{"id":"https://openalex.org/W4386598385","doi":"https://doi.org/10.1109/icip49359.2023.10222845","title":"Scene Text Segmentation by Paired Data Synthesis","display_name":"Scene Text Segmentation by Paired Data Synthesis","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598385","doi":"https://doi.org/10.1109/icip49359.2023.10222845"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/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":["Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,Korea","Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, 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":["Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,Korea","Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, 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":null,"apc_paid":null,"fwci":0.6141,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6968733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"549"},"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":0.9921000003814697,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9567000269889832,"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":0.8461942672729492},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8041430711746216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7077637910842896},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.539929986000061},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5273241400718689},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.49718812108039856},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4830658733844757},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4738136827945709},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4721377491950989},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4535750150680542},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.45245441794395447},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.4430769979953766},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4247535467147827},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.41843488812446594},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3658409118652344},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33073651790618896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461942672729492},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8041430711746216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7077637910842896},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.539929986000061},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5273241400718689},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.49718812108039856},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4830658733844757},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4738136827945709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4721377491950989},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4535750150680542},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.45245441794395447},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.4430769979953766},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4247535467147827},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.41843488812446594},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3658409118652344},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33073651790618896},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W2008806374","https://openalex.org/W2028045978","https://openalex.org/W2574887079","https://openalex.org/W2963073614","https://openalex.org/W2963299604","https://openalex.org/W2963800363","https://openalex.org/W2982148195","https://openalex.org/W2991090032","https://openalex.org/W3094502228","https://openalex.org/W3136958399","https://openalex.org/W3157525179","https://openalex.org/W3168428721","https://openalex.org/W3199003182","https://openalex.org/W3199738066","https://openalex.org/W3211490618","https://openalex.org/W4206174637","https://openalex.org/W4323892169","https://openalex.org/W4383112434","https://openalex.org/W6760560510","https://openalex.org/W6784333009","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W2945274617","https://openalex.org/W4313052709","https://openalex.org/W4205800335","https://openalex.org/W2055202857","https://openalex.org/W2022929107","https://openalex.org/W80586315","https://openalex.org/W2758994127"],"abstract_inverted_index":{"Scene":[0],"text":[1,19,95,119,132,143,162],"segmentation":[2,20,41,96],"task":[3,117],"has":[4],"numerous":[5],"practical":[6],"applications.":[7],"However,":[8],"the":[9,14,40,55,78,92,101,124,131,140,151,173],"number":[10],"of":[11,123,142,175],"images":[12,68],"in":[13,42],"available":[15,158],"datasets":[16,159,170],"for":[17,118,160],"scene":[18,94,161],"is":[21,52,88],"too":[22],"small":[23],"to":[24,31,60,81,98,129,134,171],"effectively":[25],"train":[26],"deep":[27],"learning-based":[28],"models,":[29],"leading":[30],"limited":[32],"performance.":[33],"To":[34],"solve":[35],"this":[36],"problem,":[37],"we":[38],"perform":[39],"two":[43,111,125],"aspects:":[44],"paired":[45,63,103],"data":[46],"synthesis":[47],"and":[48,114,147,168],"methodology.":[49],"The":[50,86,121],"former":[51],"executed":[53],"via":[54,73],"proposed":[56,79,93],"Text":[57],"Image-conditional":[58],"GANs":[59,80],"generate":[61],"realistic":[62,83],"data.":[64,85],"We":[65,154],"exploit":[66],"real-world":[67],"by":[69,91],"self-supervised":[70],"pre-training":[71],"scheme":[72],"inpainting":[74],"approach":[75],"before":[76],"training":[77],"produce":[82],"synthetic":[84],"latter":[87],"carried":[89],"out":[90],"network":[97],"optimize":[99],"learning":[100,139],"generated":[102],"data,":[104],"called":[105],"Multi-task":[106],"Cascade":[107],"Transformer.":[108],"It":[109],"includes":[110],"auxiliary":[112,126],"tasks":[113,127],"one":[115],"main":[116,152],"segmentation.":[120],"functions":[122],"are":[128],"learn":[130],"region":[133],"focus":[135],"on,":[136],"together":[137],"with":[138],"structure":[141],"through":[144],"their":[145],"fonts,":[146],"then":[148],"they":[149],"support":[150],"task.":[153],"implement":[155],"three":[156],"publicly":[157],"segmentation:":[163],"ICDAR13":[164],"FST,":[165],"Total":[166],"Text,":[167],"TextSeg":[169],"demonstrate":[172],"effectiveness":[174],"our":[176],"method.":[177],"Our":[178],"experimental":[179],"result":[180],"outperforms":[181],"existing":[182],"methods.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}