{"id":"https://openalex.org/W3094071022","doi":"https://doi.org/10.1109/tmm.2021.3120194","title":"RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering","display_name":"RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3094071022","doi":"https://doi.org/10.1109/tmm.2021.3120194","mag":"3094071022"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3120194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3120194","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5101481925","display_name":"Zanxia Jin","orcid":"https://orcid.org/0000-0002-7990-5544"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zan-Xia Jin","raw_affiliation_strings":["Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016190870","display_name":"Heran Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heran Wu","raw_affiliation_strings":["Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015252816","display_name":"Chun Yang","orcid":"https://orcid.org/0000-0002-6297-4500"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yang","raw_affiliation_strings":["Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101984155","display_name":"Fang Zhou","orcid":"https://orcid.org/0000-0001-5478-7898"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Zhou","raw_affiliation_strings":["Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072850755","display_name":"Jingyan Qin","orcid":"https://orcid.org/0000-0002-4101-4316"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyan Qin","raw_affiliation_strings":["Department of Industrial Design, School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China","Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Design, School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723978","display_name":"Lei Xiao","orcid":"https://orcid.org/0000-0002-3132-9234"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xiao","raw_affiliation_strings":["Tencent Technology (Shenzhen) Company Limited, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Technology (Shenzhen) Company Limited, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Cheng Yin","raw_affiliation_strings":["Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","USTB-EEasyTech Joint Laboratory of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"USTB-EEasyTech Joint Laboratory of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101481925"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":2.7097,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91683438,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"12"},"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":0.9983999729156494,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926000237464905,"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":0.849036455154419},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8130355477333069},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5544826984405518},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5272963047027588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4424746334552765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849036455154419},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8130355477333069},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5544826984405518},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5272963047027588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4424746334552765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3120194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3120194","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2141617675","display_name":null,"funder_award_id":"62076024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G356227064","display_name":null,"funder_award_id":"62006018","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2008806374","https://openalex.org/W2012689760","https://openalex.org/W2064675550","https://openalex.org/W2091857990","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2253806798","https://openalex.org/W2277195237","https://openalex.org/W2532034655","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2746097825","https://openalex.org/W2747623286","https://openalex.org/W2798786641","https://openalex.org/W2810983211","https://openalex.org/W2875814315","https://openalex.org/W2883879068","https://openalex.org/W2896603934","https://openalex.org/W2904631866","https://openalex.org/W2922690896","https://openalex.org/W2922794508","https://openalex.org/W2962985038","https://openalex.org/W2963150162","https://openalex.org/W2963223524","https://openalex.org/W2963341956","https://openalex.org/W2963383024","https://openalex.org/W2963403868","https://openalex.org/W2963420691","https://openalex.org/W2963526661","https://openalex.org/W2963622213","https://openalex.org/W2963626623","https://openalex.org/W2963717374","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964080601","https://openalex.org/W2964121744","https://openalex.org/W2966005000","https://openalex.org/W2966683369","https://openalex.org/W2967615747","https://openalex.org/W2968004941","https://openalex.org/W2970910956","https://openalex.org/W2979382951","https://openalex.org/W2981578638","https://openalex.org/W2981985547","https://openalex.org/W2987086322","https://openalex.org/W2988326850","https://openalex.org/W2990216675","https://openalex.org/W2996984511","https://openalex.org/W3004082545","https://openalex.org/W3004349648","https://openalex.org/W3005881764","https://openalex.org/W3026441479","https://openalex.org/W3031222954","https://openalex.org/W3034336960","https://openalex.org/W3034943799","https://openalex.org/W3035644209","https://openalex.org/W3043039073","https://openalex.org/W3087975588","https://openalex.org/W3105881229","https://openalex.org/W4295246343","https://openalex.org/W6631190155","https://openalex.org/W6691603626","https://openalex.org/W6728881024","https://openalex.org/W6739901393","https://openalex.org/W6746261267","https://openalex.org/W6748270630","https://openalex.org/W6753127857","https://openalex.org/W6756618220","https://openalex.org/W6760673939"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text-based":[0],"visual":[1],"question":[2,82,127],"answering":[3],"(VQA)":[4],"requires":[5],"to":[6,14],"read":[7],"and":[8,46,53,69,80,90,93,103,111,132,144,146,173,181],"understand":[9],"text":[10,92,102,123,129,172,180],"in":[11,105],"an":[12,78],"image":[13,34,79,89],"correctly":[15],"answer":[16],"a":[17,61,81],"given":[18,126],"question.":[19],"However,":[20],"most":[21],"current":[22],"methods":[23],"simply":[24],"add":[25],"optical":[26],"character":[27],"recognition":[28],"(OCR)":[29],"tokens":[30,45,52],"extracted":[31],"from":[32],"the":[33,36,48,71,88,99,106,109,114,121,125,153,167,171,175,179],"into":[35],"VQA":[37,141],"model":[38],"without":[39],"considering":[40],"contextual":[41,168],"information":[42,169],"of":[43,108,170],"OCR":[44,51],"mining":[47],"relationships":[49,115,177],"between":[50,178],"scene":[54,94],"objects.":[55,95,182],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"novel":[62],"text-centered":[63],"method":[64,163],"called":[65],"RUArt":[66,85,137],"(Reading,":[67],"Understanding":[68],"Answering":[70],"Related":[72],"Text)":[73],"for":[74,124,151],"text-based":[75,140],"VQA.":[76],"Taking":[77],"as":[83],"input,":[84],"first":[86],"reads":[87],"obtains":[91],"Then,":[96],"it":[97,119],"understands":[98],"question,":[100],"OCRed":[101],"objects":[104],"context":[107],"scene,":[110],"further":[112],"mines":[113],"among":[116],"them.":[117],"Finally,":[118],"answers":[120],"related":[122],"through":[128],"semantic":[130],"matching":[131],"reasoning.":[133],"We":[134],"evaluate":[135],"our":[136,162],"on":[138],"two":[139],"benchmarks":[142],"(ST-VQA":[143],"TextVQA)":[145],"conduct":[147],"extensive":[148],"ablation":[149],"studies":[150],"exploring":[152],"reasons":[154],"behind":[155],"RUArt\u2019s":[156],"effectiveness.":[157],"Experimental":[158],"results":[159],"demonstrate":[160],"that":[161],"can":[164],"effectively":[165],"explore":[166],"mine":[174],"stable":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}