while":[171],"achieving":[172],"notable":[173],"improvements":[174],"accuracy.":[176],"Comparative":[177],"evaluations":[178],"show":[179],"LEA-DETR":[181],"achieves":[182],"best":[184],"overall":[185],"performance":[186],"among":[187],"all":[188],"evaluated":[189],"models,":[190],"making":[191],"it":[192],"practical":[194],"solution":[197],"UAV-based":[199],"real-world":[203],"scenarios.":[204]},"counts_by_year":[],"updated_date":"2026-07-07T14:30:12.667765","created_date":"2025-10-30T00:00:00"}