{"id":"https://openalex.org/W4320507221","doi":"https://doi.org/10.1145/3579051.3579073","title":"Knowledge-Enhanced Visual Question Answering with Multi-modal Joint Guidance","display_name":"Knowledge-Enhanced Visual Question Answering with Multi-modal Joint Guidance","publication_year":2022,"publication_date":"2022-10-27","ids":{"openalex":"https://openalex.org/W4320507221","doi":"https://doi.org/10.1145/3579051.3579073"},"language":"en","primary_location":{"id":"doi:10.1145/3579051.3579073","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579051.3579073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Joint Conference on Knowledge Graphs","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/A5051840046","display_name":"Jianfeng Wang","orcid":"https://orcid.org/0000-0001-7940-1189"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Wang","raw_affiliation_strings":["Fudan University, Academy for Engineering and Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-7940-1189","affiliations":[{"raw_affiliation_string":"Fudan University, Academy for Engineering and Technology, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103229186","display_name":"Anda Zhang","orcid":"https://orcid.org/0000-0002-6505-4566"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anda Zhang","raw_affiliation_strings":["Fudan University, Academy for Engineering and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-6505-4566","affiliations":[{"raw_affiliation_string":"Fudan University, Academy for Engineering and Technology, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065672874","display_name":"Huifang Du","orcid":"https://orcid.org/0000-0002-5241-7620"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifang Du","raw_affiliation_strings":["Tongji University, College of Design and Innovation, China"],"raw_orcid":"https://orcid.org/0000-0002-5241-7620","affiliations":[{"raw_affiliation_string":"Tongji University, College of Design and Innovation, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039059501","display_name":"Haofen Wang","orcid":"https://orcid.org/0000-0003-3018-3824"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofen Wang","raw_affiliation_strings":["Tongji University, College of Design and Innovation, China"],"raw_orcid":"https://orcid.org/0000-0003-3018-3824","affiliations":[{"raw_affiliation_string":"Tongji University, College of Design and Innovation, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669255","display_name":"Wenqiang Zhang","orcid":"https://orcid.org/0000-0002-3339-8751"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Zhang","raw_affiliation_strings":["Fudan University, Academy for Engineering and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-3339-8751","affiliations":[{"raw_affiliation_string":"Fudan University, Academy for Engineering and Technology, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3046,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56593216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"120"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.998199999332428,"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":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.7229061722755432},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7069963216781616},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6148620247840881},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.535517156124115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3904865086078644},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34212514758110046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.320381760597229},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13231173157691956},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.10065609216690063},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06212899088859558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229061722755432},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7069963216781616},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6148620247840881},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.535517156124115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3904865086078644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34212514758110046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.320381760597229},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13231173157691956},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.10065609216690063},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06212899088859558},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579051.3579073","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579051.3579073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Joint Conference on Knowledge Graphs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2561529111","https://openalex.org/W2618530766","https://openalex.org/W2747623286","https://openalex.org/W2947312908","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963518342","https://openalex.org/W2963954913","https://openalex.org/W2964303913","https://openalex.org/W2966683369","https://openalex.org/W2997545008","https://openalex.org/W2998385486","https://openalex.org/W2998631105","https://openalex.org/W3101703188","https://openalex.org/W3115476810","https://openalex.org/W3155855665","https://openalex.org/W3161051151","https://openalex.org/W3167599226","https://openalex.org/W3172845486","https://openalex.org/W3196798856"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","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"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"can":[4,46],"facilitate":[5],"social":[6],"convenience,":[7],"which":[8,45],"needs":[9],"to":[10,89,106,135,141,162,170,178],"study":[11],"complex":[12,95],"joint":[13],"reasoning":[14,50],"in":[15,101],"the":[16,28,49,53,62,74,91,98,112,115,120,142,146,171,189],"visual":[17,84],"and":[18,42,68,71,81,185,199],"language":[19],"over":[20],"external":[21,37,128,139,164],"knowledge.":[22],"Recently,":[23],"Knowledge-Based":[24],"VQA":[25,54],"has":[26],"attracted":[27],"attention":[29,147],"of":[30,36,52,64,114,148],"researchers.":[31],"There":[32],"are":[33],"many":[34],"sources":[35,60],"knowledge,":[38,44],"including":[39],"visual,":[40],"textual,":[41],"commonsense":[43],"effectively":[47],"improve":[48],"ability":[51],"model.":[55],"However,":[56],"introducing":[57],"different":[58],"knowledge":[59,99,108,116,129,140,165,181],"increases":[61],"probability":[63],"retrieving":[65],"irrelevant":[66],"facts":[67],"generating":[69],"noise":[70,92],"further":[72],"impacts":[73],"model\u2019s":[75],"performance.":[76],"Existing":[77],"approaches":[78,103],"use":[79],"contrast":[80],"prompt":[82],"learning,":[83],"matrices,":[85],"density":[86],"retrieval,":[87],"etc.,":[88],"address":[90,119],"but":[93],"bring":[94],"processes.":[96],"Furthermore,":[97],"representation":[100],"these":[102],"is":[104,134,167,175,204],"limited":[105],"specific":[107,177],"forms,":[109],"such":[110],"as":[111],"triple":[113],"graphs.":[117],"To":[118],"challenges,":[121],"we":[122],"propose":[123],"a":[124,179],"multi-modal":[125,149],"joint-guided":[126],"(MMJG)":[127],"introduction":[130],"method.":[131],"The":[132,183],"method":[133,195,203],"select":[136,163],"more":[137,168,205],"relevant":[138,169],"current":[143],"question":[144],"through":[145],"information.":[150],"Unlike":[151],"any":[152],"existing":[153],"method,":[154],"our":[155,194,202],"approach":[156,174],"learns":[157],"an":[158],"adaptive":[159],"selection":[160],"module":[161],"that":[166,193,201],"question.":[172],"Our":[173],"not":[176],"particular":[180],"form.":[182],"comparison":[184],"ablation":[186],"experiments":[187],"on":[188],"benchmark":[190],"dataset":[191],"show":[192],"achieves":[196],"better":[197],"results":[198],"demonstrates":[200],"effective.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}