{"id":"https://openalex.org/W3023745006","doi":null,"title":"Probing Text Models for Common Ground with Visual Representations","display_name":"Probing Text Models for Common Ground with Visual Representations","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3023745006","mag":"3023745006"},"language":"en","primary_location":{"id":"mag:3023745006","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2005.00619","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2005.00619","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068360032","display_name":"Gabriel Ilharco","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Ilharco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030637764","display_name":"Rowan Zellers","orcid":"https://orcid.org/0000-0003-1361-9868","observed_orcids":["https://orcid.org/0000-0003-1361-9868"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rowan Zellers","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1361-9868","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576595","display_name":"Ali Farhadi","orcid":"https://orcid.org/0000-0001-7249-2380","observed_orcids":["https://orcid.org/0000-0001-7249-2380"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Farhadi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7249-2380","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082305994","display_name":"Hannaneh Hajishirzi","orcid":"https://orcid.org/0000-0002-1055-6657","observed_orcids":["https://orcid.org/0000-0002-1055-6657"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hannaneh Hajishirzi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1055-6657","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"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":0.9911999702453613,"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":0.9911999702453613,"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":0.007300000172108412,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0005000000237487257,"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/common-ground","display_name":"common ground","score":0.7020000219345093},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.5070000290870667},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.5839999914169312},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.5019999742507935},{"id":"https://openalex.org/keywords/cross-modal-representation-learning","display_name":"cross-modal representation learning","score":0.5149999856948853},{"id":"https://openalex.org/keywords/unseen-object-categories","display_name":"unseen object categories","score":0.6000000238418579},{"id":"https://openalex.org/keywords/human-performance-comparison","display_name":"human performance comparison","score":0.5759999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058945298194885},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6896024942398071},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6764308214187622},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6518010497093201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6228910684585571},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6193280816078186},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5746479034423828},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49312230944633484},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4442831575870514},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44093915820121765},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11842000484466553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10324046015739441},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07256883382797241},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3023745006","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2005.00619","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3023745006","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2005.00619","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2107019937","https://openalex.org/W2277195237","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2793978524","https://openalex.org/W2886641317","https://openalex.org/W2903073381","https://openalex.org/W2906152891","https://openalex.org/W2948947170","https://openalex.org/W2950104027","https://openalex.org/W2962749469","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963583512","https://openalex.org/W2964204621","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2970862333","https://openalex.org/W2975059944","https://openalex.org/W3008686018"],"related_works":["https://openalex.org/W3181367772","https://openalex.org/W156899190","https://openalex.org/W3049616075","https://openalex.org/W4283215748","https://openalex.org/W3212433538","https://openalex.org/W4403051422","https://openalex.org/W4386464522","https://openalex.org/W4389524503","https://openalex.org/W4386065408","https://openalex.org/W4300978570"],"abstract_inverted_index":{"Vision,":[0],"as":[1,80],"a":[2,9,30,51,89],"central":[3],"component":[4],"of":[5,61,88],"human":[6],"perception,":[7],"plays":[8],"fundamental":[10],"role":[11],"in":[12,42,46,123,143],"shaping":[13],"natural":[14],"language.":[15],"To":[16],"better":[17],"understand":[18],"how":[19],"text":[20,43],"models":[21,73],"are":[22],"connected":[23],"to":[24,57,64,86,95],"our":[25],"visual":[26,66],"perceptions,":[27],"we":[28,116,129],"propose":[29],"method":[31],"for":[32,141],"examining":[33],"the":[34,65,103,119],"similarities":[35],"between":[36],"neural":[37],"representations":[38,60,71],"extracted":[39],"from":[40,72,110],"words":[41,63],"and":[44,146],"objects":[45,122],"images.":[47],"Our":[48],"approach":[49],"uses":[50],"lightweight":[52],"probing":[53],"model":[54],"that":[55,70,98,118,131],"learns":[56],"map":[58],"language":[59],"concrete":[62],"domain.":[67],"We":[68],"find":[69,117],"trained":[74],"on":[75],"purely":[76],"textual":[77],"data,":[78],"such":[79],"BERT,":[81],"can":[82],"be":[83],"nontrivially":[84],"mapped":[85],"those":[87],"vision":[90],"model.":[91],"Such":[92],"mappings":[93,108],"generalize":[94],"object":[96],"categories":[97],"were":[99],"never":[100],"seen":[101],"by":[102],"probe":[104],"during":[105],"training,":[106],"unlike":[107],"learned":[109],"permuted":[111],"or":[112],"random":[113],"representations.":[114],"Moreover,":[115],"context":[120],"surrounding":[121],"sentences":[124],"greatly":[125],"impacts":[126],"performance.":[127],"Finally,":[128],"show":[130],"humans":[132],"significantly":[133],"outperform":[134],"all":[135],"examined":[136],"models,":[137],"suggesting":[138],"considerable":[139],"room":[140],"improvement":[142],"representation":[144],"learning":[145],"grounding.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2020-05-13T00:00:00"}