{"id":"https://openalex.org/W4372267020","doi":"https://doi.org/10.1109/icassp49357.2023.10094842","title":"A Dual-Path Transformer Network for Scene Text Detection","display_name":"A Dual-Path Transformer Network for Scene Text Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267020","doi":"https://doi.org/10.1109/icassp49357.2023.10094842"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5048406125","display_name":"Jingyu Lin","orcid":"https://orcid.org/0009-0006-6717-5261"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyu Lin","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044594971","display_name":"Hanzi Wang","orcid":"https://orcid.org/0000-0002-6913-9786"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048406125"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.8609,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74749148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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/T10601","display_name":"Handwritten Text Recognition Techniques","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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9912999868392944,"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":0.8171502351760864},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6880155801773071},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.667553722858429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5717318058013916},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5180556774139404},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4696684777736664},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46892979741096497},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4498542547225952},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.417283296585083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3576737940311432},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08611509203910828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171502351760864},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6880155801773071},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.667553722858429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717318058013916},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5180556774139404},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4696684777736664},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46892979741096497},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4498542547225952},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.417283296585083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3576737940311432},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08611509203910828},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":25,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1972065312","https://openalex.org/W2144554289","https://openalex.org/W2343052201","https://openalex.org/W2565639579","https://openalex.org/W2752782242","https://openalex.org/W2766895242","https://openalex.org/W2899663614","https://openalex.org/W2914492226","https://openalex.org/W2963299604","https://openalex.org/W2963647456","https://openalex.org/W2967615747","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W3034514377","https://openalex.org/W3184364189","https://openalex.org/W3184923351","https://openalex.org/W3186906052","https://openalex.org/W4214922754","https://openalex.org/W4225262244","https://openalex.org/W4385245566","https://openalex.org/W6638667902","https://openalex.org/W6642972425","https://openalex.org/W6739901393","https://openalex.org/W6755977528"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W2731899572","https://openalex.org/W4230611425","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W2317351040","https://openalex.org/W4383066092","https://openalex.org/W3215138031","https://openalex.org/W4200094402"],"abstract_inverted_index":{"The":[0],"prosperity":[1],"of":[2,10,32,48,131],"deep":[3],"learning":[4],"contributes":[5],"to":[6,25,45,66,95,110],"the":[7,16,40,46,74,87,115],"rapid":[8],"progress":[9],"scene":[11,75],"text":[12,30,76],"detection.":[13],"Among":[14],"all":[15],"methods,":[17],"segmentation-based":[18],"methods":[19,42],"have":[20],"drawn":[21],"extensive":[22],"attention":[23],"due":[24],"their":[26,49],"superiority":[27],"in":[28,129],"detecting":[29],"instances":[31],"arbitrary":[33],"shapes":[34],"and":[35,70,117,135],"extreme":[36],"aspect":[37],"ratios.":[38],"However,":[39],"bottom-up":[41],"are":[43],"limited":[44],"performance":[47],"segmentation":[50],"models.":[51],"In":[52,99],"this":[53],"paper,":[54],"we":[55,80],"propose":[56,81],"DPTNet":[57,121],"(Dual-Path":[58],"Transformer":[59],"Network),":[60],"a":[61,82,91,101],"simple":[62],"yet":[63],"effective":[64],"network":[65,89],"utilize":[67],"both":[68,132],"global":[69],"local":[71],"information":[72],"for":[73],"detection":[77,133],"task.":[78],"Moreover,":[79],"parallel":[83],"design":[84],"that":[85],"integrates":[86],"convolutional":[88],"with":[90],"powerful":[92],"self-attention":[93],"mechanism":[94],"provide":[96,111],"complementary":[97,112],"clues.":[98],"addition,":[100],"bi-directional":[102],"interaction":[103],"module":[104],"across":[105],"two":[106],"paths":[107],"is":[108],"developed":[109],"clues":[113],"along":[114],"channel":[116],"spatial":[118],"dimensions.":[119],"Our":[120],"achieves":[122],"state-of-the-art":[123],"results":[124],"on":[125],"several":[126],"standard":[127],"benchmarks":[128],"terms":[130],"accuracy":[134],"speed.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}