{"id":"https://openalex.org/W4414360105","doi":"https://doi.org/10.24963/ijcai.2025/150","title":"Multi-Sourced Compositional Generalization in Visual Question Answering","display_name":"Multi-Sourced Compositional Generalization in Visual Question Answering","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360105","doi":"https://doi.org/10.24963/ijcai.2025/150"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/150","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5072669914","display_name":"Chuanhao Li","orcid":"https://orcid.org/0000-0002-9840-733X"},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuanhao Li","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102718191","display_name":"Wenbo Ye","orcid":"https://orcid.org/0000-0002-7136-4675"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Ye","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332655","display_name":"Zhen Li","orcid":"https://orcid.org/0000-0003-1166-9482"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Li","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888874","display_name":"Yuwei Wu","orcid":"https://orcid.org/0000-0002-0263-925X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Wu","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050560616","display_name":"Yunde Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunde Jia","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072669914"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I180726961","https://openalex.org/I4388482657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26745329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1341","last_page":"1349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9171000123023987,"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":0.9171000123023987,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9009000062942505,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8162000179290771},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5967000126838684},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5637000203132629},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5623000264167786},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43849998712539673},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.40059998631477356}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8162000179290771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469000220298767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6226999759674072},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.536899983882904},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2667999863624573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/150","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Compositional":[0],"generalization":[1,44,53],"is":[2,174],"the":[3,23,29,43,64,79,104,108,114,119,124,130,139,153],"ability":[4,45,81,141],"of":[5,26,66,82,142,162,166],"generalizing":[6],"novel":[7,40,48,163],"compositions":[8,32,164],"from":[9,34,91,168],"seen":[10],"primitives,":[11],"and":[12,71,107],"has":[13],"received":[14],"much":[15],"attention":[16],"in":[17,38,63,103,156],"vision-and-language":[18],"(V&L)":[19],"recently.":[20],"Due":[21],"to":[22,77,117],"multi-modal":[24],"nature":[25],"V&L":[27],"tasks,":[28],"primitives":[30,90,97,133,167],"composing":[31],"source":[33],"different":[35,92,135,169],"modalities,":[36],"resulting":[37],"multi-sourced":[39,47,51],"compositions.":[41],"However,":[42],"over":[46],"compositions,":[49],"i.e.,":[50],"compositional":[52],"(MSCG)":[54],"remains":[55],"unexplored.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,145],"explore":[61],"MSCG":[62,80,140],"context":[65],"visual":[67],"question":[68],"answering":[69],"(VQA),":[70],"propose":[72],"a":[73,147],"retrieval-augmented":[74],"training":[75,105],"framework":[76],"enhance":[78],"VQA":[83,143],"models":[84],"by":[85],"learning":[86],"unified":[87],"representations":[88,128],"for":[89,100,129],"modalities.":[93,136,170],"Specifically,":[94],"semantically":[95],"equivalent":[96],"are":[98,111],"retrieved":[99,109],"each":[101],"primitive":[102,116],"samples,":[106],"features":[110],"aggregated":[112],"with":[113],"original":[115],"refine":[118],"model.":[120],"This":[121],"process":[122],"helps":[123],"model":[125],"learn":[126],"consistent":[127],"same":[131],"semantic":[132],"across":[134],"To":[137],"evaluate":[138],"models,":[144],"construct":[146],"new":[148],"GQA-MSCG":[149,172],"dataset":[150,173],"based":[151],"on":[152],"GQA":[154],"dataset,":[155],"which":[157],"samples":[158],"include":[159],"three":[160],"types":[161],"composed":[165],"The":[171],"available":[175],"at":[176],"https://github.com/NeverMoreLCH/MSCG.":[177]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}