{"id":"https://openalex.org/W4405304393","doi":"https://doi.org/10.1109/besc64747.2024.10780559","title":"Effective Retrieval Augmentation for Knowledge-Based Vision Question Answering","display_name":"Effective Retrieval Augmentation for Knowledge-Based Vision Question Answering","publication_year":2024,"publication_date":"2024-08-16","ids":{"openalex":"https://openalex.org/W4405304393","doi":"https://doi.org/10.1109/besc64747.2024.10780559"},"language":"en","primary_location":{"id":"doi:10.1109/besc64747.2024.10780559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc64747.2024.10780559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 11th International Conference on Behavioural and Social Computing (BESC)","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/A5103326001","display_name":"Jiaqi Deng","orcid":"https://orcid.org/0009-0008-5426-127X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jiaqi Deng","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103326001"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57481786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9521999955177307,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9521999955177307,"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":0.8793514370918274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7305142879486084},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6815415620803833}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8793514370918274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305142879486084},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6815415620803833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/besc64747.2024.10780559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc64747.2024.10780559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 11th International Conference on Behavioural and Social Computing (BESC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1897761818","https://openalex.org/W2080133951","https://openalex.org/W2947312908","https://openalex.org/W2963954913","https://openalex.org/W3139224848","https://openalex.org/W3155855665","https://openalex.org/W3196798856","https://openalex.org/W4221155360","https://openalex.org/W4226321975","https://openalex.org/W4254415482","https://openalex.org/W4283777642","https://openalex.org/W4312971273","https://openalex.org/W4384774018","https://openalex.org/W4385573236","https://openalex.org/W4385573463","https://openalex.org/W4385574177","https://openalex.org/W4386057720","https://openalex.org/W4387969587","https://openalex.org/W4389523839"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Knowledge-based":[0],"Vision":[1],"Question":[2],"Answering":[3],"(KBVQA)":[4],"systems":[5,32,79,134],"aim":[6],"to":[7,26,42,81,115,124,168],"answer":[8,93],"natural":[9],"language":[10],"questions":[11,102],"grounded":[12],"in":[13,66,132,143,157,185],"image":[14],"contents":[15],"by":[16],"retrieving":[17],"and":[18,68,100,135,160,166,172],"integrating":[19],"relevant":[20],"knowledge":[21,24,87,158],"from":[22,38,85],"external":[23,86],"bases":[25],"generate":[27],"the":[28,92,107,112,148,170,173],"final":[29],"answers.":[30],"These":[31],"have":[33],"diverse":[34],"application":[35],"scenarios":[36],"ranging":[37],"general":[39],"cross-modal":[40],"understanding":[41],"specialized":[43],"domains":[44],"like":[45],"healthcare":[46],"or":[47],"robotics.":[48],"While":[49],"significant":[50],"progress":[51],"has":[52],"been":[53],"made,":[54],"several":[55],"key":[56],"obstacles":[57],"still":[58,104],"persist:":[59],"(1)":[60],"multimodal":[61,152],"pretrained":[62],"models":[63],"remain":[64],"underinvestigated":[65],"KB-VQA,":[67],"existing":[69,130],"methods":[70],"can":[71],"incur":[72],"high":[73],"computational":[74],"costs;":[75],"(2)":[76],"Current":[77],"KB-VQA":[78,133,176],"tend":[80],"extract":[82],"noisy":[83],"information":[84],"sources,":[88],"which":[89],"might":[90],"impair":[91],"quality;":[94],"(3)":[95],"Cross-modal":[96],"interactions":[97],"between":[98,164],"images":[99,165],"textual":[101],"are":[103],"insufficient":[105],"at":[106],"current":[108],"state,":[109],"potentially":[110],"limiting":[111],"system's":[113],"ability":[114],"comprehend":[116],"essential":[117],"contents.":[118],"This":[119],"doctoral":[120],"consortium":[121],"paper":[122],"intends":[123],"provide":[125],"a":[126],"comprehensive":[127],"review":[128],"of":[129,150,175],"efforts":[131],"offer":[136],"insights":[137],"into":[138],"potential":[139],"future":[140],"research":[141,179],"directions":[142],"this":[144,186],"domain.":[145],"We":[146],"highlight":[147],"importance":[149],"improving":[151],"pretraining":[153],"techniques,":[154],"mitigating":[155],"noise":[156],"integration,":[159],"enhancing":[161],"interaction":[162],"modeling":[163],"texts":[167],"improve":[169],"performance":[171],"robustness":[174],"systems.":[177],"Proposed":[178],"methodology":[180],"will":[181],"also":[182],"be":[183],"outlined":[184],"paper.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}