{"id":"https://openalex.org/W3015223113","doi":"https://doi.org/10.1109/iwbf49977.2020.9107950","title":"A Method for Curation of Web-Scraped Face Image Datasets","display_name":"A Method for Curation of Web-Scraped Face Image Datasets","publication_year":2020,"publication_date":"2020-04-01","ids":{"openalex":"https://openalex.org/W3015223113","doi":"https://doi.org/10.1109/iwbf49977.2020.9107950","mag":"3015223113"},"language":"en","primary_location":{"id":"doi:10.1109/iwbf49977.2020.9107950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwbf49977.2020.9107950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 8th International Workshop on Biometrics and Forensics (IWBF)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.03074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100323983","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0002-6319-3722"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["Department of Computer Science & Engineering, University of Notre Dame","University of Notre Dame,Department of Computer Science & Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science & Engineering","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061227377","display_name":"V\u00edtor Albiero","orcid":"https://orcid.org/0000-0002-8607-9914"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitor Albiero","raw_affiliation_strings":["Department of Computer Science & Engineering, University of Notre Dame","University of Notre Dame,Department of Computer Science & Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science & Engineering","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019673624","display_name":"Kevin W. Bowyer","orcid":"https://orcid.org/0000-0002-7562-4390"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin W. Bowyer","raw_affiliation_strings":["Department of Computer Science & Engineering, University of Notre Dame","University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100323983"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.0981,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37377957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":1.0,"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/T11448","display_name":"Face recognition and analysis","score":1.0,"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/T10828","display_name":"Biometric Identification and Security","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10057","display_name":"Face and Expression Recognition","score":0.9865999817848206,"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/computer-science","display_name":"Computer science","score":0.7380502223968506},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5366792678833008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5103959441184998},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42453455924987793},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41048741340637207},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32658177614212036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380502223968506},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5366792678833008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103959441184998},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42453455924987793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41048741340637207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32658177614212036},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iwbf49977.2020.9107950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwbf49977.2020.9107950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 8th International Workshop on Biometrics and Forensics (IWBF)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.03074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03074","pdf_url":"https://arxiv.org/pdf/2004.03074","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3015223113","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.03074.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.03074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.03074","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.03074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03074","pdf_url":"https://arxiv.org/pdf/2004.03074","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1655564579","display_name":"RET Site: Biologically and Physically Inspired Computing Models and Systems","funder_award_id":"1855278","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310260","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015223113.pdf","grobid_xml":"https://content.openalex.org/works/W3015223113.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1550005041","https://openalex.org/W1782590233","https://openalex.org/W1978642336","https://openalex.org/W1997011019","https://openalex.org/W2012411608","https://openalex.org/W2033419168","https://openalex.org/W2035830871","https://openalex.org/W2118664399","https://openalex.org/W2137385871","https://openalex.org/W2137659841","https://openalex.org/W2186170585","https://openalex.org/W2515770085","https://openalex.org/W2735553491","https://openalex.org/W2871667416","https://openalex.org/W2887500939","https://openalex.org/W2889800473","https://openalex.org/W2912376035","https://openalex.org/W2949386440","https://openalex.org/W2960178077","https://openalex.org/W2962898354","https://openalex.org/W2963466847","https://openalex.org/W2963671154","https://openalex.org/W2963839617","https://openalex.org/W2969985801","https://openalex.org/W2970084480","https://openalex.org/W2985817549","https://openalex.org/W3004749872","https://openalex.org/W3010400237","https://openalex.org/W3021840842","https://openalex.org/W4233204037","https://openalex.org/W6686757273","https://openalex.org/W6773748783","https://openalex.org/W6774187817"],"related_works":["https://openalex.org/W3033428172","https://openalex.org/W2795705148","https://openalex.org/W3014490631","https://openalex.org/W3180321737","https://openalex.org/W3080409684","https://openalex.org/W3110762274","https://openalex.org/W1966572511","https://openalex.org/W3001841461","https://openalex.org/W2552684688","https://openalex.org/W2782533531","https://openalex.org/W2008863572","https://openalex.org/W2613010453","https://openalex.org/W3103795537","https://openalex.org/W3132970294","https://openalex.org/W3160795532","https://openalex.org/W3105039763","https://openalex.org/W214814202","https://openalex.org/W2952391739","https://openalex.org/W3146395954"],"abstract_inverted_index":{"Web-scraped,":[0],"in-the-wild":[1],"datasets":[2,20,172,185],"have":[3,99],"become":[4],"the":[5,30,46,59,65,95,146,149,171,187],"norm":[6],"in":[7,18,56,64,82],"face":[8,105],"recognition":[9,106],"research.":[10],"The":[11,158],"numbers":[12],"of":[13,27,35,61,86,118,140,183],"subjects":[14,53],"and":[15,54,113,133,142,154],"images":[16,28,44,62,135],"acquired":[17],"web-scraped":[19],"are":[21,175],"usually":[22],"very":[23],"large,":[24],"with":[25,45,108],"number":[26,60],"on":[29,148,170],"millions":[31],"scale.":[32],"A":[33],"variety":[34],"issues":[36],"occur":[37],"when":[38],"collecting":[39],"a":[40,67,83,91,100,137,162,166],"dataset":[41,102],"in-the-wild,":[42],"including":[43],"wrong":[47],"identity":[48],"label,":[49],"duplicate":[50,52,128],"images,":[51,126,132],"variation":[55],"quality.":[57,143],"With":[58],"being":[63],"millions,":[66],"manual":[68],"cleaning":[69],"procedure":[70],"is":[71,97],"not":[72],"feasible.":[73],"But":[74],"fully":[75],"automated":[76],"methods":[77],"used":[78],"to":[79,98,115,186],"date":[80],"result":[81],"less-than-ideal":[84],"level":[85],"clean":[87,101],"dataset.":[88,157],"We":[89,144],"propose":[90],"semi-automated":[92],"method,":[93],"where":[94],"goal":[96],"for":[103],"testing":[104],"methods,":[107],"similar":[109],"quality":[110],"across":[111,120],"men":[112],"women,":[114],"support":[116],"comparison":[117],"accuracy":[119,169],"gender.":[121],"Our":[122],"approach":[123],"removes":[124,134],"near-duplicate":[125],"merges":[127],"subjects,":[129],"corrects":[130],"mislabeled":[131],"outside":[136],"defined":[138],"range":[139],"pose":[141],"conduct":[145],"curation":[147],"Asian":[150],"Face":[151],"Dataset":[152],"(AFD)":[153],"VGGFace2":[155],"test":[156],"experiments":[159],"show":[160],"that":[161],"state-of-the-art":[163],"method":[164],"achieves":[165],"much":[167],"higher":[168],"after":[173],"they":[174],"curated.":[176],"Finally,":[177],"we":[178],"release":[179],"our":[180],"cleaned":[181],"versions":[182],"both":[184],"research":[188],"community.":[189]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}