{"id":"https://openalex.org/W3012819905","doi":"https://doi.org/10.1145/3366423.3380063","title":"Crowdsourcing Detection of Sampling Biases in Image Datasets","display_name":"Crowdsourcing Detection of Sampling Biases in Image Datasets","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3012819905","doi":"https://doi.org/10.1145/3366423.3380063","mag":"3012819905"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380063","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380063","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiao Hu","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049707744","display_name":"Haobo Wang","orcid":"https://orcid.org/0000-0001-8586-3048"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haobo Wang","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017600155","display_name":"Anirudh Vegesana","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudh Vegesana","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064265717","display_name":"Somesh Dube","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Somesh Dube","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103076352","display_name":"Kaiwen Yu","orcid":"https://orcid.org/0000-0003-0118-3593"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiwen Yu","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083782793","display_name":"Gore Kao","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gore Kao","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060246506","display_name":"Shuo-Han Chen","orcid":"https://orcid.org/0000-0002-1619-4335"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo-Han Chen","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108534924","display_name":"Yung-Hsiang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yung-Hsiang Lu","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074177185","display_name":"George K. Thiruvathukal","orcid":"https://orcid.org/0000-0002-0452-5571"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George K. Thiruvathukal","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071294124","display_name":"Ming Yin","orcid":"https://orcid.org/0000-0002-7364-139X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Yin","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":2.5505,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9064491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2955","last_page":"2961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9854000210762024,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.9331457614898682},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8415830731391907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8083658218383789},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.6898792386054993},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6303378343582153},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5356350541114807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511886477470398},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43081697821617126},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40316474437713623},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3715028464794159},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35770314931869507},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12865996360778809},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1112183928489685},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08383041620254517}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9331457614898682},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8415830731391907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083658218383789},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6898792386054993},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6303378343582153},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5356350541114807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511886477470398},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43081697821617126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40316474437713623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3715028464794159},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35770314931869507},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12865996360778809},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1112183928489685},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08383041620254517},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3366423.3380063","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380063","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:ecommons.luc.edu:cs_facpubs-1244","is_oa":true,"landing_page_url":"https://ecommons.luc.edu/cs_facpubs/244","pdf_url":null,"source":{"id":"https://openalex.org/S4306402030","display_name":"Loyola eCommons (Loyola University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1925986","host_organization_name":"Loyola University Chicago","host_organization_lineage":["https://openalex.org/I1925986"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science: Faculty Publications and Other Works","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380063","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380063","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1574679496","https://openalex.org/W1587248362","https://openalex.org/W1852255964","https://openalex.org/W1878518397","https://openalex.org/W1933349210","https://openalex.org/W2031342017","https://openalex.org/W2035818959","https://openalex.org/W2070148066","https://openalex.org/W2120396827","https://openalex.org/W2127008633","https://openalex.org/W2141282920","https://openalex.org/W2149252982","https://openalex.org/W2155904486","https://openalex.org/W2252147815","https://openalex.org/W2282821441","https://openalex.org/W2581082771","https://openalex.org/W2604188576","https://openalex.org/W2605991684","https://openalex.org/W2962787423","https://openalex.org/W2964116855","https://openalex.org/W3101298150","https://openalex.org/W3102923649","https://openalex.org/W4240153047","https://openalex.org/W4288083803"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4318823662","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W3207526114","https://openalex.org/W4286908577"],"abstract_inverted_index":{"Despite":[0],"many":[1],"exciting":[2],"innovations":[3],"in":[4,14,66,84,106,130,148],"computer":[5,16,85,149],"vision,":[6],"recent":[7],"studies":[8],"reveal":[9],"a":[10,41,92],"number":[11],"of":[12,21,30,40,112],"risks":[13,32],"existing":[15],"vision":[17,150],"systems,":[18],"suggesting":[19],"results":[20],"such":[22],"systems":[23],"may":[24],"be":[25,34],"unfair":[26],"and":[27,49,81,140,152],"untrustworthy.":[28],"Many":[29],"these":[31],"can":[33,121],"partly":[35],"attributed":[36],"to":[37,61,71,96,126],"the":[38,55,67,79,100,118,124],"use":[39],"training":[42],"image":[43,107,142],"dataset":[44,69],"that":[45,117,133,144],"exhibits":[46],"sampling":[47,64,128],"biases":[48,65,129,139],"thus":[50,75],"does":[51],"not":[52],"accurately":[53],"reflect":[54],"real":[56],"visual":[57,68],"world.":[58],"Being":[59],"able":[60],"detect":[62,127],"potential":[63],"prior":[70],"model":[72],"development":[73],"is":[74],"essential":[76],"for":[77,102],"mitigating":[78],"fairness":[80],"trustworthy":[82],"concerns":[83],"vision.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90,115],"propose":[91],"three-step":[93],"crowdsourcing":[94],"workflow":[95,120],"get":[97],"humans":[98],"into":[99],"loop":[101],"facilitating":[103],"bias":[104],"discovery":[105],"datasets.":[108],"Through":[109],"two":[110],"sets":[111],"evaluation":[113],"studies,":[114],"find":[116],"proposed":[119],"effectively":[122],"organize":[123],"crowd":[125],"both":[131],"datasets":[132,143],"are":[134,145],"artificially":[135],"created":[136],"with":[137],"designed":[138],"real-world":[141],"widely":[146],"used":[147],"research":[151],"system":[153],"development.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}