{"id":"https://openalex.org/W4392902969","doi":"https://doi.org/10.1109/icassp48485.2024.10448321","title":"Prompting Large Language Models with Fine-Grained Visual Relations from Scene Graph for Visual Question Answering","display_name":"Prompting Large Language Models with Fine-Grained Visual Relations from Scene Graph for Visual Question Answering","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902969","doi":"https://doi.org/10.1109/icassp48485.2024.10448321"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102978348","display_name":"Jiapeng Liu","orcid":"https://orcid.org/0009-0002-0249-908X"},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiapeng Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences","School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085542141","display_name":"Chengyang Fang","orcid":"https://orcid.org/0000-0002-3583-9119"},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyang Fang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences","School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420654","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1943-8219"},"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":"Liang Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109346446","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-5888-6735"},"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":"Bing Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089289613","display_name":"Dayong Hu","orcid":"https://orcid.org/0009-0007-2232-1437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dayong Hu","raw_affiliation_strings":["Heilongjiang Network Space Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heilongjiang Network Space Research Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101021225","display_name":"Can Ma","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":"Can Ma","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3147,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84321979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8125","last_page":"8129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9907000064849854,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9800999760627747,"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/computer-science","display_name":"Computer science","score":0.7022260427474976},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6442298889160156},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6078402400016785},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.602875828742981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5382852554321289},{"id":"https://openalex.org/keywords/competitor-analysis","display_name":"Competitor analysis","score":0.5308101177215576},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5147500038146973},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5003554821014404},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4919383227825165},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49023157358169556},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.42516955733299255},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11130106449127197},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1050521731376648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7022260427474976},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6442298889160156},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6078402400016785},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.602875828742981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382852554321289},{"id":"https://openalex.org/C127576917","wikidata":"https://www.wikidata.org/wiki/Q624630","display_name":"Competitor analysis","level":2,"score":0.5308101177215576},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5147500038146973},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5003554821014404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4919383227825165},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49023157358169556},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.42516955733299255},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11130106449127197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1050521731376648},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2963518342","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W3035520037","https://openalex.org/W3090449556","https://openalex.org/W3131825083","https://openalex.org/W3173220247","https://openalex.org/W3181158454","https://openalex.org/W3199693760","https://openalex.org/W3204138855","https://openalex.org/W3204281258","https://openalex.org/W4225868495","https://openalex.org/W4226278401","https://openalex.org/W4226321975","https://openalex.org/W4281944818","https://openalex.org/W4285605365","https://openalex.org/W4288286281","https://openalex.org/W4292779060","https://openalex.org/W4385567175","https://openalex.org/W4385574156","https://openalex.org/W4386065596","https://openalex.org/W4386076140","https://openalex.org/W6765591853","https://openalex.org/W6766904570","https://openalex.org/W6778883912","https://openalex.org/W6789909235","https://openalex.org/W6798350552","https://openalex.org/W6802115918","https://openalex.org/W6810738896","https://openalex.org/W6838989559"],"related_works":["https://openalex.org/W4297783004","https://openalex.org/W2914694625","https://openalex.org/W4389782456","https://openalex.org/W2964061310","https://openalex.org/W2963477107","https://openalex.org/W2231285690","https://openalex.org/W3093385053","https://openalex.org/W4389682534","https://openalex.org/W4390091918","https://openalex.org/W3045060014"],"abstract_inverted_index":{"Visual":[0,83],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4],"a":[5,75,97],"task":[6],"that":[7,78],"requires":[8],"models":[9],"to":[10,32,45,107,125,144],"comprehend":[11,126],"both":[12],"questions":[13],"and":[14,96],"images.":[15,50],"An":[16],"increasing":[17],"number":[18],"of":[19,27,58,67,90],"works":[20],"are":[21],"leveraging":[22],"the":[23,56,64,109,127,133],"strong":[24,146],"reasoning":[25,65],"capabilities":[26],"Large":[28],"Language":[29],"Models":[30],"(LLMs)":[31],"address":[33],"VQA.":[34,86],"These":[35],"methods":[36],"typically":[37],"utilize":[38],"image":[39],"captions":[40,53],"as":[41,120],"visual":[42,111],"text":[43],"description":[44],"aid":[46],"LLMs":[47,80,124],"in":[48],"comprehending":[49],"However,":[51],"these":[52],"often":[54],"overlooking":[55],"relations":[57,112],"fine-grained":[59,110],"objects,":[60],"which":[61,116],"will":[62,117],"limit":[63],"capability":[66],"LLMs.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"present":[73],"PFVR,":[74],"modular":[76],"framework":[77],"Prompts":[79],"with":[81],"Fine-grained":[82],"Relationships":[84],"for":[85,123],"PFVR":[87,139],"primarily":[88],"consists":[89],"an":[91],"answer-guided":[92],"generation":[93],"module":[94,100],"(AGG)":[95],"question-guided":[98],"filtering":[99],"(QGF).":[101],"The":[102],"two":[103],"modules":[104],"can":[105],"combine":[106],"extract":[108],"from":[113],"scene":[114],"graph,":[115],"finally":[118],"serve":[119],"crucial":[121],"context":[122],"image.":[128],"Extensive":[129],"experiments":[130],"conducted":[131],"on":[132],"popular":[134],"VQA":[135,147],"dataset,":[136],"GQA,":[137],"confirm":[138],"achieves":[140],"state-of-the-art":[141],"results":[142],"compared":[143],"other":[145],"competitors,":[148],"demonstrating":[149],"its":[150],"exceptional":[151],"effectiveness.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}