{"id":"https://openalex.org/W4383112434","doi":"https://doi.org/10.1109/access.2023.3292264","title":"Scene Text Segmentation via Multi-Task Cascade Transformer With Paired Data Synthesis","display_name":"Scene Text Segmentation via Multi-Task Cascade Transformer With Paired Data Synthesis","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383112434","doi":"https://doi.org/10.1109/access.2023.3292264"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3292264","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3292264","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10172213.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10172213.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084475780","display_name":"Quang-Vinh Dang","orcid":"https://orcid.org/0000-0002-6715-7112"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Quang-Vinh Dang","raw_affiliation_strings":["Department of Artificial Intelligence Convergence, Chonnam National University, Buk-gu, South Korea","Department of Artificial Intelligence Convergence, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju, Korea"],"raw_orcid":"https://orcid.org/0000-0002-6715-7112","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Buk-gu, South Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju, Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070936425","display_name":"Guee-Sang Lee","orcid":"https://orcid.org/0000-0002-8756-1382"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Guee-Sang Lee","raw_affiliation_strings":["Department of Artificial Intelligence Convergence, Chonnam National University, Buk-gu, South Korea","Department of Artificial Intelligence Convergence, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju, Korea"],"raw_orcid":"https://orcid.org/0000-0002-8756-1382","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Buk-gu, South Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju, Korea","institution_ids":["https://openalex.org/I111277659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084475780"],"corresponding_institution_ids":["https://openalex.org/I111277659"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1582,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80609039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"67791","last_page":"67805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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/T10601","display_name":"Handwritten Text Recognition Techniques","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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9803000092506409,"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/T11309","display_name":"Music and Audio Processing","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8721129298210144},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7950409054756165},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7140359878540039},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.6415925621986389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.627016544342041},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5240597724914551},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.45330581068992615},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42028310894966125},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41823694109916687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4051398038864136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721129298210144},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7950409054756165},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7140359878540039},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.6415925621986389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.627016544342041},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5240597724914551},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.45330581068992615},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42028310894966125},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41823694109916687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4051398038864136},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3292264","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3292264","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10172213.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:206d206d833e41d88533c9cc4cef6e98","is_oa":true,"landing_page_url":"https://doaj.org/article/206d206d833e41d88533c9cc4cef6e98","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":"IEEE Access, Vol 11, Pp 67791-67805 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3292264","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3292264","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10172213.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1354215130","display_name":null,"funder_award_id":"NRF-2018R1D1A3B05049058","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383112434.pdf","grobid_xml":"https://content.openalex.org/works/W4383112434.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1814573448","https://openalex.org/W1922126009","https://openalex.org/W1995790019","https://openalex.org/W2008806374","https://openalex.org/W2011301426","https://openalex.org/W2019830313","https://openalex.org/W2028045978","https://openalex.org/W2108598243","https://openalex.org/W2132083787","https://openalex.org/W2147880316","https://openalex.org/W2250539671","https://openalex.org/W2574887079","https://openalex.org/W2766895242","https://openalex.org/W2785383245","https://openalex.org/W2873558679","https://openalex.org/W2904785373","https://openalex.org/W2944049853","https://openalex.org/W2963073614","https://openalex.org/W2963299604","https://openalex.org/W2963800363","https://openalex.org/W2972678073","https://openalex.org/W2982148195","https://openalex.org/W2987563462","https://openalex.org/W2991090032","https://openalex.org/W3003868038","https://openalex.org/W3003921261","https://openalex.org/W3031548983","https://openalex.org/W3036054034","https://openalex.org/W3039992800","https://openalex.org/W3109301572","https://openalex.org/W3110398855","https://openalex.org/W3128982913","https://openalex.org/W3135565841","https://openalex.org/W3136958399","https://openalex.org/W3157525179","https://openalex.org/W3168428721","https://openalex.org/W3194513480","https://openalex.org/W3199003182","https://openalex.org/W3199738066","https://openalex.org/W3211490618","https://openalex.org/W3217070527","https://openalex.org/W4200301490","https://openalex.org/W4205474609","https://openalex.org/W4295246343","https://openalex.org/W4313591763","https://openalex.org/W4321021868","https://openalex.org/W4321380813","https://openalex.org/W4323020850","https://openalex.org/W4323020960","https://openalex.org/W4323892169","https://openalex.org/W4386075667","https://openalex.org/W4386598385","https://openalex.org/W6682082992","https://openalex.org/W6691603626","https://openalex.org/W6780464832","https://openalex.org/W6797399245","https://openalex.org/W6800062215","https://openalex.org/W6803376173","https://openalex.org/W6846907731","https://openalex.org/W6850667813","https://openalex.org/W6856610814"],"related_works":["https://openalex.org/W2153719181","https://openalex.org/W1971748923","https://openalex.org/W1566155057","https://openalex.org/W2060986072","https://openalex.org/W2052574922","https://openalex.org/W64588465","https://openalex.org/W3120641340","https://openalex.org/W2117825986","https://openalex.org/W3134067061","https://openalex.org/W1522196789"],"abstract_inverted_index":{"The":[0,100,114],"scene":[1,22,171],"text":[2,23,54,65,112,121,133,172],"segmentation":[3,24,55,173],"task":[4,110],"provides":[5],"a":[6,83],"wide":[7],"range":[8],"of":[9,15,96,131],"practical":[10],"applications.":[11],"However,":[12],"the":[13,18,118,129,132,141,146,153],"number":[14],"images":[16],"in":[17],"available":[19,170],"datasets":[20,174],"for":[21,53,111],"is":[25],"not":[26],"large":[27,94],"enough":[28],"to":[29,36,48,123,139],"effectively":[30],"train":[31,152],"deep":[32],"learning-based":[33],"models,":[34],"leading":[35],"limited":[37],"performance.":[38,77],"To":[39,78,144],"solve":[40],"this":[41],"problem,":[42],"we":[43,81,151],"employ":[44],"paired":[45,157],"data":[46,51,159],"generation":[47],"secure":[49],"sufficient":[50],"samples":[52],"via":[56],"Text":[57],"Image-conditional":[58],"GANs.":[59],"Furthermore,":[60],"existing":[61,180],"models":[62],"implicitly":[63],"model":[64],"attributes":[66,92],"such":[67],"as":[68,126,128],"size,":[69],"layout,":[70],"font,":[71],"and":[72,107,137],"structure,":[73],"which":[74],"hinders":[75],"their":[76],"remedy":[79],"this,":[80],"propose":[82],"Multi-task":[84],"Cascade":[85],"Transformer":[86],"network":[87,102,119,155],"that":[88,176],"explicitly":[89],"learns":[90],"these":[91],"using":[93],"volumes":[95],"generated":[97],"synthetic":[98,158],"data.":[99,165],"transformer-based":[101],"includes":[103],"two":[104],"auxiliary":[105,115],"tasks":[106,116],"one":[108],"main":[109,142],"segmentation.":[113],"help":[117],"learn":[120],"regions":[122],"focus":[124],"on,":[125],"well":[127],"structure":[130],"through":[134],"different":[135,149],"words":[136],"fonts,":[138],"support":[140],"task.":[143],"bridge":[145],"gap":[147],"between":[148],"datasets,":[150],"proposed":[154],"on":[156,163,168],"before":[160],"fine-tuning":[161],"it":[162],"real":[164],"Our":[166],"experiments":[167],"publicly":[169],"show":[175],"our":[177],"method":[178],"outperforms":[179],"methods.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}