{"id":"https://openalex.org/W4224136936","doi":"https://doi.org/10.1145/3523150.3523169","title":"Transformer-Convolution Network for Arbitrary Shape Text Detection","display_name":"Transformer-Convolution Network for Arbitrary Shape Text Detection","publication_year":2022,"publication_date":"2022-01-15","ids":{"openalex":"https://openalex.org/W4224136936","doi":"https://doi.org/10.1145/3523150.3523169"},"language":"en","primary_location":{"id":"doi:10.1145/3523150.3523169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523150.3523169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 6th International Conference on Machine Learning and Soft Computing","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/A5101647823","display_name":"Yucheng Hu","orcid":"https://orcid.org/0000-0002-6321-4837"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yucheng Hu","raw_affiliation_strings":["Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451844","display_name":"Yuting Zhang","orcid":"https://orcid.org/0009-0005-8698-6142"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Zhang","raw_affiliation_strings":["Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049814360","display_name":"Wenxin Yu","orcid":"https://orcid.org/0000-0002-6093-5516"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Yu","raw_affiliation_strings":["Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002244885","display_name":"Tianxiang Lan","orcid":"https://orcid.org/0000-0001-9345-6856"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianxiang Lan","raw_affiliation_strings":["Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089567077","display_name":"Dong Yin","orcid":"https://orcid.org/0000-0003-1995-216X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yin","raw_affiliation_strings":["Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Electromagnetic Space Information of CAS, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101647823"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.1006,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34455833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"126"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9955000281333923,"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":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.7930973768234253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7574200630187988},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7237837314605713},{"id":"https://openalex.org/keywords/quadrilateral","display_name":"Quadrilateral","score":0.5897068977355957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5506517291069031},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.43890804052352905},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4046400189399719},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2004094123840332},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1871541440486908},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.134148508310318},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.09749084711074829},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0749841034412384}],"concepts":[{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.7930973768234253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574200630187988},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7237837314605713},{"id":"https://openalex.org/C151756577","wikidata":"https://www.wikidata.org/wiki/Q36810","display_name":"Quadrilateral","level":3,"score":0.5897068977355957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5506517291069031},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.43890804052352905},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4046400189399719},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2004094123840332},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1871541440486908},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.134148508310318},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.09749084711074829},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0749841034412384},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523150.3523169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523150.3523169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 6th International Conference on Machine Learning and Soft Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W654550266","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W2144554289","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2519887557","https://openalex.org/W2550687635","https://openalex.org/W2559655401","https://openalex.org/W2565639579","https://openalex.org/W2593539516","https://openalex.org/W2604272474","https://openalex.org/W2605982830","https://openalex.org/W2612445135","https://openalex.org/W2612690371","https://openalex.org/W2613718673","https://openalex.org/W2772800855","https://openalex.org/W2810028092","https://openalex.org/W2923906479","https://openalex.org/W2963446712","https://openalex.org/W2963647456","https://openalex.org/W2964015378","https://openalex.org/W2964294787","https://openalex.org/W2965463054","https://openalex.org/W2967615747","https://openalex.org/W3034514377","https://openalex.org/W3034792612","https://openalex.org/W3045482416","https://openalex.org/W3082397598","https://openalex.org/W3094502228","https://openalex.org/W3106228955","https://openalex.org/W3138516171","https://openalex.org/W3181016597","https://openalex.org/W4297775537","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4225381306","https://openalex.org/W1968844089","https://openalex.org/W2953041517","https://openalex.org/W2077820952","https://openalex.org/W2898882437","https://openalex.org/W2164512662","https://openalex.org/W2352017532","https://openalex.org/W2027181523","https://openalex.org/W4231998818","https://openalex.org/W4306155867"],"abstract_inverted_index":{"Arbitrary":[0],"shape":[1,156],"text":[2,32,52,153,157],"detection":[3,39,53],"is":[4,68],"a":[5,44,107],"prevalent":[6],"topic":[7],"in":[8,13,50,95,138,151],"computer":[9],"vision.":[10],"Text":[11],"instances":[12],"natural":[14],"scenes":[15],"may":[16],"involve":[17],"different":[18,20],"sizes,":[19],"shapes,":[21],"and":[22,63,102,114],"complex":[23],"background":[24],"textures.":[25],"Therefore,":[26],"the":[27,75,112,116,128,132,139,147],"ability":[28],"to":[29,48,70,92,106],"extract":[30,71],"accurate":[31],"features":[33,73,101],"becomes":[34],"extremely":[35],"significant":[36],"for":[37],"subsequent":[38],"work.":[40],"This":[41],"paper":[42],"proposes":[43],"novel":[45],"Transformer-Convolution":[46],"Network(TCNet)":[47],"participate":[49],"scene":[51],"task.":[54],"TCNet":[55],"contains":[56],"two":[57,88],"major":[58],"modules":[59],"named":[60],"CNN":[61,66],"module":[62,67,80],"Transformer":[64,79],"module.":[65],"used":[69],"local":[72,85,100],"from":[74],"input":[76],"images,":[77],"while":[78],"establish":[81],"connections":[82],"among":[83],"various":[84],"features.":[86],"The":[87],"structures":[89],"are":[90],"complementary":[91],"each":[93],"other,":[94],"particular,":[96],"such":[97],"combination":[98],"between":[99],"relative":[103],"locations":[104],"contributes":[105],"more":[108],"precise":[109],"detection,":[110],"promoting":[111],"convergence":[113],"reducing":[115],"amount":[117],"of":[118,134,141],"parameters.":[119],"Numerous":[120],"experiments":[121],"based":[122],"on":[123],"public":[124],"datasets":[125],"have":[126],"demonstrated":[127],"excellent":[129],"performance":[130,149],"under":[131],"condition":[133],"sufficient":[135],"data.":[136],"specifically,":[137],"case":[140],"small":[142],"data,":[143],"our":[144],"method":[145],"achieves":[146],"state-of-the-art":[148],"whether":[150],"quadrilateral":[152],"or":[154],"arbitrary":[155],"datasets.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}