{"id":"https://openalex.org/W4413146213","doi":"https://doi.org/10.1109/cvpr52734.2025.02305","title":"Separation of powers: On segregating knowledge from observation in LLM-enabled knowledge-based visual question answering","display_name":"Separation of powers: On segregating knowledge from observation in LLM-enabled knowledge-based visual question answering","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146213","doi":"https://doi.org/10.1109/cvpr52734.2025.02305"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02305","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":"conference-paper","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/A5084415556","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-7728-916X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuo Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Tao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340143","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0001-9367-4757"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034640518","display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["Macquarie University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028024287","display_name":"Anton van den Hengel","orcid":"https://orcid.org/0000-0003-3027-8364"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anton Van Den Hengel","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041273628","display_name":"Qingming Huang","orcid":"https://orcid.org/0009-0003-8680-0278"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24753","last_page":"24762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.989300012588501,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9861999750137329,"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/question-answering","display_name":"Question answering","score":0.8609189987182617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6766799688339233},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5035457015037537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44875937700271606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4040657877922058},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35376256704330444}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8609189987182617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766799688339233},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5035457015037537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44875937700271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4040657877922058},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35376256704330444}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02305","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Knowledge-Based":[0],"visual":[1,95],"question":[2,89],"answering":[3],"(KBVQA)":[4],"separates":[5],"image":[6,99],"interpretation":[7],"and":[8,46,100,134,161],"knowledge":[9,45],"retrieval":[10],"into":[11,33],"separate":[12],"processes,":[13],"motivated":[14],"in":[15],"part":[16,155],"by":[17],"the":[18,31,42,66,71,88,98,147,153,157,164],"fact":[19],"that":[20,38,130],"they":[21],"are":[22],"very":[23],"different":[24],"tasks.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,39,110],"transform":[30],"KB-VQA":[32],"linguistic":[34],"question-answering":[35],"tasks":[36],"so":[37],"can":[40],"leverage":[41],"rich":[43],"world":[44],"strong":[47],"reasoning":[48],"abilities":[49],"of":[50,123,156],"Large":[51],"Language":[52],"Models":[53],"(LLMs).":[54],"The":[55],"caption-then-question":[56],"approach":[57],"to":[58,69,74,92,113],"KBVQA":[59,125,138],"has":[60],"been":[61],"effective,":[62],"but":[63],"relies":[64],"on":[65,121,146,152,163],"captioning":[67],"method":[68],"describe":[70],"detail":[72],"required":[73],"answer":[75],"every":[76],"possible":[77],"question.":[78],"We":[79],"propose":[80],"instead":[81],"a":[82,102,108,115],"Question-Aware":[83],"Captioner":[84],"(QACap),":[85],"which":[86],"uses":[87],"as":[90],"guidance":[91],"extract":[93],"correlated":[94],"information":[96],"from":[97],"generate":[101],"question-related":[103],"caption.":[104],"To":[105],"train":[106],"such":[107],"model,":[109],"utilize":[111],"GPT-4":[112],"build":[114],"corresponding":[116],"high-quality":[117],"question-aware":[118],"caption":[119],"dataset":[120,135],"top":[122],"existing":[124],"datasets.":[126],"Extensive":[127],"experiments":[128],"demonstrate":[129],"our":[131],"QACap":[132],"model":[133],"significantly":[136],"improve":[137],"performance.":[139],"Our":[140],"method,":[141],"QA-Cap,":[142],"achieves":[143],"68.2%":[144],"accuracy":[145],"OKVQA":[148],"validation":[149,159],"set,":[150,160],"73.4%":[151],"direct-answer":[154],"A-OKVQA":[158],"74.8%":[162],"multiple-choice":[165],"part,":[166],"all":[167],"setting":[168],"new":[169],"SOTA":[170],"benchmarks.":[171]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}