{"id":"https://openalex.org/W4405880101","doi":"https://doi.org/10.1142/s1469026824500342","title":"MKGFA: Multimodal Knowledge Graph Construction and Fact-Assisted Reasoning for VQA","display_name":"MKGFA: Multimodal Knowledge Graph Construction and Fact-Assisted Reasoning for VQA","publication_year":2024,"publication_date":"2024-12-30","ids":{"openalex":"https://openalex.org/W4405880101","doi":"https://doi.org/10.1142/s1469026824500342"},"language":"en","primary_location":{"id":"doi:10.1142/s1469026824500342","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1469026824500342","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","raw_type":"journal-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/A5004209720","display_name":"Longbao Wang","orcid":"https://orcid.org/0000-0002-6164-1253"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]},{"id":"https://openalex.org/I4210155611","display_name":"Ministry of Water Resources of the People's Republic of China","ror":"https://ror.org/04e698d63","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210155611"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longbao Wang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China","Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Nanjing 210000, China"],"raw_orcid":"https://orcid.org/0000-0002-6164-1253","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Nanjing 210000, China","institution_ids":["https://openalex.org/I4210155611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049890335","display_name":"Jinhao Zhang","orcid":"https://orcid.org/0009-0003-3004-4872"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhao Zhang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China"],"raw_orcid":"https://orcid.org/0009-0003-3004-4872","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Libing Zhang","orcid":"https://orcid.org/0009-0002-5712-092X"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libing Zhang","raw_affiliation_strings":["Kunming Engineering Corporation Limited, Kunming 650000, China"],"raw_orcid":"https://orcid.org/0009-0002-5712-092X","affiliations":[{"raw_affiliation_string":"Kunming Engineering Corporation Limited, Kunming 650000, China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Zhang","orcid":"https://orcid.org/0009-0008-0243-1337"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Kunming Engineering Corporation Limited, Kunming 650000, China"],"raw_orcid":"https://orcid.org/0009-0008-0243-1337","affiliations":[{"raw_affiliation_string":"Kunming Engineering Corporation Limited, Kunming 650000, China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064694486","display_name":"Shufang Xu","orcid":"https://orcid.org/0000-0002-6802-9083"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shufang Xu","raw_affiliation_strings":["College of Information Science and Engineering, Hohai University, Changzhou 213200, China"],"raw_orcid":"https://orcid.org/0000-0002-6802-9083","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hohai University, Changzhou 213200, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112490958","display_name":"Lin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Yu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China"],"raw_orcid":"https://orcid.org/0009-0003-2201-5879","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044826967","display_name":"Hongmin Gao","orcid":"https://orcid.org/0000-0002-8404-2464"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmin Gao","raw_affiliation_strings":["College of Information Science and Engineering, Hohai University, Changzhou 213200, China"],"raw_orcid":"https://orcid.org/0000-0002-8404-2464","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hohai University, Changzhou 213200, China","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004209720"],"corresponding_institution_ids":["https://openalex.org/I163340411","https://openalex.org/I4210155611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23045127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"02","first_page":null,"last_page":null},"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":0.9926999807357788,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9876000285148621,"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":0.8607580661773682},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6549727320671082},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6351311206817627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082682967185974},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.49710777401924133},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.495281845331192},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4930064380168915},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47257721424102783},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4332565665245056},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4282364249229431},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.42795857787132263},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3881543278694153},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14260649681091309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607580661773682},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6549727320671082},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6351311206817627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082682967185974},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.49710777401924133},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.495281845331192},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4930064380168915},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47257721424102783},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4332565665245056},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4282364249229431},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.42795857787132263},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3881543278694153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14260649681091309},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"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:10.1142/s1469026824500342","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1469026824500342","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2563399268","https://openalex.org/W2747623286","https://openalex.org/W2760103357","https://openalex.org/W2947312908","https://openalex.org/W2964345214","https://openalex.org/W2969679616","https://openalex.org/W2970231061","https://openalex.org/W3037575487","https://openalex.org/W3080318437","https://openalex.org/W3093006710","https://openalex.org/W3101703188","https://openalex.org/W3146844750","https://openalex.org/W3173220247","https://openalex.org/W3174025757","https://openalex.org/W3201302554","https://openalex.org/W3203354307","https://openalex.org/W4252076394","https://openalex.org/W4283217014","https://openalex.org/W4288046368","https://openalex.org/W4376607886","https://openalex.org/W4398131456"],"related_works":["https://openalex.org/W4401140950","https://openalex.org/W4297783004","https://openalex.org/W2914694625","https://openalex.org/W4292070284","https://openalex.org/W4312933959","https://openalex.org/W4391009500","https://openalex.org/W4229080059","https://openalex.org/W4286257253","https://openalex.org/W2916853871","https://openalex.org/W4287330440"],"abstract_inverted_index":{"Knowledge-based":[0],"visual":[1,16,48,151],"question":[2],"answering":[3],"relies":[4],"on":[5,169,203],"open-ended":[6],"external":[7,85,91],"knowledge":[8,27,52,98,114,142],"and":[9,20,84,89,94,101,125,153,183,189,199,208],"a":[10,96,181],"fine-grained":[11],"comprehension":[12],"of":[13,18,41,109,137,172,219,222],"both":[14],"the":[15,29,39,73,112,119,126,134,165,170,176,194,204,216,220,223],"content":[17],"images":[19],"semantic":[21],"information.":[22],"Existing":[23],"methods":[24,35],"for":[25,140,156],"utilizing":[26],"have":[28],"following":[30],"limitations:":[31],"(1)":[32],"Language":[33],"pre-training":[34,182],"output":[36],"answers":[37],"in":[38,133],"form":[40],"plain":[42],"text,":[43],"which":[44],"only":[45],"understand":[46],"shallow":[47],"content;":[49],"(2)":[50],"The":[51,106,130,144,160,212],"retrieved":[53],"by":[54],"image":[55],"objects":[56,152],"as":[57,61],"labels":[58],"is":[59],"represented":[60],"first-order":[62],"logic,":[63],"making":[64],"it":[65],"difficult":[66],"to":[67],"infer":[68],"complex":[69],"questions.":[70],"To":[71],"address":[72],"above":[74],"problems,":[75],"this":[76],"paper":[77],"integrates":[78],"visual-textual":[79],"multimodal":[80,97,113,141],"information,":[81],"accumulates":[82],"domain-specific":[83,190],"multi-modal":[86],"knowledge,":[87],"introduces":[88],"supplements":[90],"objective":[92,120],"facts,":[93],"proposes":[95],"graph":[99,115],"construction":[100,116],"fact-assisted":[102,121],"reasoning":[103,122],"network":[104,107],"(MKGFA).":[105],"consists":[108],"three":[110],"parts:":[111],"module":[117,123,163],"(MKGC),":[118],"(FAR),":[124],"answer":[127,161],"inference":[128,162],"module.":[129],"MKGC":[131],"engages":[132],"coarse-to-fine-grained":[135],"learning":[136],"triplet":[138],"representations":[139],"units.":[143],"FAR":[145],"establishes":[146],"deep":[147],"cross-modal":[148],"relations":[149],"between":[150],"factual":[154],"words":[155],"correlating":[157],"real":[158],"answers.":[159],"makes":[164],"final":[166],"decision":[167],"based":[168],"results":[171,214],"both.":[173],"Among":[174],"them,":[175],"former":[177],"two":[178,205,224],"modules":[179],"employ":[180],"fine-tuning":[184],"strategy,":[185],"systematically":[186],"accumulating":[187],"foundational":[188],"knowledge.":[191],"Compared":[192],"with":[193],"state-of-the-arts,":[195],"MKGFA":[196],"achieves":[197],"1.09%":[198],"0.7%":[200],"higher":[201],"accuracy":[202],"challenging":[206],"OKVQA":[207],"KRVQA":[209],"datasets,":[210],"respectively.":[211],"experimental":[213],"demonstrate":[215],"complementary":[217],"advantages":[218],"integration":[221],"modules.":[225]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}