{"id":"https://openalex.org/W4387969627","doi":"https://doi.org/10.1145/3581783.3612844","title":"VTQAGen: BART-based Generative Model For Visual Text Question Answering","display_name":"VTQAGen: BART-based Generative Model For Visual Text Question Answering","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969627","doi":"https://doi.org/10.1145/3581783.3612844"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5093130814","display_name":"Haoru Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoru Chen","raw_affiliation_strings":["Chongqing University of Posts and Telecommunication, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0002-0250-1426","affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunication, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061252955","display_name":"Tianjiao Wan","orcid":"https://orcid.org/0000-0002-2423-4982"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjiao Wan","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2423-4982","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101831800","display_name":"Zhimin Lin","orcid":"https://orcid.org/0009-0009-9882-9215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhimin Lin","raw_affiliation_strings":["MindRank AI Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-9882-9215","affiliations":[{"raw_affiliation_string":"MindRank AI Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346114","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0001-5993-6063"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-5993-6063","affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101522100","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0002-3245-1901"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3245-1901","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41966671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"9456","last_page":"9461"},"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":0.9972000122070312,"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":0.9919000267982483,"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":0.8477538824081421},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6668477058410645},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5904764533042908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5744357705116272},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5650055408477783},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5446760654449463},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5174546837806702},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5170338749885559},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5068839192390442},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4860873520374298},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3490205407142639},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33110326528549194},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09147945046424866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8477538824081421},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6668477058410645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5904764533042908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5744357705116272},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5650055408477783},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5446760654449463},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5174546837806702},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5170338749885559},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5068839192390442},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4860873520374298},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3490205407142639},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33110326528549194},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09147945046424866},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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:10.1145/3581783.3612844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2563399268","https://openalex.org/W2597425697","https://openalex.org/W2962869524","https://openalex.org/W2963890019","https://openalex.org/W2964138017","https://openalex.org/W2964345214","https://openalex.org/W2988326850","https://openalex.org/W2990503944","https://openalex.org/W2998536339","https://openalex.org/W3004082545","https://openalex.org/W3093385053","https://openalex.org/W3094071022","https://openalex.org/W3108274592","https://openalex.org/W3206082179","https://openalex.org/W3215633354","https://openalex.org/W4226278471","https://openalex.org/W4312263373","https://openalex.org/W4386065596","https://openalex.org/W6600002382","https://openalex.org/W6600175266","https://openalex.org/W6600769105","https://openalex.org/W6601141708","https://openalex.org/W6825417173"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Visual":[0,192],"Text":[1,193],"Question":[2,194],"Answering":[3],"(VTQA)":[4],"is":[5,27,138,149],"a":[6,77,85,100,116],"challenging":[7],"task":[8,60],"that":[9,31],"requires":[10],"answering":[11],"questions":[12],"pertaining":[13],"to":[14,28,90,120,140,151,167],"visual":[15,142],"content":[16],"by":[17],"combining":[18],"image":[19],"understanding":[20],"and":[21,44,70,94,105,111,124,162,170],"language":[22],"comprehension.":[23],"The":[24,113,155],"main":[25],"objective":[26],"develop":[29],"models":[30],"can":[32],"accurately":[33],"provide":[34],"relevant":[35],"answers":[36],"based":[37,133],"on":[38,134,181],"complementary":[39],"information":[40],"from":[41,108],"both":[42,109],"images":[43,110],"text,":[45],"as":[46,48,97,99],"well":[47,98],"the":[49,53,58,159,173,175,182,189],"semantic":[50],"meaning":[51],"of":[52,144],"question.":[54],"Despite":[55],"ongoing":[56],"efforts,":[57],"VTQA":[59],"presents":[61],"several":[62],"challenges,":[63],"including":[64],"multimedia":[65],"alignment,":[66],"multi-step":[67],"cross-media":[68],"reasoning,":[69],"handling":[71],"open-ended":[72],"questions.":[73],"This":[74],"paper":[75],"introduces":[76,163],"novel":[78],"generative":[79,131],"framework":[80,114],"called":[81],"VTQAGen,":[82],"which":[83],"leverages":[84],"Multi-":[86],"modal":[87],"Attention":[88],"Layer":[89],"combine":[91],"image-text":[92],"pairs":[93],"question":[95],"inputs,":[96],"BART-based":[101],"model":[102,122,132],"for":[103],"reasoning":[104],"entity":[106],"extraction":[107],"text.":[112],"incorporates":[115],"step-based":[117,164],"ensemble":[118],"method":[119],"enhance":[121],"performance":[123,180],"generalization":[125],"ability.":[126],"VTQAGen":[127,177],"utilizes":[128,158],"an":[129],"encoder-decoder":[130],"BART.":[135],"Faster":[136],"R-CNN":[137],"employed":[139],"extract":[141],"regions":[143],"interest,":[145],"while":[146],"BART's":[147],"encoder":[148],"modified":[150],"handle":[152],"multi-modal":[153],"interaction.":[154],"decoder":[156],"stage":[157],"shift-predict":[160],"approach":[161],"logits":[165],"fusion":[166],"improve":[168],"stability":[169],"accuracy.":[171],"In":[172],"experiments,":[174],"proposed":[176],"demonstrates":[178],"superior":[179],"testing":[183],"set,":[184],"securing":[185],"second":[186],"place":[187],"in":[188],"ACM":[190],"Multimedia":[191],"Answer":[195],"Challenge.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}