{"id":"https://openalex.org/W4387968123","doi":"https://doi.org/10.1145/3581783.3612395","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","display_name":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968123","doi":"https://doi.org/10.1145/3581783.3612395"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5001893388","display_name":"Zhenyang Li","orcid":"https://orcid.org/0000-0002-4694-1231"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyang Li","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-4694-1231","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054313646","display_name":"Yangyang Guo","orcid":"https://orcid.org/0000-0001-8691-5372"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yangyang Guo","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8691-5372","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053685797","display_name":"Kejie Wang","orcid":"https://orcid.org/0000-0003-0595-6856"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejie Wang","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0595-6856","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693591","display_name":"Xiaolin Chen","orcid":"https://orcid.org/0000-0003-4638-0603"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Chen","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-4638-0603","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology,\u00a0Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,\u00a0Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415049","display_name":"Mohan Kankanhalli","orcid":"https://orcid.org/0000-0002-4846-2015"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mohan Kankanhalli","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4846-2015","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001893388"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":1.2952,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82850878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5634","last_page":"5644"},"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":0.9914000034332275,"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":0.9726999998092651,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.7821512222290039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512650489807129},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.7176094055175781},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6904894113540649},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.6177824139595032},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5838719606399536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5615292191505432},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5610311627388},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5103279948234558},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4530980885028839},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4409417510032654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40076494216918945},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3910970389842987},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.29729920625686646},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.17463627457618713},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15069258213043213},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09708526730537415}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.7821512222290039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512650489807129},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.7176094055175781},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6904894113540649},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.6177824139595032},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5838719606399536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615292191505432},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5610311627388},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5103279948234558},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4530980885028839},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4409417510032654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40076494216918945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3910970389842987},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.29729920625686646},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.17463627457618713},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15069258213043213},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09708526730537415},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7231895066","display_name":null,"funder_award_id":"U1936203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2956959730","https://openalex.org/W2963115613","https://openalex.org/W2969960436","https://openalex.org/W2997072136","https://openalex.org/W3090350559","https://openalex.org/W3099790621","https://openalex.org/W3160447289","https://openalex.org/W3174151851","https://openalex.org/W3174690404","https://openalex.org/W3176896951","https://openalex.org/W3177224328","https://openalex.org/W4205488143","https://openalex.org/W4225547367","https://openalex.org/W4225683910","https://openalex.org/W4225957036","https://openalex.org/W4292092982","https://openalex.org/W4297999738","https://openalex.org/W4304092731","https://openalex.org/W4312305353","https://openalex.org/W6600175564","https://openalex.org/W6600280466"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W4385488510","https://openalex.org/W4313191056","https://openalex.org/W3021007069","https://openalex.org/W4389518870","https://openalex.org/W2981750021","https://openalex.org/W4302773889","https://openalex.org/W4398163702"],"abstract_inverted_index":{"Visual":[0],"Commonsense":[1],"Reasoning":[2],"(VCR)":[3],"calls":[4],"for":[5,30,117],"explanatory":[6],"reasoning":[7],"behind":[8],"question":[9],"answering":[10],"over":[11],"visual":[12,87,170],"scenes.":[13],"To":[14],"achieve":[15],"this":[16,77,150],"goal,":[17],"a":[18],"model":[19,115],"is":[20,90],"required":[21],"to":[22,68,93],"provide":[23],"an":[24],"acceptable":[25],"rationale":[26],"as":[27],"the":[28,31,36,42,63,69,81,91,118,125,139,156,166],"reason":[29],"predicted":[32],"answers.":[33],"Progress":[34],"on":[35,55],"benchmark":[37],"dataset":[38],"stems":[39],"largely":[40],"from":[41,109,138],"recent":[43],"advancement":[44],"of":[45,103,124,141,160],"Vision-Language":[46],"Transformers":[47,83],"(VL":[48],"Transformers).":[49],"These":[50],"models":[51],"are":[52,66],"first":[53],"pre-trained":[54],"some":[56,135],"generic":[57],"large-scale":[58],"vision-text":[59],"datasets,":[60],"and":[61,122,145,158,162],"then":[62],"learned":[64],"representations":[65],"transferred":[67],"downstream":[70],"VCR":[71],"task.":[72],"Despite":[73],"their":[74],"attractive":[75],"performance,":[76],"paper":[78],"posits":[79],"that":[80],"VL":[82,105],"do":[84],"not":[85],"exhibit":[86],"commonsense,":[88],"which":[89],"key":[92],"VCR.":[94],"In":[95],"particular,":[96],"our":[97],"empirical":[98],"results":[99],"pinpoint":[100],"several":[101],"shortcomings":[102],"existing":[104],"Transformers:":[106],"small":[107],"gains":[108],"pre-training,":[110],"unexpected":[111],"language":[112],"bias,":[113],"limited":[114],"architecture":[116],"two":[119],"inseparable":[120],"sub-tasks,":[121],"neglect":[123],"important":[126],"object-tag":[127],"correlation.":[128],"With":[129],"these":[130],"findings,":[131],"we":[132],"tentatively":[133],"suggest":[134],"future":[136],"directions":[137],"aspect":[140],"dataset,":[142],"evaluation":[143],"metric,":[144],"training":[146],"tricks.":[147],"We":[148],"believe":[149],"work":[151],"could":[152],"make":[153],"researchers":[154],"revisit":[155],"intuition":[157],"goals":[159],"VCR,":[161],"thus":[163],"help":[164],"tackle":[165],"remaining":[167],"challenges":[168],"in":[169],"reasoning.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}