{"id":"https://openalex.org/W2996735448","doi":"https://doi.org/10.1109/iccvw.2019.00020","title":"Dense and Small Object Detection in UAV Vision Based on Cascade Network","display_name":"Dense and Small Object Detection in UAV Vision Based on Cascade Network","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2996735448","doi":"https://doi.org/10.1109/iccvw.2019.00020","mag":"2996735448"},"language":"en","primary_location":{"id":"doi:10.1109/iccvw.2019.00020","doi":"https://doi.org/10.1109/iccvw.2019.00020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw.2019.00020","pdf_url":null,"source":{"id":"https://openalex.org/S4393918695","display_name":"IEEE International Conference on Computer Vision Workshops","issn_l":"2473-9936","issn":["2473-9936"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101788266","display_name":"Xindi Zhang","orcid":"https://orcid.org/0000-0003-2587-6415","observed_orcids":["https://orcid.org/0000-0003-2587-6415"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xindi Zhang","raw_affiliation_strings":["Multimedia and Vision Research Group, School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia and Vision Research Group, School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058530878","display_name":"Ebroul Izquierdo M.","orcid":"https://orcid.org/0000-0002-7142-3970","observed_orcids":["https://orcid.org/0000-0002-7142-3970"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ebroul Izquierdo","raw_affiliation_strings":["Multimedia and Vision Research Group, School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia and Vision Research Group, School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065549868","display_name":"Krishna Chandramouli","orcid":"https://orcid.org/0000-0001-5850-9799","observed_orcids":["https://orcid.org/0000-0001-5850-9799"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishna Chandramouli","raw_affiliation_strings":["Venaka Media Limited, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Venaka Media Limited, London, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5057,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.92924021,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":9.999999747378752e-05,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":9.999999747378752e-05,"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/small-object-detection","display_name":"small object detection","score":0.8849999904632568},{"id":"https://openalex.org/keywords/dense-object-detection","display_name":"dense object detection","score":0.9539999961853027},{"id":"https://openalex.org/keywords/uav-video","display_name":"UAV video","score":0.6779999732971191},{"id":"https://openalex.org/keywords/uav-imagery","display_name":"UAV imagery","score":0.4620000123977661},{"id":"https://openalex.org/keywords/cascaded-networks","display_name":"cascaded networks","score":0.4050000011920929},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8830000162124634},{"id":"https://openalex.org/keywords/multi-model-fusion","display_name":"multi-model fusion","score":0.8790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063804507255554},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.6481682062149048},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6456714272499084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6421184539794922},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5947760939598083},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5680863857269287},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5433706641197205},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.5197912454605103},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.49507537484169006},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4604170620441437},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.44185951352119446},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4273568093776703},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41497987508773804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29236143827438354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18200814723968506},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14086779952049255},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw.2019.00020","doi":"https://doi.org/10.1109/iccvw.2019.00020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw.2019.00020","pdf_url":null,"source":{"id":"https://openalex.org/S4393918695","display_name":"IEEE International Conference on Computer Vision Workshops","issn_l":"2473-9936","issn":["2473-9936"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.428600013256073,"id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1483870316","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2286929393","https://openalex.org/W2341497066","https://openalex.org/W2407521645","https://openalex.org/W2557728737","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2743706233","https://openalex.org/W2768489488","https://openalex.org/W2769291631","https://openalex.org/W2797527871","https://openalex.org/W2798799804","https://openalex.org/W2886335102","https://openalex.org/W2899771611","https://openalex.org/W2913012218","https://openalex.org/W2950141105","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963786238","https://openalex.org/W2963849369","https://openalex.org/W2963857746","https://openalex.org/W2964241181","https://openalex.org/W2988452521","https://openalex.org/W2988916019","https://openalex.org/W2997408160","https://openalex.org/W3012573144","https://openalex.org/W3106250896","https://openalex.org/W3119129845","https://openalex.org/W6759051463"],"related_works":["https://openalex.org/W3113752395","https://openalex.org/W4396712957","https://openalex.org/W7158729268","https://openalex.org/W7125981531","https://openalex.org/W7210284918","https://openalex.org/W4392945389","https://openalex.org/W7167031581","https://openalex.org/W4394010234","https://openalex.org/W7162775616","https://openalex.org/W4417056468"],"abstract_inverted_index":{"With":[0],"the":[1,31,37,49,65,88,118,129,173,183],"development":[2],"of":[3,14,45,51,57,64,98,120,128,145,172],"Unmanned":[4],"Aerial":[5],"Vehicles,":[6],"drones":[7,35],"are":[8],"being":[9],"deployed":[10],"in":[11,55,93,178,186],"a":[12,76,106],"number":[13],"commercial":[15],"and":[16,24,69,96,141,168],"civil":[17],"government":[18],"applications":[19],"ranging":[20],"from":[21],"remote":[22],"surveillance":[23],"infrastructure":[25],"maintenance":[26],"among":[27],"others.":[28],"However,":[29],"processing":[30,108],"videos":[32,89],"captured":[33,66],"by":[34,43],"for":[36,165],"extracting":[38],"meaningful":[39],"information":[40],"is":[41,75,83],"hindered":[42],"multitude":[44],"challenges":[46],"that":[47,82,90,110],"include,":[48],"appearance":[50],"small":[52,99],"objects,":[53,59],"changes":[54],"viewpoint":[56],"these":[58,72],"illumination":[60],"changes,":[61],"large-scale":[62],"resolution":[63],"video,":[67],"occlusion":[68],"truncation.":[70],"Addressing":[71],"challenges,":[73],"there":[74],"critical":[77],"need":[78],"to":[79,85],"develop":[80],"algorithms":[81],"able":[84],"efficiently":[86],"process":[87,136],"can":[91],"result":[92],"robust":[94],"detection":[95,147,159],"recognition":[97],"objects.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104],"propose":[105],"novel":[107],"pipeline,":[109],"brings":[111],"together":[112],"several":[113],"key":[114],"contributions":[115],"including":[116],"(i)":[117],"introduction":[119],"DeForm":[121],"convolution":[122],"layers":[123],"within":[124],"backbone;":[125],"(ii)":[126],"use":[127],"interleaved":[130],"cascade":[131],"architecture;":[132],"(iii)":[133],"data":[134],"augmentation":[135],"based":[137],"on":[138,182],"crop":[139],"functionality":[140],"(iv)":[142],"multi-model":[143],"fusion":[144],"sub-category":[146],"networks.":[148],"The":[149,170],"proposed":[150,174],"approach":[151,175],"has":[152,176],"been":[153],"exhaustively":[154],"benchmarked":[155],"against":[156],"VisDrone-DET":[157,187],"object":[158],"dataset,":[160],"which":[161],"includes":[162],"10,209":[163],"images":[164],"training,":[166],"validation":[167],"testing.":[169],"evaluation":[171],"resulted":[177],"22.61":[179],"average":[180],"precision":[181],"test-challenge":[184],"set":[185],"2019.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2019-12-26T00:00:00"}