{"id":"https://openalex.org/W4313564308","doi":"https://doi.org/10.1109/icit48603.2022.10002808","title":"HCD-Mask: a multi-task model for small object detection and instance segmentation in high-resolution UAV images","display_name":"HCD-Mask: a multi-task model for small object detection and instance segmentation in high-resolution UAV images","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4313564308","doi":"https://doi.org/10.1109/icit48603.2022.10002808"},"language":"en","primary_location":{"id":"doi:10.1109/icit48603.2022.10002808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit48603.2022.10002808","pdf_url":null,"source":{"id":"https://openalex.org/S4363608411","display_name":"2022 IEEE International Conference on Industrial Technology (ICIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Industrial Technology (ICIT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100426184","display_name":"Qun Li","orcid":"https://orcid.org/0000-0003-2231-6615"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qun Li","raw_affiliation_strings":["Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657908","display_name":"Mingshan Sun","orcid":"https://orcid.org/0000-0002-0785-7387"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingshan Sun","raw_affiliation_strings":["Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659911","display_name":"Dong Li","orcid":"https://orcid.org/0000-0001-7369-1445"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Dong","raw_affiliation_strings":["Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003491781","display_name":"Xiao\u2010Zhi Gao","orcid":"https://orcid.org/0000-0002-0078-5675"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210115759","display_name":"Eastern Finland Laboratory Center","ror":"https://ror.org/01zcq6z67","country_code":"FI","type":"facility","lineage":["https://openalex.org/I4210115759"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaozhi Gao","raw_affiliation_strings":["University of Eastern Finland,Department of Computing,Kuopio,Finland","Department of Computing, University of Eastern Finland, Kuopio, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland,Department of Computing,Kuopio,Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210115759"]},{"raw_affiliation_string":"Department of Computing, University of Eastern Finland, Kuopio, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614110","display_name":"Zenghui Wang","orcid":"https://orcid.org/0000-0003-3025-336X"},"institutions":[{"id":"https://openalex.org/I165390105","display_name":"University of South Africa","ror":"https://ror.org/048cwvf49","country_code":"ZA","type":"education","lineage":["https://openalex.org/I165390105"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Zenghui Wang","raw_affiliation_strings":["University of South Africa,Deparment of Electrical and Mining Engineering,Florida,South Africa,1709"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Africa,Deparment of Electrical and Mining Engineering,Florida,South Africa,1709","institution_ids":["https://openalex.org/I165390105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458457","display_name":"Haijun Zhang","orcid":"https://orcid.org/0000-0002-1648-0227"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Zhang","raw_affiliation_strings":["Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Computer Science,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9980999827384949,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.806697428226471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8036726713180542},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7316008806228638},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.648505449295044},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6390061974525452},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5347292423248291},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5154134035110474},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5077860951423645},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.45994824171066284},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.44376686215400696},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4285505414009094},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42515718936920166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3690186142921448},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.12935298681259155},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0927225649356842},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.083609938621521}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.806697428226471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036726713180542},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7316008806228638},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.648505449295044},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6390061974525452},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5347292423248291},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5154134035110474},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5077860951423645},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.45994824171066284},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.44376686215400696},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4285505414009094},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42515718936920166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3690186142921448},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.12935298681259155},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0927225649356842},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.083609938621521},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit48603.2022.10002808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit48603.2022.10002808","pdf_url":null,"source":{"id":"https://openalex.org/S4363608411","display_name":"2022 IEEE International Conference on Industrial Technology (ICIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Industrial Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1530236255","https://openalex.org/W1861492603","https://openalex.org/W1905829557","https://openalex.org/W2006588449","https://openalex.org/W2031489346","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2165139660","https://openalex.org/W2176924101","https://openalex.org/W2193145675","https://openalex.org/W2304578911","https://openalex.org/W2314029052","https://openalex.org/W2400138547","https://openalex.org/W2480078828","https://openalex.org/W2537801681","https://openalex.org/W2570343428","https://openalex.org/W2606788270","https://openalex.org/W2612465689","https://openalex.org/W2613825824","https://openalex.org/W2618530766","https://openalex.org/W2902184095","https://openalex.org/W2910778976","https://openalex.org/W2913508739","https://openalex.org/W2940262938","https://openalex.org/W2962749812","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963786238","https://openalex.org/W2963881378","https://openalex.org/W3106250896","https://openalex.org/W4293584584","https://openalex.org/W6620707391","https://openalex.org/W6750227808","https://openalex.org/W6756314655","https://openalex.org/W6761630670"],"related_works":["https://openalex.org/W2348909947","https://openalex.org/W4292672442","https://openalex.org/W2362101859","https://openalex.org/W2791431590","https://openalex.org/W2941610985","https://openalex.org/W4235810826","https://openalex.org/W3000105423","https://openalex.org/W2350688482","https://openalex.org/W2122135111","https://openalex.org/W2053575972"],"abstract_inverted_index":{"Object":[0],"detection":[1,29,116],"and":[2,39,84,153,169],"instance":[3],"segmentation":[4],"in":[5,33,42,89,117,158],"images":[6,44,59],"captured":[7],"by":[8,151,187,197],"unmanned":[9],"aerial":[10,43],"vehicles":[11],"(UAVs)":[12],"are":[13,45,60,76,86,173],"becoming":[14],"increasingly":[15],"important.":[16],"Although":[17],"considerable":[18],"progress":[19],"has":[20],"been":[21],"made,":[22],"there":[23],"still":[24],"exist":[25],"challenges":[26],"for":[27,47,113,176],"the":[28,52,71,132,144,166,170,181],"of":[30,73,183],"small":[31,74,88,114],"objects":[32,38,75,81],"high-resolution":[34,58,118,125],"UAV":[35,119],"images.":[36],"Detecting":[37],"segmenting":[40],"instances":[41],"challengeable":[46],"extant":[48],"methods":[49],"due":[50],"to":[51,94,102,130],"following":[53],"two":[54],"aspects:":[55],"(1)":[56],"original":[57],"usually":[61],"resized":[62],"before":[63],"being":[64],"fed":[65],"into":[66],"models.":[67],"As":[68],"a":[69,109,124,138,192],"result,":[70],"features":[72,133],"mostly":[77],"lost;":[78],"(2)":[79],"target":[80],"like":[82],"cars":[83],"trucks":[85],"very":[87],"pixels,":[90],"making":[91],"them":[92],"difficult":[93],"be":[95],"distinguished":[96],"from":[97],"surrounding":[98],"backgrounds.":[99],"In":[100],"order":[101],"address":[103],"these":[104],"issues,":[105],"this":[106],"paper":[107],"presents":[108],"new":[110],"multitask":[111],"model":[112],"object":[115],"images,":[120],"namely":[121],"HCD-Mask.":[122],"Specifically,":[123],"feature":[126],"extractor":[127],"is":[128],"devised":[129],"distribute":[131],"at":[134],"different":[135],"layers.":[136],"Meanwhile,":[137],"coarse-to-fine":[139],"region":[140],"proposal":[141],"network":[142],"raises":[143],"intersection":[145],"over":[146],"union":[147],"(IoU)":[148],"threshold":[149],"stage":[150],"stage,":[152],"maintains":[154],"sufficient":[155],"positive":[156],"anchors":[157],"each":[159],"stage.":[160],"For":[161],"more":[162],"accurate":[163],"mask":[164,177],"estimation,":[165],"classification":[167],"score":[168,172],"position":[171],"jointly":[174],"scored":[175],"head.":[178],"We":[179],"demonstrate":[180],"effectiveness":[182],"our":[184],"proposed":[185],"model,":[186],"showing":[188],"state-of-the-art":[189],"performance":[190],"on":[191],"UAV-based":[193],"image":[194],"dataset":[195],"constructed":[196],"ourselves.":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}