{"id":"https://openalex.org/W4416748912","doi":"https://doi.org/10.1109/iros60139.2025.11246176","title":"UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery","display_name":"UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748912","doi":"https://doi.org/10.1109/iros60139.2025.11246176"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5113755120","display_name":"Huaxiang Zhang","orcid":"https://orcid.org/0000-0001-6259-7533"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaxiang Zhang","raw_affiliation_strings":["Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396908","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-4364-6624"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092418742","display_name":"Kai Liu","orcid":"https://orcid.org/0009-0003-2419-2094"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Liu","raw_affiliation_strings":["Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103131528","display_name":"Zhongxue Gan","orcid":"https://orcid.org/0000-0003-1365-396X"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongxue Gan","raw_affiliation_strings":["Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050027236","display_name":"Guo\u2010Niu Zhu","orcid":"https://orcid.org/0000-0003-2421-740X"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo-Niu Zhu","raw_affiliation_strings":["Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,College of Intelligent Robotics and Advanced Manufacturing,China,200433","institution_ids":["https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":44.1142,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.99905367,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15143","last_page":"15149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7573999762535095,"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":0.7573999762535095,"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":0.1071000024676323,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.010700000450015068,"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/object-detection","display_name":"Object detection","score":0.6703000068664551},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.6650000214576721},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6001999974250793},{"id":"https://openalex.org/keywords/aerial-imagery","display_name":"Aerial imagery","score":0.5187000036239624},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.45649999380111694},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.40380001068115234},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3995000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494999766349792},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6703000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6662999987602234},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6650000214576721},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6126000285148621},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.45649999380111694},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27320000529289246},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2989611864","https://openalex.org/W3013211776","https://openalex.org/W3042011474","https://openalex.org/W3092151103","https://openalex.org/W3096609285","https://openalex.org/W3122799380","https://openalex.org/W3128774528","https://openalex.org/W3134040756","https://openalex.org/W3205100603","https://openalex.org/W4205248738","https://openalex.org/W4307823382","https://openalex.org/W4312823573","https://openalex.org/W4317727254","https://openalex.org/W4366421225","https://openalex.org/W4383753161","https://openalex.org/W4386072246","https://openalex.org/W4387197137","https://openalex.org/W4390872670","https://openalex.org/W4390873076","https://openalex.org/W4393150006","https://openalex.org/W4401414471","https://openalex.org/W4401415788","https://openalex.org/W4402754006","https://openalex.org/W4403770406","https://openalex.org/W4403847397","https://openalex.org/W7105700427"],"related_works":[],"abstract_inverted_index":{"Unmanned":[0],"aerial":[1],"vehicle":[2],"object":[3],"detection":[4,60],"(UAV-OD)":[5],"has":[6],"been":[7],"widely":[8],"used":[9],"in":[10],"various":[11,134],"scenarios.":[12],"However,":[13],"most":[14],"existing":[15],"UAV-OD":[16],"algorithms":[17],"rely":[18],"on":[19,33,159],"manually":[20,35],"designed":[21,36,40],"components,":[22],"which":[23,44,81],"require":[24],"extensive":[25],"tuning.":[26],"End-to-end":[27],"models":[28],"that":[29],"do":[30],"not":[31],"depend":[32],"such":[34,53],"components":[37],"are":[38,45,157],"mainly":[39],"for":[41,48,65],"natural":[42],"images,":[43],"less":[46],"effective":[47],"UAV":[49,66,135],"imagery.":[50],"To":[51],"address":[52],"challenges,":[54],"this":[55],"paper":[56],"proposes":[57],"an":[58],"efficient":[59],"transformer":[61],"(DETR)":[62],"framework":[63,71],"tailored":[64],"imagery,":[67],"i.e.,":[68],"UAV-DETR.":[69],"The":[70,163],"includes":[72],"a":[73,93],"multi-scale":[74],"feature":[75],"fusion":[76,121],"with":[77],"frequency":[78,86],"enhancement":[79],"module,":[80],"captures":[82],"both":[83],"spatial":[84,102],"and":[85,109,116,128,148],"information":[87],"at":[88,168],"different":[89,120],"scales.":[90],"In":[91],"addition,":[92],"frequency-focused":[94],"downsampling":[95],"module":[96,111],"is":[97,112,166],"presented":[98],"to":[99,114],"retain":[100],"critical":[101],"details":[103],"during":[104],"downsampling.":[105],"A":[106],"semantic":[107],"alignment":[108],"calibration":[110],"developed":[113],"align":[115],"fuse":[117],"features":[118],"from":[119],"paths.":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"the":[126,139,153,160],"effectiveness":[127],"generalization":[129],"of":[130],"our":[131,142],"approach":[132],"across":[133],"imagery":[136],"datasets.":[137],"On":[138],"VisDrone":[140],"dataset,":[141],"method":[143],"improves":[144],"AP":[145],"by":[146,150],"3.1%":[147],"AP50":[149],"4.2%":[151],"over":[152],"baseline.":[154],"Similar":[155],"enhancements":[156],"observed":[158],"UAVVaste":[161],"dataset.":[162],"project":[164],"page":[165],"available":[167],"https://github.com/ValiantDiligent/UAV-DETR.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":18}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}