{"id":"https://openalex.org/W4214824212","doi":"https://doi.org/10.1145/3489142","title":"Inner Knowledge-based Img2Doc Scheme for Visual Question Answering","display_name":"Inner Knowledge-based Img2Doc Scheme for Visual Question Answering","publication_year":2022,"publication_date":"2022-03-04","ids":{"openalex":"https://openalex.org/W4214824212","doi":"https://doi.org/10.1145/3489142"},"language":"en","primary_location":{"id":"doi:10.1145/3489142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489142","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, 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/A5100426173","display_name":"Qun Li","orcid":"https://orcid.org/0000-0002-8034-6030"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qun Li","raw_affiliation_strings":["School of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602821","display_name":"Fu Xiao","orcid":"https://orcid.org/0000-0003-1815-2793"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Xiao","raw_affiliation_strings":["School of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071522801","display_name":"Bir Bhanu","orcid":"https://orcid.org/0000-0001-8971-6416"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bir Bhanu","raw_affiliation_strings":["Center for Research in Intelligent Systems, University of California at Riverside, Riverside, CA"],"affiliations":[{"raw_affiliation_string":"Center for Research in Intelligent Systems, University of California at Riverside, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039232420","display_name":"Biyun Sheng","orcid":"https://orcid.org/0000-0002-5006-3822"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biyun Sheng","raw_affiliation_strings":["School of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100426173"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":1.7112,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85271809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"3","first_page":"1","last_page":"21"},"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":0.9950000047683716,"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":0.9887999892234802,"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":0.8776808977127075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8235851526260376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5622943043708801},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5602662563323975},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5559887886047363},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5238694548606873},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48632603883743286},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4856051802635193},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.46746352314949036},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4223966598510742},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36643186211586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3611009120941162},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32388609647750854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08194345235824585}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8776808977127075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235851526260376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622943043708801},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5602662563323975},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5559887886047363},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5238694548606873},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48632603883743286},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4856051802635193},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.46746352314949036},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4223966598510742},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36643186211586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3611009120941162},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32388609647750854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08194345235824585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3489142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489142","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G6893057037","display_name":null,"funder_award_id":"2017M621795, 2019M651915","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8417308462","display_name":null,"funder_award_id":"61906099, 61906098, 61803212, 61571238, 61602193","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1933349210","https://openalex.org/W2036640547","https://openalex.org/W2081580037","https://openalex.org/W2094728533","https://openalex.org/W2154851992","https://openalex.org/W2171278097","https://openalex.org/W2186222003","https://openalex.org/W2442626797","https://openalex.org/W2471094925","https://openalex.org/W2496096353","https://openalex.org/W2529436507","https://openalex.org/W2560730294","https://openalex.org/W2560920409","https://openalex.org/W2564898401","https://openalex.org/W2595840341","https://openalex.org/W2731821979","https://openalex.org/W2747623286","https://openalex.org/W2771472444","https://openalex.org/W2832876791","https://openalex.org/W2887626628","https://openalex.org/W2914393402","https://openalex.org/W2951798058","https://openalex.org/W2962749469","https://openalex.org/W2962994687","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963644680","https://openalex.org/W2963656855","https://openalex.org/W2963758027","https://openalex.org/W2963954913","https://openalex.org/W2963981422","https://openalex.org/W2964018924","https://openalex.org/W2964061310","https://openalex.org/W2964138017","https://openalex.org/W2964138343","https://openalex.org/W2964303913","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2979382951","https://openalex.org/W2982461533","https://openalex.org/W2988326850","https://openalex.org/W2997591391","https://openalex.org/W3003487319","https://openalex.org/W3025665229","https://openalex.org/W3035512383","https://openalex.org/W3041222599","https://openalex.org/W3104097132","https://openalex.org/W3110388292","https://openalex.org/W4205572233","https://openalex.org/W4234552385","https://openalex.org/W4247552011","https://openalex.org/W4301045096"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2387743295","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,48,53,77,138],"a":[5,80,97,125],"research":[6,22],"topic":[7],"of":[8,14],"significant":[9],"interest":[10],"at":[11,103],"the":[12,56,112,135,149],"intersection":[13],"computer":[15],"vision":[16],"and":[17,26,36],"natural":[18,105],"language":[19,106],"understanding.":[20],"Recent":[21],"indicates":[23],"that":[24,148],"attributes":[25],"knowledge":[27,52],"can":[28],"effectively":[29],"improve":[30],"performance":[31,154],"for":[32,46,70,84,93],"both":[33],"image":[34,73,122],"captioning":[35],"VQA.":[37],"In":[38,63],"this":[39],"article,":[40],"an":[41,67,129],"inner":[42,51,57,71,90],"knowledge-based":[43,72,91],"Img2Doc":[44],"algorithm":[45],"VQA":[47,75,136],"presented.":[49],"The":[50,86,144],"characterized":[54],"as":[55],"attribute":[58,68,87],"relationship":[59],"in":[60],"visual":[61,94,121],"images.":[62],"addition":[64],"to":[65,108,127],"using":[66],"network":[69,88],"representation,":[74],"scheme":[76],"associated":[78],"with":[79,120],"question-guided":[81,99],"Doc2Vec":[82,100],"method":[83,101,151],"question\u2013answering.":[85],"generates":[89],"features":[92,114,123],"images,":[95],"while":[96],"novel":[98],"aims":[102],"converting":[104],"text":[107],"vector":[109,113],"features.":[110],"After":[111],"are":[115,118],"extracted,":[116],"they":[117],"combined":[119],"into":[124],"classifier":[126],"provide":[128],"answer.":[130],"Based":[131],"on":[132,155],"our":[133],"model,":[134],"problem":[137],"resolved":[139],"by":[140],"textual":[141],"question":[142],"answering.":[143],"experimental":[145],"results":[146],"demonstrate":[147],"proposed":[150],"achieves":[152],"superior":[153],"multiple":[156],"benchmark":[157],"datasets.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}