{"id":"https://openalex.org/W4386076015","doi":"https://doi.org/10.1109/cvpr52729.2023.01050","title":"@ CREPE: Can Vision-Language Foundation Models Reason Compositionally?","display_name":"@ CREPE: Can Vision-Language Foundation Models Reason Compositionally?","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386076015","doi":"https://doi.org/10.1109/cvpr52729.2023.01050"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.01050","doi":"https://doi.org/10.1109/cvpr52729.2023.01050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01050","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","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":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.07796","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103221706","display_name":"Zixian Ma","orcid":"https://orcid.org/0000-0001-6175-3039","observed_orcids":["https://orcid.org/0000-0001-6175-3039"]},"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":"Zixian Ma","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009093489","display_name":"Jerry Hong","orcid":null,"observed_orcids":[]},"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":"Jerry Hong","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074059774","display_name":"Mustafa Omer Gul","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mustafa Omer Gul","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mona Gandhi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Gandhi","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011345811","display_name":"Irena Gao","orcid":null,"observed_orcids":[]},"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":"Irena Gao","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032451496","display_name":"Ranjay Krishna","orcid":"https://orcid.org/0000-0001-8784-2531","observed_orcids":["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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.9898,"has_fulltext":true,"cited_by_count":111,"citation_normalized_percentile":{"value":0.98559608,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10910","last_page":"10921"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/vision-language-foundation-models","display_name":"vision-language foundation models","score":0.7829999923706055},{"id":"https://openalex.org/keywords/compositional-reasoning","display_name":"compositional reasoning","score":0.9539999961853027},{"id":"https://openalex.org/keywords/systematicity","display_name":"systematicity","score":0.765999972820282},{"id":"https://openalex.org/keywords/productivity","display_name":"productivity","score":0.9599999785423279},{"id":"https://openalex.org/keywords/image-text-retrieval","display_name":"image-text retrieval","score":0.8949999809265137}],"concepts":[{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.8729574084281921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281742691993713},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6120578646659851},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5967469215393066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578519344329834},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5454642176628113},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5293838381767273},{"id":"https://openalex.org/C204983608","wikidata":"https://www.wikidata.org/wiki/Q2111958","display_name":"Productivity","level":2,"score":0.502251148223877},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4279051423072815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35259681940078735},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1710498332977295},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14529350399971008},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr52729.2023.01050","doi":"https://doi.org/10.1109/cvpr52729.2023.01050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01050","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","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":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2212.07796","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.07796","pdf_url":"https://arxiv.org/pdf/2212.07796","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2212.07796","doi":"https://doi.org/10.48550/arxiv.2212.07796","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.07796","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.07796","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.07796","pdf_url":"https://arxiv.org/pdf/2212.07796","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386076015.pdf","grobid_xml":"https://content.openalex.org/works/W4386076015.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2081580037","https://openalex.org/W2095739681","https://openalex.org/W2194775991","https://openalex.org/W2250378130","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2328078142","https://openalex.org/W2555897561","https://openalex.org/W2561715562","https://openalex.org/W2611009517","https://openalex.org/W2786209943","https://openalex.org/W2789352267","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2899335602","https://openalex.org/W2914647989","https://openalex.org/W2936420065","https://openalex.org/W2950104027","https://openalex.org/W2963117534","https://openalex.org/W2965373594","https://openalex.org/W2995479498","https://openalex.org/W2996094825","https://openalex.org/W2996665521","https://openalex.org/W3010805364","https://openalex.org/W3017374003","https://openalex.org/W3021087975","https://openalex.org/W3021802247","https://openalex.org/W3030163527","https://openalex.org/W3034679267","https://openalex.org/W3034952258","https://openalex.org/W3126337491","https://openalex.org/W3130033937","https://openalex.org/W3135367836","https://openalex.org/W3139743318","https://openalex.org/W3140373187","https://openalex.org/W3150459247","https://openalex.org/W3153469116","https://openalex.org/W3173181308","https://openalex.org/W3173220247","https://openalex.org/W3177487519","https://openalex.org/W3181158454","https://openalex.org/W3191581723","https://openalex.org/W3195577433","https://openalex.org/W3199101198","https://openalex.org/W3203511201","https://openalex.org/W3203711169","https://openalex.org/W3209532394","https://openalex.org/W3211483028","https://openalex.org/W3215466129","https://openalex.org/W4224035735","https://openalex.org/W4224925702","https://openalex.org/W4225796999","https://openalex.org/W4226047537","https://openalex.org/W4226058394","https://openalex.org/W4226182655","https://openalex.org/W4226452378","https://openalex.org/W4229042118","https://openalex.org/W4281485151","https://openalex.org/W4281633937","https://openalex.org/W4282968790","https://openalex.org/W4283819124","https://openalex.org/W4285192809","https://openalex.org/W4287887529","https://openalex.org/W4289645295","https://openalex.org/W4312261477","https://openalex.org/W4312339522","https://openalex.org/W4312438583","https://openalex.org/W4312460555","https://openalex.org/W4312599396","https://openalex.org/W4312805760","https://openalex.org/W4312877428","https://openalex.org/W4312910992","https://openalex.org/W4313176063","https://openalex.org/W4313181088","https://openalex.org/W4313186669","https://openalex.org/W4319300158","https://openalex.org/W4388854793","https://openalex.org/W7133213514"],"related_works":["https://openalex.org/W4417255529","https://openalex.org/W7133185086","https://openalex.org/W4312261477","https://openalex.org/W7149217700","https://openalex.org/W3212780076","https://openalex.org/W4403570065","https://openalex.org/W7127152695","https://openalex.org/W7133208214","https://openalex.org/W7214683652","https://openalex.org/W4405003309"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"characteristic":[2],"common":[3],"to":[4,95,189],"both":[5],"human":[6],"vision":[7,23],"and":[8,24,69,85,106,113,145,159,162,166,213],"natural":[9],"language":[10,25],"is":[11],"their":[12],"compositional":[13],"nature.":[14],"Yet,":[15],"despite":[16],"the":[17,122,154,181],"performance":[18,174],"gains":[19],"contributed":[20],"by":[21,64,152,187],"large":[22],"pretraining,":[26],"we":[27,47,170],"find":[28,171],"that-across":[29],"7":[30],"architectures":[31],"trained":[32,98],"with":[33,133,142,184],"4":[34],"algorithms":[35],"on":[36,99],"massive":[37],"datasets-they":[38],"struggle":[39],"at":[40,44,204],"compositionality.":[41],"To":[42,71,124],"arrive":[43],"this":[45],"conclusion,":[46],"introduce":[48],"a":[49,77,119],"new":[50],"compositionality":[51,62],"evaluation":[52],"benchmark,":[53],"@":[54],"CREPE,":[55],"which":[56],"measures":[57],"two":[58],"important":[59],"aspects":[60],"of":[61,76,121,211],"identified":[63],"cognitive":[65],"science":[66],"literature:":[67],"system-aticity":[68],"productivity.":[70],"measure":[72],"systematicity,":[73,169],"CREPE":[74,127],"consists":[75],"test":[78,96,125],"dataset":[79,215],"containing":[80],"over":[81],"370K":[82],"image-text":[83,131],"pairs":[84,132],"three":[86,91,100],"different":[87,135],"seen-unseen":[88],"splits.":[89],"The":[90,148],"splits":[92],"are":[93,150],"designed":[94],"models":[97],"popular":[101],"training":[102,214],"datasets:":[103],"CC-12M,":[104],"YFCC-15M,":[105],"LAION-400M.":[107],"We":[108],"also":[109],"generate":[110],"325K,":[111],"316K,":[112],"309K":[114],"hard":[115,139],"negative":[116,140],"captions":[117,141],"for":[118],"subset":[120],"pairs.":[123],"productivity,":[126,192],"contains":[128],"17":[129],"K":[130],"nine":[134],"complexities":[136],"plus":[137],"278K":[138],"atomic,":[143],"swapping":[144],"negation":[146],"foils.":[147],"datasets":[149],"generated":[151],"repurposing":[153],"Visual":[155],"Genome":[156],"scene":[157],"graphs":[158],"region":[160],"descriptions":[161],"applying":[163],"handcrafted":[164],"templates":[165],"GPT-3.":[167],"For":[168,191],"that":[172],"model":[173,212],"decreases":[175],"consistently":[176],"when":[177],"novel":[178],"compositions":[179],"dominate":[180],"retrieval":[182,194],"set,":[183],"Recall@1":[185],"dropping":[186],"up":[188],"9%.":[190],"models'":[193],"success":[195],"decays":[196],"as":[197],"complexity":[198],"increases,":[199],"frequently":[200],"nearing":[201],"random":[202],"chance":[203],"high":[205],"complexity.":[206],"These":[207],"results":[208],"hold":[209],"regardless":[210],"size.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":25},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":18}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-23T00:00:00"}