{"id":"https://openalex.org/W4388928556","doi":"https://doi.org/10.1142/s021800142353004x","title":"LCSTR: Scene Text Recognition with Large Convolutional Kernels","display_name":"LCSTR: Scene Text Recognition with Large Convolutional Kernels","publication_year":2023,"publication_date":"2023-11-23","ids":{"openalex":"https://openalex.org/W4388928556","doi":"https://doi.org/10.1142/s021800142353004x"},"language":"en","primary_location":{"id":"doi:10.1142/s021800142353004x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021800142353004x","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5100375441","display_name":"Jiale Wang","orcid":"https://orcid.org/0009-0004-3213-8167"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiale Wang","raw_affiliation_strings":["Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0004-3213-8167","affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008154497","display_name":"Lina Yang","orcid":"https://orcid.org/0000-0003-3489-1887"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Yang","raw_affiliation_strings":["Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0003-3489-1887","affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114626655","display_name":"Jing Wang","orcid":"https://orcid.org/0009-0005-4449-377X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0005-4449-377X","affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyan Yang","orcid":"https://orcid.org/0000-0002-8769-9736"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyan Yang","raw_affiliation_strings":["Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0002-8769-9736","affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114626486","display_name":"Lin Bai","orcid":"https://orcid.org/0000-0001-8311-1694"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Bai","raw_affiliation_strings":["Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0001-8311-1694","affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077075722","display_name":"Patrick S. P. Wang","orcid":"https://orcid.org/0000-0002-9336-3155"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Shen-Pei Wang","raw_affiliation_strings":["College of Comouter and Informatiomn Science, Northeastern University, Boston, MA 02115, USA"],"raw_orcid":"https://orcid.org/0000-0002-9336-3155","affiliations":[{"raw_affiliation_string":"College of Comouter and Informatiomn Science, Northeastern University, Boston, MA 02115, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114626582","display_name":"Xichun Li","orcid":"https://orcid.org/0009-0006-1921-1651"},"institutions":[{"id":"https://openalex.org/I4210118063","display_name":"Guangxi Normal University for Nationalities","ror":"https://ror.org/02cejc171","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210118063"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xichun Li","raw_affiliation_strings":["Guangxi Normal University for Nationalities, Chongzuo 532200, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0006-1921-1651","affiliations":[{"raw_affiliation_string":"Guangxi Normal University for Nationalities, Chongzuo 532200, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I4210118063"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101498949","display_name":"Huiwu Luo","orcid":"https://orcid.org/0000-0002-5908-5518"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiwu Luo","raw_affiliation_strings":["Changsha Xingshen Intelligent Technology Co., Ltd, Changsha 410100, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0002-5908-5518","affiliations":[{"raw_affiliation_string":"Changsha Xingshen Intelligent Technology Co., Ltd, Changsha 410100, P.\u00a0R.\u00a0China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100580973","display_name":"Huafu Xu","orcid":"https://orcid.org/0009-0007-2848-9900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huafu Xu","raw_affiliation_strings":["Guangxi Key Laboratory of Digital Infrastructure, Guangxi Information Center, Nanning 530200, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0007-2848-9900","affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Digital Infrastructure, Guangxi Information Center, Nanning 530200, P.\u00a0R.\u00a0China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100375441"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":0.1127,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42887673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"38","issue":"01","first_page":null,"last_page":null},"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":0.9918000102043152,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7011120915412903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6599857807159424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5660398602485657},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5645889639854431},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4337823688983917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3355017900466919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32268208265304565}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7011120915412903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6599857807159424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5660398602485657},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5645889639854431},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4337823688983917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3355017900466919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32268208265304565}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s021800142353004x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021800142353004x","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5659565908","display_name":"\u57fa\u4e8e\u6df7\u5408\u6df1\u5ea6\u5b66\u4e60\u7684\u56fe\u50cf\u4eba\u4e0e\u7269\u4f53\u4ea4\u4e92\u6d3b\u52a8\u8bc6\u522b\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61966003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6300071479","display_name":null,"funder_award_id":"2020GXNSFAA159171","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G7226221071","display_name":null,"funder_award_id":"62371144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2099247484","https://openalex.org/W2127141656","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2612690371","https://openalex.org/W2809273748","https://openalex.org/W2810983211","https://openalex.org/W2962790387","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2965066169","https://openalex.org/W2982083293","https://openalex.org/W2990138404","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3034414401","https://openalex.org/W3035449864","https://openalex.org/W3035682737","https://openalex.org/W3043311956","https://openalex.org/W3113987534","https://openalex.org/W3122930709","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W3205961173","https://openalex.org/W3213619440","https://openalex.org/W4210692322","https://openalex.org/W4226334005","https://openalex.org/W4283805255","https://openalex.org/W4287448984","https://openalex.org/W4292825881","https://openalex.org/W4309343528","https://openalex.org/W4312443924","https://openalex.org/W4312843595","https://openalex.org/W4313045695","https://openalex.org/W4320489219","https://openalex.org/W4386076222","https://openalex.org/W4386160491"],"related_works":["https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W2947043951","https://openalex.org/W4399188509","https://openalex.org/W2318112981","https://openalex.org/W4210874298"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,43,151,159],"scene":[3,36],"text":[4,37,78,95,104],"recognition":[5,38,79,96],"involves":[6],"processing":[7],"information":[8,105],"from":[9,25],"two":[10],"modalities:":[11],"images":[12,26],"and":[13,27,49,62,115,137,149,173,176],"text,":[14],"thereby":[15],"requiring":[16],"models":[17,45],"to":[18,22,94,120,156],"have":[19],"the":[20,40,81,99,147,157,174],"ability":[21],"extract":[23],"features":[24,123,180],"model":[28,50,58,74,130,164],"sequences":[29],"simultaneously.":[30],"Although":[31],"linguistic":[32],"knowledge":[33],"greatly":[34],"aids":[35],"tasks,":[39],"extensive":[41],"use":[42],"language":[44,87,161],"in":[46,53,169],"sequence":[47],"modeling":[48],"prediction":[51],"stages":[52],"recent":[54],"years":[55],"has":[56],"made":[57],"architectures":[59],"increasingly":[60],"complex":[61],"inefficient.":[63],"In":[64],"this":[65,129,152,163],"paper,":[66],"we":[67],"propose":[68],"LCSTR,":[69],"a":[70,132,160],"pure":[71],"convolutional":[72],"visual":[73],"that":[75,128],"can":[76],"complete":[77],"without":[80],"need":[82],"for":[83,98,184],"attention":[84],"mechanisms":[85],"or":[86],"models.":[88],"This":[89],"approach":[90],"applies":[91],"large":[92,107],"kernels":[93],"tasks":[97],"first":[100],"time,":[101],"extracting":[102],"word-level":[103],"through":[106],"text-aware":[108,118],"blocks,":[109],"capturing":[110],"long-range":[111],"dependencies":[112],"between":[113,135],"characters,":[114],"using":[116],"small":[117],"blocks":[119],"obtain":[121],"local":[122],"within":[124],"characters.":[125],"Experiments":[126],"show":[127],"strikes":[131],"good":[133],"trade-off":[134],"accuracy":[136,167],"speed,":[138],"achieving":[139],"notable":[140],"results":[141],"on":[142],"seven":[143],"public":[144],"benchmarks,":[145],"validating":[146],"generalizability":[148],"effectiveness":[150],"method.":[153],"Furthermore,":[154],"owing":[155],"absence":[158],"module,":[162],"demonstrates":[165],"remarkable":[166],"even":[168],"limited":[170],"sample":[171],"scenarios,":[172],"lightweight":[175],"low":[177],"computational":[178],"overhead":[179],"make":[181],"it":[182],"suitable":[183],"engineering":[185],"applications.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}