{"id":"https://openalex.org/W4385484634","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191606","title":"Generating Questions via Unexploited OCR Texts: Prompt-Based Data Augmentation for TextVQA","display_name":"Generating Questions via Unexploited OCR Texts: Prompt-Based Data Augmentation for TextVQA","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385484634","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191606"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191606","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5101430326","display_name":"Mingjie Han","orcid":"https://orcid.org/0000-0001-5065-705X"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingjie Han","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University,HaiKou,China","School of Computer Science and Technology, Hainan University, HaiKou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University,HaiKou,China","institution_ids":["https://openalex.org/I20942203"]},{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, HaiKou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078492740","display_name":"Ting Jin","orcid":"https://orcid.org/0000-0001-5073-0667"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Jin","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University,HaiKou,China","School of Computer Science and Technology, Hainan University, HaiKou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University,HaiKou,China","institution_ids":["https://openalex.org/I20942203"]},{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, HaiKou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072676009","display_name":"Wancong Lin","orcid":"https://orcid.org/0009-0000-1477-5390"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wancong Lin","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University,HaiKou,China","School of Computer Science and Technology, Hainan University, HaiKou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University,HaiKou,China","institution_ids":["https://openalex.org/I20942203"]},{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, HaiKou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334058","display_name":"Can Li","orcid":"https://orcid.org/0000-0002-8873-0045"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Li","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University,Shanghai,China","School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Qiao","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang University,Hangzhou,China","School of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101430326"],"corresponding_institution_ids":["https://openalex.org/I20942203"],"apc_list":null,"apc_paid":null,"fwci":0.1228,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39792172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996999979019165,"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":0.9919999837875366,"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":0.8156540393829346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.659689724445343},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6454126238822937},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6100451946258545},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.60951167345047},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5988316535949707},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5423823595046997},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5021300315856934},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4119735062122345},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32233476638793945},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26394519209861755},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09230291843414307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156540393829346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.659689724445343},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6454126238822937},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6100451946258545},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.60951167345047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5988316535949707},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5423823595046997},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5021300315856934},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4119735062122345},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32233476638793945},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26394519209861755},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09230291843414307},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191606","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1689711448","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2008806374","https://openalex.org/W2012689760","https://openalex.org/W2016589492","https://openalex.org/W2053317383","https://openalex.org/W2108598243","https://openalex.org/W2144554289","https://openalex.org/W2277195237","https://openalex.org/W2493916176","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2786273134","https://openalex.org/W2896457183","https://openalex.org/W2947380532","https://openalex.org/W2963622213","https://openalex.org/W2963925437","https://openalex.org/W2963976294","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W3034336960","https://openalex.org/W3093385053","https://openalex.org/W3108512475","https://openalex.org/W3110661548","https://openalex.org/W3115287481","https://openalex.org/W3181159501","https://openalex.org/W3205050305","https://openalex.org/W3215381707","https://openalex.org/W4295246343","https://openalex.org/W4300602348","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6691603626","https://openalex.org/W6725207838","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6780226713","https://openalex.org/W6845600268"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2384605597","https://openalex.org/W2358755282","https://openalex.org/W2387743295","https://openalex.org/W2625833328","https://openalex.org/W1533177136"],"abstract_inverted_index":{"Text-based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(TextVQA)":[4],"tasks":[5],"rely":[6],"on":[7,150],"Optical":[8],"Character":[9],"Recognition":[10],"(OCR)":[11],"text":[12],"to":[13,107],"answer.":[14],"There":[15],"have":[16],"been":[17],"many":[18],"models":[19],"successfully":[20],"exploring":[21],"multi-modal":[22],"features":[23],"fusing":[24],"and":[25,34],"knowledge":[26],"reasoning.":[27],"However,":[28],"current":[29,65],"TextVQA":[30],"datasets":[31],"are":[32,68,98,104,136],"few":[33],"the":[35,71,74,80,87,91,95,108,111,115,119,132],"cost":[36],"of":[37,64,73,76,129],"using":[38],"manual":[39],"annotation":[40],"is":[41,48,60,83,143],"too":[42],"high.":[43],"So":[44],"generating":[45,123],"pseudo-labeled":[46,81,96],"data":[47,57,66,82,97],"a":[49,55],"better":[50,145],"choice.":[51],"In":[52],"this":[53],"paper,":[54],"prompt-based":[56],"augmentation":[58,67],"method":[59,142],"proposed.":[61],"The":[62],"problems":[63],"solved:":[69],"1)":[70],"distribution":[72],"number":[75],"answer":[77],"words":[78,103,117,135],"in":[79,94,110,118],"not":[84,99],"consistent":[85],"with":[86],"real":[88],"dataset.":[89],"2)":[90],"question":[92],"forms":[93],"diverse.":[100],"Specifically,":[101],"prompt":[102,134],"first":[105],"matched":[106],"constraints":[109],"questions":[112,130],"by":[113],"finding":[114],"same":[116],"vocabulary.":[120],"So,":[121],"our":[122,141],"model":[124],"can":[125],"generate":[126],"different":[127,133],"types":[128],"when":[131],"input.":[137],"Experiments":[138],"show":[139],"that":[140],"significantly":[144],"than":[146],"other":[147],"state-of-the-art":[148],"methods":[149],"TextVQA.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}