{"id":"https://openalex.org/W4213060972","doi":"https://doi.org/10.3390/s22041575","title":"Learning to Reason on Tree Structures for Knowledge-Based Visual Question Answering","display_name":"Learning to Reason on Tree Structures for Knowledge-Based Visual Question Answering","publication_year":2022,"publication_date":"2022-02-17","ids":{"openalex":"https://openalex.org/W4213060972","doi":"https://doi.org/10.3390/s22041575","pmid":"https://pubmed.ncbi.nlm.nih.gov/35214484"},"language":"en","primary_location":{"id":"doi:10.3390/s22041575","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22041575","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/s22041575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101794764","display_name":"Qifeng Li","orcid":"https://orcid.org/0000-0003-2258-8987"},"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/I4210135723","display_name":"Shanghai Institute of Technical Physics","ror":"https://ror.org/02txedb84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210135723"]},{"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":true,"raw_author_name":"Qifeng Li","raw_affiliation_strings":["Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China","School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China","Shanghai Institute of Technical Physics of the Chinese Academy of Sciences, Shanghai 200083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Shanghai Institute of Technical Physics of the Chinese Academy of Sciences, Shanghai 200083, China","institution_ids":["https://openalex.org/I4210135723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072061189","display_name":"Xinyi Tang","orcid":"https://orcid.org/0000-0001-5672-2801"},"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/I4210135723","display_name":"Shanghai Institute of Technical Physics","ror":"https://ror.org/02txedb84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210135723"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Tang","raw_affiliation_strings":["Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China","Shanghai Institute of Technical Physics of the Chinese Academy of Sciences, Shanghai 200083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Shanghai Institute of Technical Physics of the Chinese Academy of Sciences, Shanghai 200083, China","institution_ids":["https://openalex.org/I4210135723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003467238","display_name":"Jian Yi","orcid":"https://orcid.org/0000-0001-7314-0213"},"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/I4210135723","display_name":"Shanghai Institute of Technical Physics","ror":"https://ror.org/02txedb84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210135723"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Jian","raw_affiliation_strings":["Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China","Shanghai Institute of Technical Physics of the Chinese Academy of Sciences, Shanghai 200083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Shanghai Institute of Technical Physics of the Chinese Academy of Sciences, Shanghai 200083, China","institution_ids":["https://openalex.org/I4210135723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101794764"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210135723","https://openalex.org/I4210165038"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01044697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"4","first_page":"1575","last_page":"1575"},"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":0.9983000159263611,"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":0.9927999973297119,"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/visual-reasoning","display_name":"Visual reasoning","score":0.7829866409301758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7620726823806763},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7615944147109985},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7425271272659302},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6834458708763123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.673358678817749},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.5022971630096436},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.4952467978000641},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4905635714530945},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.44666725397109985},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43440622091293335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41796061396598816},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.4061850905418396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39240118861198425},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.08699661493301392}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7829866409301758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620726823806763},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7615944147109985},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7425271272659302},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6834458708763123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.673358678817749},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.5022971630096436},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.4952467978000641},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4905635714530945},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.44666725397109985},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43440622091293335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41796061396598816},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4061850905418396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39240118861198425},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.08699661493301392},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22041575","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22041575","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:35214484","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35214484","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8874875","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8874875","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:97b9e1dbe17d44698998dd292ea840c3","is_oa":true,"landing_page_url":"https://doaj.org/article/97b9e1dbe17d44698998dd292ea840c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 22, Iss 4, p 1575 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/4/1575/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22041575","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 22; Issue 4; Pages: 1575","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22041575","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22041575","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W2083897630","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2250861254","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2561529111","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2787119853","https://openalex.org/W2892259963","https://openalex.org/W2947312908","https://openalex.org/W2962716332","https://openalex.org/W2962749469","https://openalex.org/W2963143606","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963477107","https://openalex.org/W2963656855","https://openalex.org/W2963722138","https://openalex.org/W2963770662","https://openalex.org/W2963907629","https://openalex.org/W2963954913","https://openalex.org/W2964072591","https://openalex.org/W2964118342","https://openalex.org/W2964303913","https://openalex.org/W2969332757","https://openalex.org/W2976187852","https://openalex.org/W2982699810","https://openalex.org/W3016211260","https://openalex.org/W3044175177","https://openalex.org/W3084798277","https://openalex.org/W6604189946","https://openalex.org/W6631190155","https://openalex.org/W6634232107","https://openalex.org/W6680053761","https://openalex.org/W6685337303","https://openalex.org/W6685574838","https://openalex.org/W6687483927","https://openalex.org/W6692004142","https://openalex.org/W6716358881","https://openalex.org/W6729399837","https://openalex.org/W6731265811","https://openalex.org/W6737805085","https://openalex.org/W6738893770","https://openalex.org/W6754553780"],"related_works":["https://openalex.org/W2650743995","https://openalex.org/W2964061310","https://openalex.org/W2963477107","https://openalex.org/W2231285690","https://openalex.org/W2969127500","https://openalex.org/W3093385053","https://openalex.org/W2361142061","https://openalex.org/W4389682534","https://openalex.org/W1545212651","https://openalex.org/W2131907548"],"abstract_inverted_index":{"Collaborative":[0],"reasoning":[1,52,68,82,128,139,178,211],"for":[2,42,60,94,160],"knowledge-based":[3,154],"visual":[4,51,67,148,164,175,210],"question":[5,121],"answering":[6],"is":[7],"challenging":[8],"but":[9],"vital":[10],"and":[11,20,53,120,132,150,153,165,177,185,206,209],"efficient":[12],"in":[13,75],"understanding":[14],"the":[15,18,48,62,108,117,126,134,137,146,161,203,214,217],"features":[16,30,119,149],"of":[17,29,50,58,72,84,103,145,163,216],"images":[19],"questions.":[21],"While":[22],"previous":[23],"methods":[24,201],"jointly":[25],"fuse":[26],"all":[27,70],"kinds":[28,71],"by":[31,123],"attention":[32,109,124],"mechanism":[33],"or":[34],"use":[35],"handcrafted":[36],"rules":[37],"to":[38],"generate":[39],"a":[40,55,80,85,90],"layout":[41],"performing":[43],"compositional":[44],"reasoning,":[45],"which":[46],"lacks":[47],"process":[49],"introduces":[54],"large":[56],"number":[57],"parameters":[59],"predicting":[61],"correct":[63],"answer.":[64],"For":[65],"conducting":[66],"on":[69,116,180,202],"image-question":[73],"pairs,":[74],"this":[76],"paper,":[77],"we":[78],"propose":[79],"novel":[81],"model":[83,101,110,129,140,156,173,195],"question-guided":[86],"tree":[87,181],"structure":[88],"with":[89,168],"knowledge":[91,151,183],"base":[92,152,184],"(QGTSKB)":[93],"addressing":[95],"these":[96],"problems.":[97],"In":[98],"addition,":[99],"our":[100,172,194],"consists":[102],"four":[104,186],"neural":[105,187],"module":[106,188],"networks:":[107],"that":[111,130,141,157,193],"locates":[112],"attended":[113,147],"regions":[114],"based":[115,179],"image":[118],"embeddings":[122],"mechanism,":[125],"gated":[127],"forgets":[131],"updates":[133],"fused":[135],"features,":[136],"fusion":[138],"mines":[142],"high-level":[143],"semantics":[144],"fact":[155],"makes":[158],"up":[159],"lack":[162],"textual":[166],"information":[167],"external":[169],"knowledge.":[170],"Therefore,":[171],"performs":[174],"analysis":[176],"structures,":[182],"networks.":[189],"Experimental":[190],"results":[191],"show":[192],"achieves":[196],"superior":[197],"performance":[198],"over":[199],"existing":[200],"VQA":[204],"v2.0":[205],"CLVER":[207],"dataset,":[208],"experiments":[212],"prove":[213],"interpretability":[215],"model.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2022-02-24T00:00:00"}