{"id":"https://openalex.org/W4411630085","doi":"https://doi.org/10.18653/v1/2024.eacl-long.146","title":"Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models","display_name":"Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630085","doi":"https://doi.org/10.18653/v1/2024.eacl-long.146"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.146","pdf_url":"https://aclanthology.org/2024.eacl-long.146.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-long.146.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004491730","display_name":"Zhuowan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuowan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022344556","display_name":"Cihang Xie","orcid":"https://orcid.org/0000-0003-1243-8045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cihang Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075825791","display_name":"Benjamin Van Durme","orcid":"https://orcid.org/0000-0003-4328-4288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Van Durme","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan Yuille","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2378","last_page":"2390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.49889999628067017,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.49889999628067017,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.46860000491142273,"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/T12694","display_name":"Categorization, perception, and language","score":0.42179998755455017,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6946606040000916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6596758365631104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082816481590271},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4657488763332367},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.4132058918476105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24621301889419556}],"concepts":[{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6946606040000916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596758365631104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082816481590271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4657488763332367},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.4132058918476105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24621301889419556}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.146","pdf_url":"https://aclanthology.org/2024.eacl-long.146.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-long.146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.146","pdf_url":"https://aclanthology.org/2024.eacl-long.146.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7734489741","display_name":null,"funder_award_id":"N00014-23-1-2641","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630085.pdf","grobid_xml":"https://content.openalex.org/works/W4411630085.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W3112765659","https://openalex.org/W2963364736","https://openalex.org/W2808113865","https://openalex.org/W2112408611","https://openalex.org/W3018074947","https://openalex.org/W256313897","https://openalex.org/W58061955","https://openalex.org/W4232784337","https://openalex.org/W4366284213"],"abstract_inverted_index":{"Despite":[0],"the":[1,30,50,53,98],"impressive":[2],"advancements":[3],"achieved":[4],"through":[5],"vision-and-language":[6,35],"pretraining,":[7],"it":[8],"remains":[9],"unclear":[10],"whether":[11],"this":[12,22],"joint":[13],"learning":[14],"paradigm":[15],"can":[16],"help":[17],"understand":[18],"each":[19],"individual":[20],"modality.In":[21],"work,":[23],"we":[24],"conduct":[25],"a":[26,42,57],"comparative":[27],"analysis":[28],"of":[29,45,52,100],"visual":[31,103],"representations":[32,55],"in":[33,56,102],"existing":[34],"models":[36,39,66,80],"and":[37,75,105],"visiononly":[38],"by":[40],"probing":[41],"broad":[43],"range":[44],"tasks,":[46],"aiming":[47],"to":[48],"assess":[49],"quality":[51],"learned":[54],"nuanced":[58],"manner.Interestingly,":[59],"our":[60,93],"empirical":[61,109],"observations":[62],"suggest":[63],"that":[64,87],"visionand-language":[65],"are":[67,81],"better":[68],"at":[69,83,118],"label":[70],"prediction":[71,85],"tasks":[72,86],"like":[73],"object":[74],"attribute":[76],"prediction,":[77],"while":[78],"vision-only":[79],"stronger":[82],"dense":[84],"require":[88],"more":[89],"localized":[90],"information.We":[91],"hope":[92],"study":[94],"sheds":[95],"light":[96],"on":[97],"role":[99],"language":[101],"learning,":[104],"serves":[106],"as":[107],"an":[108],"guide":[110],"for":[111],"various":[112],"pretrained":[113],"models.Code":[114],"will":[115],"be":[116],"released":[117],"https:":[119],"//github.com/Lizw14/visual_probing.":[120]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
