{"id":"https://openalex.org/W4409019037","doi":"https://doi.org/10.1109/bigcomp64353.2025.00084","title":"Exploring the Visual Perspective Taking of Vision-and-Language Model","display_name":"Exploring the Visual Perspective Taking of Vision-and-Language Model","publication_year":2025,"publication_date":"2025-02-09","ids":{"openalex":"https://openalex.org/W4409019037","doi":"https://doi.org/10.1109/bigcomp64353.2025.00084"},"language":"en","primary_location":{"id":"doi:10.1109/bigcomp64353.2025.00084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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/A5100738830","display_name":"Youngjun Lee","orcid":"https://orcid.org/0000-0002-9803-0253"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Young-Jun Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Computing,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015094039","display_name":"Ho\u2010Jin Choi","orcid":"https://orcid.org/0000-0002-3398-9543"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho-Jin Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Computing,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100738830"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06335566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"410","last_page":"411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12694","display_name":"Categorization, perception, and language","score":0.12120000272989273,"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"}},"topics":[{"id":"https://openalex.org/T12694","display_name":"Categorization, perception, and language","score":0.12120000272989273,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.06520000100135803,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.03790000081062317,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.775344967842102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6734802722930908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43213969469070435},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.37809082865715027},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3425820767879486},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17518803477287292}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.775344967842102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734802722930908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43213969469070435},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.37809082865715027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3425820767879486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17518803477287292}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigcomp64353.2025.00084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334869","display_name":"Korean National Police Agency","ror":"https://ror.org/05x57gp50"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4390874566","https://openalex.org/W6718625969","https://openalex.org/W6810334672","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2018871932","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Recently,":[0],"many":[1],"vision-and-language":[2,43,74],"models":[3,44,62,75],"have":[4],"demonstrated":[5],"remarkable":[6],"performance":[7],"in":[8,23,50],"various":[9],"multimodal":[10],"tasks":[11],"using":[12],"a":[13,30,51,55],"zero-shot":[14,52],"approach.":[15],"However,":[16],"they":[17],"lack":[18],"spatial":[19],"reasoning":[20],"abilities,":[21],"particularly":[22],"understanding":[24],"visuo-spatial":[25],"information":[26],"from":[27,69],"another\u2019s":[28,70],"perspective,":[29],"skill":[31],"known":[32],"as":[33],"visual":[34,47],"perspective":[35],"taking.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,58],"investigate":[41],"whether":[42],"can":[45],"develop":[46],"perspective-taking":[48],"abilities":[49],"manner.":[53],"Through":[54],"simple":[56],"experiment,":[57],"demonstrate":[59],"that":[60,73],"these":[61],"still":[63],"struggle":[64],"to":[65],"see":[66],"the":[67],"world":[68],"viewpoint,":[71],"suggesting":[72],"are":[76],"hindered":[77],"by":[78],"an":[79],"egocentric":[80],"bias.":[81]},"counts_by_year":[],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}