{"id":"https://openalex.org/W4390874161","doi":"https://doi.org/10.1109/iccv51070.2023.00247","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","display_name":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390874161","doi":"https://doi.org/10.1109/iccv51070.2023.00247"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.00247","doi":"https://doi.org/10.1109/iccv51070.2023.00247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","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/2303.07274","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085028836","display_name":"Nitzan Bitton Guetta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nitzan Bitton-Guetta","raw_affiliation_strings":["Ben Gurion University of the Negev"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben Gurion University of the Negev","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068580969","display_name":"Yonatan Bitton","orcid":"https://orcid.org/0000-0002-1185-6838","observed_orcids":["https://orcid.org/0000-0002-1185-6838"]},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yonatan Bitton","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043614405","display_name":"Jack Hessel","orcid":"https://orcid.org/0000-0002-4012-8979","observed_orcids":["https://orcid.org/0000-0002-4012-8979"]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Hessel","raw_affiliation_strings":["Allen Institute for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110578233","display_name":"Ludwig Schmidt","orcid":null,"observed_orcids":[]},"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":"Ludwig Schmidt","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072913672","display_name":"Yuval Elovici","orcid":"https://orcid.org/0000-0002-9641-128X","observed_orcids":["https://orcid.org/0000-0002-9641-128X"]},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuval Elovici","raw_affiliation_strings":["Ben Gurion University of the Negev"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben Gurion University of the Negev","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082136238","display_name":"Gabriel Stanovsky","orcid":"https://orcid.org/0000-0002-2420-8979","observed_orcids":["https://orcid.org/0000-0002-2420-8979"]},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Gabriel Stanovsky","raw_affiliation_strings":["The Hebrew University of Jerusalem","Allen Institute for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"Allen Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007903277","display_name":"Roy Schwartz","orcid":"https://orcid.org/0000-0003-3487-5713","observed_orcids":["https://orcid.org/0000-0003-3487-5713"]},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roy Schwartz","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7699,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.9665074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2616","last_page":"2627"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10036","display_name":"Advanced Neural Network Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-commonsense-reasoning","display_name":"visual commonsense reasoning","score":0.9580000042915344},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.7310000061988831},{"id":"https://openalex.org/keywords/cross-modal-matching","display_name":"cross-modal matching","score":0.9480000138282776},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":1.0},{"id":"https://openalex.org/keywords/explanation-generation","display_name":"explanation generation","score":0.9430000185966492},{"id":"https://openalex.org/keywords/midjourney","display_name":"Midjourney","score":0.8629999756813049}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7812306880950928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639255881309509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6029662489891052},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.5996049046516418},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5564616918563843},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.5355738401412964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5015668869018555},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45958322286605835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3573857247829437},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.13861599564552307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1287389099597931},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51070.2023.00247","doi":"https://doi.org/10.1109/iccv51070.2023.00247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.07274","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.07274","pdf_url":"https://arxiv.org/pdf/2303.07274","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2303.07274","doi":"https://doi.org/10.48550/arxiv.2303.07274","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.07274","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2303.07274","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.07274","pdf_url":"https://arxiv.org/pdf/2303.07274","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390874161.pdf","grobid_xml":"https://content.openalex.org/works/W4390874161.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2196779496","https://openalex.org/W2471094925","https://openalex.org/W2560730294","https://openalex.org/W2886424491","https://openalex.org/W2896457183","https://openalex.org/W2903073381","https://openalex.org/W2936262349","https://openalex.org/W2946609015","https://openalex.org/W2963101081","https://openalex.org/W2963341956","https://openalex.org/W2963890019","https://openalex.org/W2964895772","https://openalex.org/W2996388127","https://openalex.org/W2998617917","https://openalex.org/W3030163527","https://openalex.org/W3105928338","https://openalex.org/W3129576130","https://openalex.org/W3135367836","https://openalex.org/W3136788995","https://openalex.org/W3150658752","https://openalex.org/W3153947101","https://openalex.org/W3154186000","https://openalex.org/W3193231083","https://openalex.org/W3196672660","https://openalex.org/W4225323055","https://openalex.org/W4226182655","https://openalex.org/W4226352076","https://openalex.org/W4229042118","https://openalex.org/W4281633595","https://openalex.org/W4287887134","https://openalex.org/W4307079201","https://openalex.org/W4312261477","https://openalex.org/W4312299632","https://openalex.org/W4312933868","https://openalex.org/W4318718936","https://openalex.org/W4366330503","https://openalex.org/W4367367040","https://openalex.org/W4376312115","https://openalex.org/W4382469053","https://openalex.org/W4384918448","https://openalex.org/W4385571053","https://openalex.org/W4385572714","https://openalex.org/W6799626271","https://openalex.org/W6849177959","https://openalex.org/W6854866820","https://openalex.org/W7133185515","https://openalex.org/W7133217989"],"related_works":["https://openalex.org/W4417517237","https://openalex.org/W4399598097","https://openalex.org/W4389518870","https://openalex.org/W4318185075","https://openalex.org/W4389712588","https://openalex.org/W4412623820","https://openalex.org/W4416035530","https://openalex.org/W7127541466","https://openalex.org/W2903073381","https://openalex.org/W4285044887"],"abstract_inverted_index":{"Weird,":[0],"unusual,":[1],"and":[2,31,53,71,109,124,141],"uncanny":[3],"images":[4,83],"pique":[5],"the":[6,20,25,47,63,100,156],"curiosity":[7],"of":[8,80,158],"observers":[9],"because":[10],"they":[11],"challenge":[12],"commonsense.":[13,75],"For":[14],"example,":[15],"an":[16],"image":[17,89,105,129],"released":[18],"during":[19],"2022":[21],"world":[22],"cup":[23],"depicts":[24],"famous":[26],"soccer":[27],"stars":[28],"Lionel":[29],"Messi":[30],"Cristiano":[32],"Ronaldo":[33],"playing":[34],"chess,":[35],"which":[36],"playfully":[37],"violates":[38],"our":[39,152],"expectation":[40],"that":[41,135],"their":[42],"competition":[43],"should":[44],"occur":[45],"on":[46,148],"football":[48],"field.1Humans":[49],"can":[50,59],"easily":[51],"recognize":[52],"interpret":[54],"these":[55],"unconventional":[56],"images,":[57],"but":[58],"AI":[60,159],"models":[61,121,137,160],"do":[62],"same?":[64],"We":[65,94,150],"introduce":[66,114],"WHOOPS!,":[67],"a":[68,115,127],"new":[69],"dataset":[70,77,153],"benchmark":[72],"for":[73],"visual":[74,110,163],"The":[76],"is":[78,130],"comprised":[79],"purposefully":[81],"commonsense-defying":[82],"created":[84],"by":[85],"designers":[86],"using":[87],"publicly-available":[88],"generation":[90,118],"tools":[91],"like":[92],"Midjourney.":[93],"consider":[95],"several":[96],"tasks":[97],"posed":[98],"over":[99],"dataset.":[101],"In":[102],"addition":[103],"to":[104],"captioning,":[106],"cross-modal":[107],"matching,":[108],"question":[111],"answering,":[112],"we":[113],"difficult":[116],"explanation":[117],"task,":[119],"where":[120],"must":[122],"identify":[123],"explain":[125],"why":[126],"given":[128],"unusual.":[131],"Our":[132],"results":[133],"show":[134],"state-of-the-art":[136],"such":[138],"as":[139],"GPT3":[140],"BLIP2":[142],"still":[143],"lag":[144],"behind":[145],"human":[146],"performance":[147],"WHOOPS!.":[149],"hope":[151],"will":[154],"inspire":[155],"development":[157],"with":[161],"stronger":[162],"commonsense":[164],"reasoning":[165],"abilities.2":[166]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-01-16T00:00:00"}