{"id":"https://openalex.org/W4415709530","doi":"https://doi.org/10.1109/icme59968.2025.11209827","title":"A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering","display_name":"A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709530","doi":"https://doi.org/10.1109/icme59968.2025.11209827"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5010737776","display_name":"Zhiyue Liu","orcid":"https://orcid.org/0000-0001-6432-7836"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyue Liu","raw_affiliation_strings":["Guangxi University,School of Computer, Electronics and Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer, Electronics and Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103171351","display_name":"Sihang Liu","orcid":"https://orcid.org/0009-0001-5193-4319"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihang Liu","raw_affiliation_strings":["Guangxi University,School of Computer, Electronics and Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer, Electronics and Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675903","display_name":"Jinyuan Liu","orcid":"https://orcid.org/0000-0003-0488-0263"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyuan Liu","raw_affiliation_strings":["Guangxi University,School of Computer, Electronics and Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer, Electronics and Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102017127","display_name":"Xinru Zhang","orcid":"https://orcid.org/0000-0001-7605-2913"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinru Zhang","raw_affiliation_strings":["Guangxi University,School of Computer, Electronics and Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer, Electronics and Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010737776"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31291577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.993399977684021,"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":0.993399977684021,"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":0.002099999925121665,"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":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7771999835968018},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5954999923706055},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/knowledge-retrieval","display_name":"Knowledge retrieval","score":0.47920000553131104},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4763999879360199},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.451200008392334},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.39890000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112999796867371},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7771999835968018},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5954999923706055},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C2780613888","wikidata":"https://www.wikidata.org/wiki/Q6423394","display_name":"Knowledge retrieval","level":3,"score":0.47920000553131104},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C56289545","wikidata":"https://www.wikidata.org/wiki/Q6423376","display_name":"Knowledge integration","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":16,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2016089260","https://openalex.org/W2080133951","https://openalex.org/W2947312908","https://openalex.org/W2966683369","https://openalex.org/W3172845486","https://openalex.org/W3196798856","https://openalex.org/W3199693760","https://openalex.org/W4226321975","https://openalex.org/W4312381519","https://openalex.org/W4385574156","https://openalex.org/W4385574177","https://openalex.org/W4386065596","https://openalex.org/W4389519546","https://openalex.org/W4390873086","https://openalex.org/W4404782870"],"related_works":[],"abstract_inverted_index":{"Knowledge-based":[0],"visual":[1],"question":[2],"answering":[3,41,136],"(KB-VQA)":[4],"requires":[5],"a":[6,48,119],"model":[7,126],"to":[8,15,107,127],"understand":[9],"images":[10],"and":[11,66,109,153,156],"utilize":[12],"external":[13],"knowledge":[14,29,34,52,64,71,121,129],"provide":[16],"accurate":[17,152],"answers.":[18],"Existing":[19],"approaches":[20],"often":[21],"directly":[22],"augment":[23],"models":[24,106],"with":[25,51],"retrieved":[26,100],"information":[27],"from":[28,78,113],"sources":[30],"while":[31],"ignoring":[32],"substantial":[33],"redundancy,":[35],"which":[36],"introduces":[37],"noise":[38,61],"into":[39],"the":[40,58,79,87,99,125,137,141,149],"process.":[42],"To":[43],"address":[44],"this,":[45],"we":[46,102,117],"propose":[47],"training-free":[49],"framework":[50,74,147],"focusing":[53],"for":[54,70],"KB-VQA,":[55],"that":[56,85,94,160],"mitigates":[57],"impact":[59],"of":[60,89,143,151],"by":[62],"enhancing":[63],"relevance":[65],"reducing":[67],"redundancy.":[68],"First,":[69],"retrieval,":[72],"our":[73],"concludes":[75],"essential":[76],"parts":[77],"image-question":[80],"pairs,":[81],"creating":[82],"low-noise":[83],"queries":[84],"enhance":[86],"retrieval":[88],"highly":[90],"relevant":[91],"knowledge.":[92,114],"Considering":[93],"redundancy":[95],"still":[96],"persists":[97],"in":[98,135],"knowledge,":[101,155],"then":[103],"prompt":[104],"large":[105],"identify":[108],"extract":[110],"answer-beneficial":[111],"segments":[112],"In":[115],"addition,":[116],"introduce":[118],"selective":[120],"integration":[122],"strategy,":[123],"allowing":[124],"incorporate":[128],"only":[130],"when":[131],"it":[132,161],"lacks":[133],"confidence":[134],"question,":[138],"thereby":[139],"mitigating":[140],"influence":[142],"redundant":[144],"information.":[145],"Our":[146],"enables":[148],"acquisition":[150],"critical":[154],"extensive":[157],"experiments":[158],"demonstrate":[159],"outperforms":[162],"state-of-the-art":[163],"methods.":[164]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}