{"id":"https://openalex.org/W2024922353","doi":"https://doi.org/10.1109/icip.2014.7025068","title":"A data-driven approach to cleaning large face datasets","display_name":"A data-driven approach to cleaning large face datasets","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2024922353","doi":"https://doi.org/10.1109/icip.2014.7025068","mag":"2024922353"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2014.7025068","doi":"https://doi.org/10.1109/icip.2014.7025068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2014.7025068","pdf_url":null,"source":{"id":"https://openalex.org/S4210223844","display_name":"Proceedings - International Conference on Image Processing","issn_l":"1522-4880","issn":["1522-4880","2381-8549"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"volume":null,"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/A5071435724","display_name":"Hongwei Ng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Hong-Wei Ng","raw_affiliation_strings":["Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore","Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210108443"]},{"raw_affiliation_string":"Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore#TAB#","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210108443"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018017185","display_name":"STEFAN S. WINKLER","orcid":"https://orcid.org/0000-0003-4305-8408","observed_orcids":["https://orcid.org/0000-0003-4305-8408"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Stefan Winkler","raw_affiliation_strings":["Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore","Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210108443"]},{"raw_affiliation_string":"Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign, Singapore#TAB#","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210108443"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.0512,"has_fulltext":false,"cited_by_count":668,"citation_normalized_percentile":{"value":0.99394192,"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":"343","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9810000061988831,"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":0.9810000061988831,"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/T10057","display_name":"Face and Expression Recognition","score":0.017000000923871994,"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/T11094","display_name":"Face Recognition and Perception","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/face-recognition","display_name":"face recognition","score":0.6039999723434448},{"id":"https://openalex.org/keywords/public-figures","display_name":"public figures","score":0.7459999918937683},{"id":"https://openalex.org/keywords/face-detection","display_name":"face detection","score":0.7549999952316284},{"id":"https://openalex.org/keywords/quadratic-programming","display_name":"quadratic programming","score":0.8149999976158142},{"id":"https://openalex.org/keywords/facial-similarity","display_name":"face similarity","score":0.4050000011920929},{"id":"https://openalex.org/keywords/image-deduplication","display_name":"image deduplication","score":0.4860000014305115},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292216062545776},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.7313888072967529},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6289263367652893},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6068274974822998},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.5595699548721313},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5161677002906799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094252228736877},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43629926443099976},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4245436191558838},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3803372383117676},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26259487867355347},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16127043962478638},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10294660925865173},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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":2,"locations":[{"id":"doi:10.1109/icip.2014.7025068","doi":"https://doi.org/10.1109/icip.2014.7025068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2014.7025068","pdf_url":null,"source":{"id":"https://openalex.org/S4210223844","display_name":"Proceedings - International Conference on Image Processing","issn_l":"1522-4880","issn":["1522-4880","2381-8549"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.2876","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.2876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vintage.winklerbros.net/Publications/icip2014a.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1782590233","https://openalex.org/W1990334093","https://openalex.org/W2009119155","https://openalex.org/W2019041733","https://openalex.org/W2107558380","https://openalex.org/W2108598243","https://openalex.org/W2117736950","https://openalex.org/W2117756735","https://openalex.org/W2118585731","https://openalex.org/W2149489787","https://openalex.org/W2153603270","https://openalex.org/W2153635508","https://openalex.org/W2156001867","https://openalex.org/W2158844819","https://openalex.org/W2163808566","https://openalex.org/W2536626143","https://openalex.org/W2566113627","https://openalex.org/W2652751060","https://openalex.org/W3097096317"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2384651879"],"abstract_inverted_index":{"Large":[0],"face":[1,7,42],"datasets":[2,43],"are":[3,12,137],"important":[4],"for":[5,54],"advancing":[6],"recognition":[8],"research,":[9],"but":[10],"they":[11],"tedious":[13],"to":[14,22,40,66,78,124,132],"build,":[15],"because":[16],"a":[17,82,120,125],"lot":[18],"of":[19,29,74,92,150,153],"work":[20,130],"has":[21],"go":[23],"into":[24],"cleaning":[25],"the":[26,58,72,76,88,93,100,129,139],"huge":[27],"amount":[28],"raw":[30],"data.":[31],"To":[32],"facilitate":[33],"this":[34,115,146],"task,":[35],"we":[36,136],"describe":[37],"an":[38],"approach":[39],"building":[41],"that":[44,90,114,142],"starts":[45],"with":[46],"detecting":[47],"faces":[48,77,91,152],"in":[49,128],"images":[50],"returned":[51],"from":[52,161],"searches":[53],"public":[55,155],"figures":[56,156],"on":[57],"Internet,":[59],"followed":[60],"by":[61],"discarding":[62],"those":[63],"not":[64],"belonging":[65],"each":[67],"queried":[68],"person.":[69],"We":[70],"formulate":[71],"problem":[73],"identifying":[75],"be":[79,159],"removed":[80],"as":[81],"quadratic":[83],"programming":[84],"problem,":[85],"which":[86],"exploits":[87],"observations":[89],"same":[94,101],"person":[95],"should":[96],"look":[97],"similar,":[98],"have":[99],"gender,":[102],"and":[103,157],"normally":[104],"appear":[105],"at":[106],"most":[107],"once":[108],"per":[109],"image.":[110],"Our":[111],"results":[112],"show":[113],"method":[116],"can":[117,158],"reliably":[118],"clean":[119],"large":[121],"dataset,":[122],"leading":[123],"considerable":[126],"reduction":[127],"needed":[131],"build":[133],"it.":[134],"Finally,":[135],"releasing":[138],"FaceScrub":[140],"dataset":[141],"was":[143],"created":[144],"using":[145],"approach.":[147],"It":[148],"consists":[149],"141,130":[151],"695":[154],"obtained":[160],"http://vintage.winklerbros.net/facescrub.html.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":61},{"year":2023,"cited_by_count":64},{"year":2022,"cited_by_count":68},{"year":2021,"cited_by_count":102},{"year":2020,"cited_by_count":87},{"year":2019,"cited_by_count":101},{"year":2018,"cited_by_count":56},{"year":2017,"cited_by_count":40},{"year":2016,"cited_by_count":33},{"year":2015,"cited_by_count":11}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}