{"id":"https://openalex.org/W4408703712","doi":"https://doi.org/10.1109/ipas63548.2025.10924504","title":"How Culturally Aware Are Vision-Language Models?","display_name":"How Culturally Aware Are Vision-Language Models?","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4408703712","doi":"https://doi.org/10.1109/ipas63548.2025.10924504"},"language":"en","primary_location":{"id":"doi:10.1109/ipas63548.2025.10924504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipas63548.2025.10924504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 6th International Conference on Image Processing, Applications and Systems (IPAS)","raw_type":"proceedings-article"},"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/A5098937018","display_name":"Olena Burda-Lassen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olena Burda-Lassen","raw_affiliation_strings":["Independent Research Scientist,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Research Scientist,United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047032131","display_name":"Aman Chadha","orcid":"https://orcid.org/0000-0001-6621-9003"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Chadha","raw_affiliation_strings":["Stanford University/Amazon Inc.,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University/Amazon Inc.,United States","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shashank Goswami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shashank Goswami","raw_affiliation_strings":["Independent Research Scientist,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Research Scientist,United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076595090","display_name":"Vinija Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinija Jain","raw_affiliation_strings":["Stanford University,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.89410001039505,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.89410001039505,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6457201242446899},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3788423538208008},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34285768866539},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3390176594257355},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18138664960861206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6457201242446899},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3788423538208008},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34285768866539},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3390176594257355},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18138664960861206}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipas63548.2025.10924504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipas63548.2025.10924504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 6th International Conference on Image Processing, Applications and Systems (IPAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2783643009","https://openalex.org/W3133717587","https://openalex.org/W4386980849","https://openalex.org/W4389523832","https://openalex.org/W4390041933","https://openalex.org/W4404783219","https://openalex.org/W6810334672","https://openalex.org/W6850015000","https://openalex.org/W6850204008","https://openalex.org/W6851592950","https://openalex.org/W6852551572","https://openalex.org/W6853116092","https://openalex.org/W6854347851","https://openalex.org/W6855739947","https://openalex.org/W6855815363","https://openalex.org/W6856920807","https://openalex.org/W6857256186","https://openalex.org/W6860028411","https://openalex.org/W6862115694","https://openalex.org/W6862325135","https://openalex.org/W6869443758","https://openalex.org/W6873600876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"An":[0],"image":[1,24,75,97,134],"is":[2,136],"often":[3],"considered":[4],"worth":[5],"a":[6,80,101,116,155],"thousand":[7],"words,":[8],"and":[9,15,37,59,69,72,113,115,141,169,197],"certain":[10],"images":[11,68,109],"can":[12,125,142],"tell":[13],"rich":[14],"insightful":[16],"stories.":[17],"Can":[18],"these":[19],"stories":[20],"be":[21,126,143],"told":[22],"via":[23],"captioning?":[25],"Images":[26],"from":[27],"folklore":[28],"genres,":[29],"such":[30,67],"as":[31],"mythology,":[32],"folk":[33],"dance,":[34],"cultural":[35,94,111,159],"signs,":[36],"symbols,":[38],"are":[39],"vital":[40],"to":[41,174,179],"every":[42],"culture.":[43],"Our":[44],"research":[45,140,182],"compares":[46],"the":[47,84,91,167,175,187],"performance":[48],"of":[49,93,158,189],"four":[50],"popular":[51],"vision-language":[52],"models":[53],"(GPT-4V,":[54],"Gemini":[55],"Pro":[56],"Vision,":[57],"LLaVA,":[58],"OpenFlamingo)":[60],"in":[61,66,96,161,183],"identifying":[62],"culturally":[63,73,132,191],"specific":[64],"information":[65],"creating":[70],"accurate":[71],"sensitive":[74],"captions.":[76,98],"We":[77,99,149],"also":[78],"propose":[79],"new":[81],"evaluation":[82],"metric,":[83],"Cultural":[85,121,170],"Awareness":[86,122,171],"Score":[87,172],"(CAS),":[88],"which":[89],"measures":[90],"degree":[92],"awareness":[95],"provide":[100],"dataset":[102,118,168],"MOSAIC-1.5k":[103],"labeled":[104,117],"with":[105,119,128],"ground":[106],"truth":[107],"for":[108,138,145],"containing":[110],"background":[112],"context":[114],"assigned":[120],"Scores":[123],"that":[124,195],"used":[127],"unseen":[129],"data.":[130],"Creating":[131],"appropriate":[133],"captions":[135],"valuable":[137],"scientific":[139],"beneficial":[144],"many":[146],"practical":[147],"applications.":[148],"envision":[150],"our":[151],"work":[152],"will":[153],"promote":[154],"deeper":[156],"integration":[157],"sensitivity":[160],"AI":[162,193],"applications":[163],"worldwide.":[164],"By":[165],"making":[166],"available":[173],"public,":[176],"we":[177],"aim":[178],"facilitate":[180],"further":[181],"this":[184],"area,":[185],"encouraging":[186],"development":[188],"more":[190],"aware":[192],"systems":[194],"respect":[196],"celebrate":[198],"global":[199],"diversity.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}