{"id":"https://openalex.org/W4406611244","doi":"https://doi.org/10.1109/smc54092.2024.10832004","title":"Enhancing GPT-3.5 for Knowledge-Based VQA with In-Context Prompt Learning and Image Captioning","display_name":"Enhancing GPT-3.5 for Knowledge-Based VQA with In-Context Prompt Learning and Image Captioning","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611244","doi":"https://doi.org/10.1109/smc54092.2024.10832004"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10832004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10832004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5100872625","display_name":"Yuling Yang","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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuling Yang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102823047","display_name":"Cong Cao","orcid":"https://orcid.org/0000-0002-6853-6421"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Cao","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102878238","display_name":"Fangfang Yuan","orcid":"https://orcid.org/0000-0002-1255-1999"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangfang Yuan","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114348454","display_name":"Shuai Zeng","orcid":"https://orcid.org/0009-0006-9661-8236"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zeng","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102783832","display_name":"Dakui Wang","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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dakui Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101651401","display_name":"Yanbing Liu","orcid":"https://orcid.org/0000-0001-8068-8316"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbing Liu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4030","last_page":"4035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9711999893188477,"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":0.9711999893188477,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9707000255584717,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9182999730110168,"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/closed-captioning","display_name":"Closed captioning","score":0.9651432037353516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7559754848480225},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6735482215881348},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5722307562828064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.425750732421875},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3642966151237488},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34266799688339233},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3276355266571045},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3238568902015686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32232430577278137}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9651432037353516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559754848480225},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6735482215881348},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5722307562828064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.425750732421875},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3642966151237488},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34266799688339233},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3276355266571045},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3238568902015686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32232430577278137},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10832004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10832004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3084162778","display_name":null,"funder_award_id":"2023YFC3303800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2016089260","https://openalex.org/W2080133951","https://openalex.org/W2947312908","https://openalex.org/W3035454069","https://openalex.org/W3093200502","https://openalex.org/W3101703188","https://openalex.org/W3139224848","https://openalex.org/W3172845486","https://openalex.org/W3173220247","https://openalex.org/W3199693760","https://openalex.org/W4200635486","https://openalex.org/W4282920689","https://openalex.org/W4283777642","https://openalex.org/W4304092583","https://openalex.org/W4312289196","https://openalex.org/W4312344082","https://openalex.org/W4385570217","https://openalex.org/W4386065596","https://openalex.org/W4386159793","https://openalex.org/W4388186922"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Traditional":[0],"visual":[1,49,64,153],"question":[2],"answering":[3],"(VQA)":[4],"often":[5,60],"falls":[6],"short":[7],"as":[8,168],"merely":[9],"relying":[10],"on":[11,198],"image":[12,69,128],"information":[13],"is":[14],"insufficient":[15],"to":[16,54,73,139,182],"answer":[17],"given":[18],"questions.":[19],"Therefore,":[20],"Knowledge-Based":[21,120],"Visual":[22,121],"Question":[23,122],"Answering":[24,123],"(KB-VQA)":[25,124],"has":[26],"emerged.":[27],"Typically,":[28],"KB-VQA":[29],"involves":[30],"first":[31],"retrieving":[32],"knowledge":[33,36,42,78,81,93,109,162,170,173],"from":[34,62,103],"external":[35,77],"bases,":[37,79],"then":[38],"using":[39,125],"the":[40,46,74,90,97,104,108,147,158,199,204],"retrieved":[41,80],"in":[43,107],"conjunction":[44],"with":[45],"understanding":[47,151],"of":[48,76,92,152,207],"content":[50],"for":[51,119,160,172,191],"joint":[52],"reasoning":[53,99],"predict":[55,183],"answers.":[56,184],"However,":[57],"current":[58],"models":[59],"suffer":[61],"weak":[63],"perception":[65],"capabilities":[66],"when":[67],"processing":[68],"information.":[70,88,154],"Additionally,":[71],"due":[72],"incompleteness":[75],"may":[82,101],"contain":[83],"noise":[84],"or":[85],"even":[86],"irrelevant":[87],"Moreover,":[89,155],"re-embedding":[91],"text":[94,179],"features":[95],"during":[96,180],"model's":[98,150],"process":[100],"deviate":[102],"original":[105],"meanings":[106],"base.":[110],"To":[111],"address":[112],"these":[113],"challenges,":[114],"we":[115,156,186],"propose":[116],"a":[117,169],"method":[118],"GPT-3.5,":[126],"leveraging":[127],"captions":[129],"and":[130,175],"in-context":[131,194],"prompts.":[132],"We":[133],"utilize":[134],"an":[135],"advanced":[136],"captioning":[137],"model":[138],"convert":[140],"images":[141],"into":[142],"accurate":[143],"textual":[144],"representations,":[145],"enhancing":[146],"large":[148],"language":[149],"eliminate":[157],"need":[159],"additional":[161],"bases":[163],"by":[164],"directly":[165],"employing":[166],"GPT-3.5":[167],"base":[171],"retrieval":[174],"generate":[176],"logically":[177],"consistent":[178],"inference":[181],"Furthermore,":[185],"enhance":[187],"GPT-3.5's":[188],"question-answering":[189],"capability":[190],"VQA":[192],"through":[193],"prompt":[195],"learning.":[196],"Experiments":[197],"public":[200],"OK-VQA":[201],"dataset":[202],"demonstrate":[203],"superior":[205],"performance":[206],"our":[208],"model.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}