{"id":"https://openalex.org/W4304086863","doi":"https://doi.org/10.1145/3503161.3548396","title":"Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models","display_name":"Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304086863","doi":"https://doi.org/10.1145/3503161.3548396"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548396","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548396","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5100388041","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0001-6586-1037"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722015","display_name":"Junyang Wang","orcid":"https://orcid.org/0000-0001-8334-4009"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyang Wang","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023834030","display_name":"Jitao Sang","orcid":"https://orcid.org/0000-0002-0699-3205"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Sang","raw_affiliation_strings":["Beijing Jiaotong University & Peng Cheng Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Peng Cheng Lab, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100388041"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.6597,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7825467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4996","last_page":"5004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.995199978351593,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.972100019454956,"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/debiasing","display_name":"Debiasing","score":0.9655070900917053},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9348018169403076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865170001983643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5694448947906494},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5314927101135254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46801483631134033},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4455406069755554},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.4298858046531677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38347649574279785},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21935075521469116},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11876651644706726}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9655070900917053},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9348018169403076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865170001983643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5694448947906494},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5314927101135254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46801483631134033},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4455406069755554},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.4298858046531677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38347649574279785},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21935075521469116},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11876651644706726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548396","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548396","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2250539671","https://openalex.org/W2592232824","https://openalex.org/W2926555354","https://openalex.org/W2950888501","https://openalex.org/W2962793481","https://openalex.org/W2963526187","https://openalex.org/W2963530300","https://openalex.org/W2970231061","https://openalex.org/W2972413484","https://openalex.org/W2982232682","https://openalex.org/W2990138404","https://openalex.org/W3034352949","https://openalex.org/W3049478012","https://openalex.org/W3091177855","https://openalex.org/W3091407209","https://openalex.org/W3091588028","https://openalex.org/W3093377743","https://openalex.org/W3099839483","https://openalex.org/W3135367836","https://openalex.org/W3172141633","https://openalex.org/W3206310417","https://openalex.org/W3207798279","https://openalex.org/W4200044613","https://openalex.org/W4285345750","https://openalex.org/W4312877428"],"related_works":["https://openalex.org/W2056582926","https://openalex.org/W3137864021","https://openalex.org/W2162910442","https://openalex.org/W2079879923","https://openalex.org/W4200271736","https://openalex.org/W2104420793","https://openalex.org/W3017854570","https://openalex.org/W2028689793","https://openalex.org/W4313936361","https://openalex.org/W4242448314"],"abstract_inverted_index":{"Vision-Language":[0],"Pre-training":[1],"(VLP)":[2],"models":[3,56],"have":[4],"achieved":[5],"state-of-the-art":[6],"performance":[7],"in":[8,33,54,82,95,110,149],"numerous":[9],"cross-modal":[10],"tasks.":[11],"Since":[12],"they":[13,132],"are":[14,133],"optimized":[15],"to":[16,28,49,106,135,143],"capture":[17],"the":[18,34,51,59,108,111],"statistical":[19],"properties":[20],"of":[21,63],"intra-":[22],"and":[23,65,98,117,126,139,145],"inter-modality,":[24],"there":[25],"remains":[26],"risk":[27],"learn":[29],"social":[30,52,130],"biases":[31],"presented":[32],"data":[35],"as":[36,137],"well.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,87],"(1)":[42],"introduce":[43],"a":[44,70,101],"counterfactual-based":[45],"bias":[46,53,81,92],"measurement":[47],"CounterBias":[48,125],"quantify":[50],"VLP":[55,83,96,102,122,150],"by":[57],"comparing":[58],"[MASK]ed":[60,112],"prediction":[61,113],"probabilities":[62,114],"factual":[64,116],"counterfactual":[66,118],"samples;":[67],"(2)":[68],"construct":[69],"novel":[71],"VL-Bias":[72],"dataset":[73],"including":[74],"24K":[75],"image-text":[76,119],"pairs":[77,120],"for":[78,121],"measuring":[79],"gender":[80,91],"models,":[84],"from":[85],"which":[86],"observed":[88],"that":[89],"significant":[90],"is":[93],"prevalent":[94],"models;":[97],"(3)":[99],"propose":[100],"debiasing":[103],"method":[104],"FairVLP":[105,127],"minimize":[107],"difference":[109],"between":[115],"debiasing.":[123],"Although":[124],"focus":[128],"on":[129],"bias,":[131],"generalizable":[134],"serve":[136],"tools":[138],"provide":[140],"new":[141],"insights":[142],"probe":[144],"regularize":[146],"more":[147],"knowledge":[148],"models.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}