{"id":"https://openalex.org/W4413146327","doi":"https://doi.org/10.1109/cvpr52734.2025.02762","title":"Semantic and Expressive Variation in Image Captions Across Languages","display_name":"Semantic and Expressive Variation in Image Captions Across Languages","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146327","doi":"https://doi.org/10.1109/cvpr52734.2025.02762"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5090891133","display_name":"Andre Ye","orcid":"https://orcid.org/0000-0003-4936-7914"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andre Ye","raw_affiliation_strings":["University of Washington,Seattle,Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Seattle,Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047302679","display_name":"Sebastin Santy","orcid":"https://orcid.org/0000-0003-1162-0865"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastin Santy","raw_affiliation_strings":["University of Washington,Seattle,Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Seattle,Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080544237","display_name":"Jena D. Hwang","orcid":"https://orcid.org/0000-0003-3801-294X"},"institutions":[{"id":"https://openalex.org/I4210104555","display_name":"Allen Institute for Immunology","ror":"https://ror.org/0154kn471","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210104555","https://openalex.org/I4210140341"]},{"id":"https://openalex.org/I4210140341","display_name":"Allen Institute","ror":"https://ror.org/03cpe7c52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140341"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jena D. Hwang","raw_affiliation_strings":["Allen Institute for AI,Seattle,Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI,Seattle,Washington","institution_ids":["https://openalex.org/I4210104555","https://openalex.org/I4210140341"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037569091","display_name":"Amy X. Zhang","orcid":"https://orcid.org/0000-0001-9462-9835"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amy X. Zhang","raw_affiliation_strings":["University of Washington,Seattle,Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Seattle,Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032451496","display_name":"Ranjay Krishna","orcid":"https://orcid.org/0000-0001-8784-2531"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranjay Krishna","raw_affiliation_strings":["University of Washington,Seattle,Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Seattle,Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19647256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29667","last_page":"29679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.993399977684021,"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":0.993399977684021,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9581000208854675,"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":0.795440137386322},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.7675421833992004},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6176044940948486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5925010442733765},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45887696743011475},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3797839879989624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795440137386322},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7675421833992004},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6176044940948486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5925010442733765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45887696743011475},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3797839879989624},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W2038534795","https://openalex.org/W2384358604","https://openalex.org/W1567829292","https://openalex.org/W3001063351","https://openalex.org/W3196905815","https://openalex.org/W2351370765","https://openalex.org/W3204019825","https://openalex.org/W2348490172"],"abstract_inverted_index":{"Most":[0],"vision-language":[1],"models":[2,27,159,170,196,209],"today":[3],"are":[4,210],"primarily":[5],"trained":[6,171],"on":[7,162,172,181,197],"English":[8],"image-text":[9,173],"pairs,":[10],"with":[11,116],"non-English":[12],"pairs":[13],"often":[14],"filtered":[15],"out.":[16],"Evidence":[17],"from":[18],"cross-cultural":[19],"psychology":[20],"suggests":[21],"that":[22,83,169,182],"this":[23],"approach":[24],"will":[25],"bias":[26,156],"against":[28],"perceptual":[29],"modes":[30],"exhibited":[31],"by":[32,120],"people":[33,157],"who":[34],"speak":[35],"other":[36],"(non-English)":[37],"languages.":[38],"We":[39,111],"investigate":[40],"semantic":[41],"and":[42,56,78,107,122,141,158],"expressive":[43],"variation":[44],"in":[45,72,175],"image":[46,74],"captions":[47,61,118],"across":[48,62,148],"different":[49,154,163],"languages;":[50],"we":[51,81,167],"analyze":[52],"both":[53],"human-annotated":[54],"datasets":[55,76],"model-produced":[57],"captions.":[58],"By":[59],"analyzing":[60],"seven":[63],"languages":[64,155],"(English,":[65],"French,":[66],"German,":[67],"Russian,":[68],"Chinese,":[69],"Japanese,":[70],"Korean)":[71],"high-quality":[73],"captioning":[75],"(Crossmodal":[77],"Visual":[79],"Genome),":[80],"find":[82],"multilingual":[84,98,117,198],"caption":[85],"sets":[86,99],"tend":[87],"to":[88,130,160,201],"provide":[89],"richer":[90],"visual":[91,164],"descriptions":[92],"than":[93],"monolingual":[94,131],"(including":[95],"English-only)":[96],"ones;":[97],"contain":[100],"46.0%":[101],"more":[102,105,109,136,139,143],"objects,":[103,137],"66.1%":[104],"relationships,":[106],"66.8%":[108],"attributes.":[110,144],"observe":[112],"the":[113,123,190,203],"same":[114],"results":[115],"produced":[119],"LLaVA":[121],"Google":[124],"Vertex":[125],"API:":[126],"for":[127],"example,":[128],"compared":[129],"captions,":[132],"they":[133],"cover":[134],"21.9%":[135],"18.8%":[138],"relations,":[140],"20.1%":[142],"These":[145],"suggest":[146],"that,":[147],"a":[149],"large":[150],"number":[151],"of":[152,193,205],"samples,":[153],"focus":[161],"concepts.":[165],"Finally,":[166],"show":[168],"data":[174,199],"one":[176],"language":[177],"perform":[178],"distinctly":[179],"better":[180],"language\u2019s":[183],"test":[184],"set.":[185],"Our":[186],"work":[187],"points":[188],"towards":[189],"potential":[191],"value":[192],"training":[194],"vision":[195],"sources":[200],"widen":[202],"range/variation":[204],"descriptive":[206],"information":[207],"those":[208],"exposed":[211],"to.":[212]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}