{"id":"https://openalex.org/W4413145245","doi":"https://doi.org/10.1109/cvpr52734.2025.02091","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA","display_name":"Embodied Scene Understanding for Vision Language Models via MetaVQA","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145245","doi":"https://doi.org/10.1109/cvpr52734.2025.02091"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5041529443","display_name":"Weizhen Wang","orcid":"https://orcid.org/0000-0002-0081-9660"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weizhen Wang","raw_affiliation_strings":["University of California,Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054458304","display_name":"Chenda Duan","orcid":"https://orcid.org/0009-0003-8652-3960"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenda Duan","raw_affiliation_strings":["University of California,Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109521346","display_name":"Zhenghao Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenghao Peng","raw_affiliation_strings":["University of California,Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385833","display_name":"Yuxin Liu","orcid":"https://orcid.org/0000-0002-8632-2910"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxin Liu","raw_affiliation_strings":["University of California,Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033444412","display_name":"Bolei Zhou","orcid":"https://orcid.org/0000-0003-4030-0684"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bolei Zhou","raw_affiliation_strings":["University of California,Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041529443"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":2.6381,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91117936,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"22453","last_page":"22464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9945999979972839,"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":0.9945999979972839,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9438999891281128,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.925599992275238,"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/embodied-cognition","display_name":"Embodied cognition","score":0.8667266368865967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6711618900299072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4821597933769226},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4542170464992523},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4140101373195648},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.32247763872146606},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11838850378990173}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8667266368865967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711618900299072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4821597933769226},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4542170464992523},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4140101373195648},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.32247763872146606},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11838850378990173}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Vision":[0],"Language":[1],"Models":[2],"(VLMs)":[3],"demonstrate":[4],"significant":[5],"potential":[6],"as":[7],"embodied":[8,105],"AI":[9],"agents":[10],"for":[11,20],"various":[12],"mobility":[13],"applications.":[14],"However,":[15],"a":[16,37],"standardized,":[17],"closed-loop":[18,59],"benchmark":[19,39],"evaluating":[21],"their":[22,104],"spatial":[23,48],"reasoning":[24],"and":[25,43,50,58,65,72,89],"sequential":[26],"decision-making":[27],"capabilities":[28],"is":[29,109,139],"lacking.":[30],"To":[31],"address":[32],"this,":[33],"we":[34],"present":[35],"MetaVQA:":[36],"comprehensive":[38],"designed":[40],"to":[41,75,133],"assess":[42],"enhance":[44],"VLMs\u2019":[45],"understanding":[46],"of":[47],"relationships":[49],"scene":[51,106],"dynamics":[52],"through":[53],"Visual":[54],"Question":[55],"Answering":[56],"(VQA)":[57],"simulations.":[60],"MetaVQA":[61,100],"leverages":[62],"Set-of-Mark":[63],"prompting":[64],"top-down":[66],"view":[67],"ground-truth":[68],"annotations":[69],"from":[70,131],"nuScenes":[71],"Waymo":[73],"datasets":[74],"automatically":[76],"generate":[77],"extensive":[78],"question-answer":[79],"pairs":[80],"based":[81],"on":[82],"diverse":[83],"real-world":[84,134],"traffic":[85],"scenarios,":[86],"ensuring":[87],"object-centric":[88],"context-rich":[90],"instructions.":[91],"Our":[92],"experiments":[93],"show":[94],"that":[95],"fine-tuning":[96],"VLMs":[97],"with":[98],"the":[99,126],"Dataset":[101],"significantly":[102],"improves":[103],"understanding,":[107],"which":[108],"evident":[110],"not":[111],"only":[112],"in":[113,119],"improved":[114],"VQA":[115],"accuracy":[116],"but":[117],"also":[118],"emerging":[120],"safety-aware":[121],"driving":[122],"maneuvers.":[123],"In":[124],"addition,":[125],"learning":[127],"exhibits":[128],"strong":[129],"transferability":[130],"simulation":[132],"observation.":[135],"The":[136],"project":[137],"webpage":[138],"at":[140],"https://metadriverse.github.io/metavqa.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}