{"id":"https://openalex.org/W4399144461","doi":"https://doi.org/10.1145/3654823.3654857","title":"Object Detection and Instance Segmentation in Construction Sites","display_name":"Object Detection and Instance Segmentation in Construction Sites","publication_year":2024,"publication_date":"2024-03-22","ids":{"openalex":"https://openalex.org/W4399144461","doi":"https://doi.org/10.1145/3654823.3654857"},"language":"en","primary_location":{"id":"doi:10.1145/3654823.3654857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654823.3654857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning","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/A5060029428","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0003-1667-0503"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101405146","display_name":"Jie Shen","orcid":"https://orcid.org/0000-0002-3409-4469"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060029428"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.5468,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62011502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/T10809","display_name":"Occupational Health and Safety Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9307000041007996,"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/computer-science","display_name":"Computer science","score":0.8243357539176941},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7916839718818665},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.7555832862854004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7417721152305603},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6695891618728638},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.524319052696228},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5117868781089783},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.49301382899284363},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4814023971557617},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47355714440345764},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44611647725105286},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42209771275520325},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35671359300613403},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07618334889411926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8243357539176941},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7916839718818665},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.7555832862854004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7417721152305603},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6695891618728638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.524319052696228},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5117868781089783},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.49301382899284363},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4814023971557617},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47355714440345764},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44611647725105286},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42209771275520325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35671359300613403},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07618334889411926},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3654823.3654857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654823.3654857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2109255472","https://openalex.org/W2144560128","https://openalex.org/W2412782625","https://openalex.org/W2625943085","https://openalex.org/W2761891891","https://openalex.org/W2772016598","https://openalex.org/W2791834423","https://openalex.org/W2792224473","https://openalex.org/W2906127197","https://openalex.org/W2944397195","https://openalex.org/W2955058313","https://openalex.org/W2963150697","https://openalex.org/W2964241181","https://openalex.org/W2966167487","https://openalex.org/W2969825080","https://openalex.org/W3005856570","https://openalex.org/W3014641072","https://openalex.org/W3035358681","https://openalex.org/W3106586859","https://openalex.org/W3138516171","https://openalex.org/W3166337757","https://openalex.org/W3170544306","https://openalex.org/W3189310703","https://openalex.org/W3211490618","https://openalex.org/W4224936685","https://openalex.org/W4288987448","https://openalex.org/W4386567943"],"related_works":["https://openalex.org/W2153719181","https://openalex.org/W1971748923","https://openalex.org/W1566155057","https://openalex.org/W2060986072","https://openalex.org/W2052574922","https://openalex.org/W64588465","https://openalex.org/W3120641340","https://openalex.org/W2117825986","https://openalex.org/W3134067061","https://openalex.org/W2079855347"],"abstract_inverted_index":{"Identifying":[0],"safety":[1],"hazards":[2],"and":[3,29,64,89,121,158,175],"ensuring":[4],"quality":[5],"control":[6],"in":[7,47,61,75,93,161],"construction":[8,49,94,126,162],"sites":[9],"requires":[10],"information":[11],"from":[12,70],"surveillance":[13],"images,":[14],"such":[15],"as":[16,106],"clear":[17],"detection":[18,28,66,88,174],"boxes,":[19],"accurate":[20],"edges":[21],"of":[22,109,170],"targets,":[23],"etc.":[24],"Although":[25],"both":[26],"object":[27,87,173],"instance":[30,90,139,178],"segmentation":[31,91],"models":[32],"have":[33,58],"yielded":[34],"good":[35],"results":[36,67],"on":[37,55],"large":[38],"open":[39],"datasets,":[40],"there":[41],"is":[42,152],"still":[43],"room":[44],"for":[45,125,172,177],"improvement":[46],"the":[48,65,79,101,107,110,119,123,136,143],"field.":[50],"Besides,":[51],"previous":[52],"methods":[53],"based":[54],"traditional":[56],"DNNs":[57],"encountered":[59],"bottlenecks":[60],"improving":[62],"performance,":[63],"are":[68],"far":[69],"enough":[71],"to":[72],"be":[73],"used":[74],"practice.":[76],"We":[77],"present":[78],"Cascade":[80,111,144],"Mask":[81],"R-CNN":[82],"framework,":[83],"which":[84,113],"simultaneously":[85],"handles":[86],"tasks":[92],"scenarios":[95],"using":[96],"a":[97,131,165],"single":[98],"model.":[99,145],"And":[100],"Swin":[102],"Transformer":[103],"model":[104,124,151],"serves":[105],"backbone":[108,120],"model,":[112],"enhances":[114],"feature":[115],"maps":[116],"extracted":[117],"by":[118,142],"strengthens":[122],"sites.":[127],"Additionally,":[128],"we":[129],"propose":[130],"post-processing":[132],"method":[133],"that":[134,149],"refines":[135],"initial":[137],"coarse":[138],"masks":[140],"generated":[141],"Our":[146],"experiments":[147],"show":[148],"our":[150],"highly":[153],"effective":[154],"at":[155],"detecting":[156],"objects":[157],"segmenting":[159],"instances":[160],"sites,":[163],"with":[164],"mean":[166],"average":[167],"precision":[168],"(mAP)":[169],"60.2%":[171],"54%":[176],"segmentation.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}