{"id":"https://openalex.org/W4205355659","doi":"https://doi.org/10.1109/rivf51545.2021.9642119","title":"An Improved Deep Neural Network Based on a Novel Visual Attention Mechanism for Text Recognition","display_name":"An Improved Deep Neural Network Based on a Novel Visual Attention Mechanism for Text Recognition","publication_year":2021,"publication_date":"2021-08-19","ids":{"openalex":"https://openalex.org/W4205355659","doi":"https://doi.org/10.1109/rivf51545.2021.9642119"},"language":"en","primary_location":{"id":"doi:10.1109/rivf51545.2021.9642119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091304802","display_name":"Nguyen Trong Thai","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Trong Thai","raw_affiliation_strings":["Department of Computer Science, Hanoi University of Science and Technology, Hai Ba Trung, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanoi University of Science and Technology, Hai Ba Trung, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018101883","display_name":"Nguyen Hoang Thuan","orcid":"https://orcid.org/0000-0002-6241-8205"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Hoang Thuan","raw_affiliation_strings":["Department of Computer Science, Hanoi University of Science and Technology, Hai Ba Trung, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanoi University of Science and Technology, Hai Ba Trung, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025948040","display_name":"Dinh Viet Sang","orcid":"https://orcid.org/0000-0002-9254-1327"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dinh Viet Sang","raw_affiliation_strings":["Department of Computer Science, Hanoi University of Science and Technology, Hai Ba Trung, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanoi University of Science and Technology, Hai Ba Trung, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"6"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9970999956130981,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9905999898910522,"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":0.8580737113952637},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.6951555609703064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.619493305683136},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5952728986740112},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5299851894378662},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49958133697509766},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4351280629634857},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4284370541572571},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4207218587398529},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3405081033706665},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2823125123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580737113952637},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.6951555609703064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.619493305683136},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5952728986740112},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5299851894378662},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49958133697509766},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4351280629634857},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4284370541572571},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4207218587398529},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3405081033706665},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2823125123977661},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf51545.2021.9642119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337807","display_name":"U.S. Army Combat Capabilities Development Command","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W1557952530","https://openalex.org/W1901129140","https://openalex.org/W2079735306","https://openalex.org/W2122221966","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2955425717","https://openalex.org/W2963163009","https://openalex.org/W2963517393","https://openalex.org/W2971325593","https://openalex.org/W2994189733","https://openalex.org/W2995752927","https://openalex.org/W2998382406","https://openalex.org/W3000758063","https://openalex.org/W3003484198","https://openalex.org/W3003508901","https://openalex.org/W3106271744","https://openalex.org/W3127710088","https://openalex.org/W6602936574","https://openalex.org/W6633516429","https://openalex.org/W6639824700","https://openalex.org/W6679434410","https://openalex.org/W6684191040","https://openalex.org/W6697925102","https://openalex.org/W6753412334","https://openalex.org/W6762718338","https://openalex.org/W6772827613"],"related_works":["https://openalex.org/W2382997850","https://openalex.org/W4375867731","https://openalex.org/W4390516098","https://openalex.org/W2390968135","https://openalex.org/W2181948922","https://openalex.org/W3034529322","https://openalex.org/W2384362569","https://openalex.org/W2382213751","https://openalex.org/W2351750670","https://openalex.org/W1597848696"],"abstract_inverted_index":{"Text":[0],"recognition":[1,23,59],"from":[2],"images":[3,37],"captured":[4,38],"by":[5,90],"handheld":[6],"mobile":[7],"devices":[8],"has":[9],"attracted":[10],"considerable":[11],"research":[12],"interest":[13],"because":[14],"of":[15],"its":[16],"commercial":[17],"applications.":[18],"The":[19],"state-of-the-art":[20],"printed":[21],"text":[22,58],"methods":[24,33],"are":[25],"often":[26],"based":[27,61],"on":[28,36,62,96],"attention":[29,71,82,114],"mechanisms.":[30],"However,":[31],"these":[32,51],"perform":[34],"poorly":[35],"due":[39],"to":[40,121],"poor":[41],"illumination":[42],"conditions,":[43,53],"blur,":[44],"noise,":[45],"and":[46,104,116],"low":[47],"resolution.":[48],"To":[49],"address":[50],"unfavorable":[52],"we":[54,67],"propose":[55],"a":[56,69,74,80],"new":[57],"method":[60,110],"an":[63,91],"encoder-decoder":[64],"model.":[65],"Particularly,":[66],"present":[68],"novel":[70],"mechanism":[72,115],"using":[73],"multi-scale":[75],"cascade":[76],"fashion":[77],"combined":[78],"with":[79],"channel":[81],"gate":[83],"module.":[84],"Our":[85],"model":[86],"is":[87],"also":[88],"strengthened":[89],"EfficientNet-like":[92],"backbone.":[93],"Extensive":[94],"experiments":[95],"three":[97],"popular":[98],"datasets,":[99],"including":[100],"SROIE":[101],"2019,":[102],"B-MOD,":[103],"CORD,":[105],"show":[106],"that":[107],"our":[108],"proposed":[109],"outperforms":[111],"the":[112],"baseline":[113],"achieves":[117],"competitive":[118],"accuracy":[119],"compared":[120],"other":[122],"state-ofthe-art":[123],"approaches.":[124]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}