{"id":"https://openalex.org/W7204152083","doi":null,"title":"Who Did What to Whom? Visually Grounded Role Assignment in Humans but Not in Vision--Language Models","display_name":"Who Did What to Whom? Visually Grounded Role Assignment in Humans but Not in Vision--Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204152083"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt5jt8j974","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/5jt8j974","pdf_url":"https://escholarship.org/content/qt5jt8j974/qt5jt8j974.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 48, iss 0","raw_type":"article"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt5jt8j974/qt5jt8j974.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135027945","display_name":"Enjie Xu","orcid":"https://orcid.org/0009-0007-1750-2137","observed_orcids":["https://orcid.org/0009-0007-1750-2137"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Enjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033589524","display_name":"Ning Tang","orcid":"https://orcid.org/0000-0001-5715-6338","observed_orcids":["https://orcid.org/0000-0001-5715-6338","https://orcid.org/0009-0008-2726-0810"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Ning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147938326","display_name":"Alvin Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Alvin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015577544","display_name":"Joshua K. Hartshorne","orcid":"https://orcid.org/0000-0003-1240-3598","observed_orcids":["https://orcid.org/0000-0003-1240-3598"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hartshorne, Joshua K","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056335534","display_name":"Tao Gao","orcid":"https://orcid.org/0000-0002-6425-1568","observed_orcids":["https://orcid.org/0000-0002-6425-1568"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.6010416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9897000193595886,"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":0.9897000193595886,"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/T12694","display_name":"Categorization, perception, and language","score":0.007199999876320362,"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"}},{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8259999752044678},{"id":"https://openalex.org/keywords/human-ai-comparison","display_name":"human-AI comparison","score":0.6299999952316284},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.753000020980835},{"id":"https://openalex.org/keywords/stroop-effect","display_name":"Stroop interference","score":0.6359999775886536},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.656000018119812},{"id":"https://openalex.org/keywords/gpt-5","display_name":"GPT-5","score":0.9570000171661377},{"id":"https://openalex.org/keywords/event-understanding","display_name":"event understanding","score":0.5170000195503235}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5537999868392944},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5145000219345093},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39640000462532043},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3659999966621399},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2365568","wikidata":"https://www.wikidata.org/wiki/Q844664","display_name":"Uncanny valley","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C86658582","wikidata":"https://www.wikidata.org/wiki/Q1432778","display_name":"Social cognition","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt5jt8j974","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/5jt8j974","pdf_url":"https://escholarship.org/content/qt5jt8j974/qt5jt8j974.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 48, iss 0","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt5jt8j974","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/5jt8j974","pdf_url":"https://escholarship.org/content/qt5jt8j974/qt5jt8j974.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 48, iss 0","raw_type":"article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W7204152083.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414946472","https://openalex.org/W7153978741","https://openalex.org/W4414755216","https://openalex.org/W4409679134","https://openalex.org/W7222438283","https://openalex.org/W4417136530","https://openalex.org/W7143468641","https://openalex.org/W7214568406","https://openalex.org/W7165195376","https://openalex.org/W4400518804"],"abstract_inverted_index":{"Event":[0],"role":[1,98,101],"assignment":[2],"is":[3,20],"central":[4],"to":[5],"event":[6,114],"understanding":[7,159],"in":[8,23,160,172],"both":[9,134],"language":[10],"and":[11,45,57,74],"vision.":[12],"Crucially,":[13],"the":[14,112],"foundation":[15],"of":[16],"this":[17,37],"semantic":[18],"structure":[19],"likely":[21],"rooted":[22],"visual":[24,113,174],"experience.":[25],"However,":[26],"it":[27],"remains":[28],"unclear":[29],"whether":[30],"recent":[31],"vision\u2013language":[32],"models":[33,135],"(VLMs)":[34],"can":[35],"attain":[36],"fundamental":[38],"human":[39],"cognitive":[40],"capability.":[41],"To":[42],"compare":[43],"humans":[44,63,165],"VLMs,":[46],"we":[47,86],"conducted":[48],"two":[49],"studies":[50],"using":[51],"Heider\u2013Simmel\u2013style":[52],"animations":[53,94],"that":[54,153],"minimize":[55],"object":[56],"scene":[58],"semantics.":[59],"In":[60,83,127],"Study":[61,84,128,147],"1,":[62],"identified":[64],"roles":[65],"near":[66],"ceiling":[67],"(~97%),":[68],"whereas":[69],"VLMs":[70,108,154],"were":[71],"less":[72,75],"accurate":[73],"stable":[76],"across":[77],"actions":[78],"(GPT-5:":[79,117],"84%;":[80],"GPT-4o:":[81,119],"47%).":[82],"2,":[85],"introduced":[87],"a":[88,130,141,168],"Stroop-inspired":[89],"visual\u2013linguistic":[90],"mismatch":[91],"by":[92],"pairing":[93],"with":[95],"occasionally":[96],"incongruent":[97],"statements.":[99],"Humans\u2019":[100],"judgments":[102],"remained":[103],"highly":[104],"vision-consistent":[105,137],"(92.7%),":[106],"but":[107],"shifted":[109],"away":[110],"from":[111],"under":[115],"conflict":[116],"46.9%;":[118],"29.7%),":[120],"indicating":[121,167],"heavier":[122],"reliance":[123],"on":[124],"linguistic":[125,176],"cues.":[126],"3,":[129],"mismatch-shape":[131],"baseline":[132],"left":[133],"perfectly":[136],"(100.0%),":[138],"ruling":[139],"out":[140],"generic":[142],"object-recognition":[143],"failure":[144],"explanation":[145],"for":[146],"2.":[148],"Together,":[149],"these":[150],"results":[151],"demonstrate":[152],"do":[155],"not":[156],"ground":[157],"event-role":[158],"vision":[161],"as":[162,164],"reliably":[163],"do,":[166],"substantial":[169],"human\u2013VLM":[170],"gap":[171],"integrating":[173],"versus":[175],"information.":[177]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-25T00:00:00"}