{"id":"https://openalex.org/W4376630167","doi":"https://doi.org/10.3390/s23094490","title":"Lightweight Scene Text Recognition Based on Transformer","display_name":"Lightweight Scene Text Recognition Based on Transformer","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4376630167","doi":"https://doi.org/10.3390/s23094490","pmid":"https://pubmed.ncbi.nlm.nih.gov/37177694"},"language":"en","primary_location":{"id":"doi:10.3390/s23094490","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23094490","pdf_url":"https://www.mdpi.com/1424-8220/23/9/4490/pdf?version=1683266725","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/9/4490/pdf?version=1683266725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114050200","display_name":"Xin Luan","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Luan","raw_affiliation_strings":["College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392712","display_name":"Jinwei Zhang","orcid":"https://orcid.org/0000-0002-9116-358X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Zhang","raw_affiliation_strings":["College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087487085","display_name":"Miaomiao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaomiao Xu","raw_affiliation_strings":["College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109198165","display_name":"Wushouer Silamu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wushouer Silamu","raw_affiliation_strings":["College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007551785","display_name":"Yanbing Li","orcid":"https://orcid.org/0009-0000-3271-5279"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanbing Li","raw_affiliation_strings":["College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007551785"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":1.4654,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81912181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"23","issue":"9","first_page":"4490","last_page":"4490"},"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":0.9969000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9954000115394592,"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":0.7507940530776978},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6521371603012085},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6304854154586792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904167294502258},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5591483116149902},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4906217157840729},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4690112769603729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40005379915237427},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35285288095474243},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16065478324890137},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15618720650672913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507940530776978},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6521371603012085},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6304854154586792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904167294502258},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5591483116149902},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4906217157840729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4690112769603729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40005379915237427},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35285288095474243},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16065478324890137},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15618720650672913},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s23094490","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23094490","pdf_url":"https://www.mdpi.com/1424-8220/23/9/4490/pdf?version=1683266725","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:37177694","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37177694","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10181526","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10181526","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10181526/pdf/sensors-23-04490.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:ab32f1e6e6444bd78297c8e536a470b0","is_oa":true,"landing_page_url":"https://doaj.org/article/ab32f1e6e6444bd78297c8e536a470b0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 9, p 4490 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/9/4490/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23094490","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 23; Issue 9; Pages: 4490","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23094490","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23094490","pdf_url":"https://www.mdpi.com/1424-8220/23/9/4490/pdf?version=1683266725","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376630167.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1902237438","https://openalex.org/W1922126009","https://openalex.org/W1978729128","https://openalex.org/W1981283549","https://openalex.org/W2043075591","https://openalex.org/W2049951199","https://openalex.org/W2061802763","https://openalex.org/W2078997308","https://openalex.org/W2141756865","https://openalex.org/W2144554289","https://openalex.org/W2151815580","https://openalex.org/W2157331557","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2593572697","https://openalex.org/W2595620450","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2751169665","https://openalex.org/W2809273748","https://openalex.org/W2891939579","https://openalex.org/W2899368669","https://openalex.org/W2963327605","https://openalex.org/W2997749585","https://openalex.org/W3003478049","https://openalex.org/W3035106683","https://openalex.org/W3106271744","https://openalex.org/W3110267192","https://openalex.org/W3116489684","https://openalex.org/W3176387555","https://openalex.org/W3204479434","https://openalex.org/W4213339374","https://openalex.org/W4312879041","https://openalex.org/W6649973027","https://openalex.org/W6682804188","https://openalex.org/W6772198947"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2055243143","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Scene":[0],"text":[1,16],"recognition":[2,103,117],"(STR)":[3],"has":[4],"been":[5],"a":[6,43,113,134,144],"hot":[7],"research":[8,76],"field":[9],"in":[10,17,61],"computer":[11],"vision,":[12],"aiming":[13],"to":[14,27,67,88,100,124],"recognize":[15],"natural":[18],"scenes":[19],"using":[20],"computers.":[21],"Currently,":[22],"attention-based":[23],"encoder-decoder":[24],"frameworks":[25],"struggle":[26],"precisely":[28],"align":[29],"feature":[30],"regions":[31],"with":[32,38,50,97],"the":[33,51,55,69,74,120,125,131],"target":[34],"object":[35],"when":[36],"dealing":[37],"complex":[39],"and":[40,92,139,150],"low-quality":[41],"images,":[42],"phenomenon":[44],"known":[45],"as":[46],"attention":[47,90],"drift.":[48],"Additionally,":[49],"rise":[52],"of":[53,58,78,133,137],"Transformer,":[54],"increasing":[56],"size":[57],"parameters":[59,138],"results":[60,77,107],"higher":[62,115],"computational":[63,151],"costs.":[64],"In":[65],"order":[66],"solve":[68],"above":[70],"problems,":[71],"based":[72],"on":[73,119],"latest":[75],"Vision":[79],"Transformer":[80],"(ViT),":[81],"we":[82],"utilize":[83],"an":[84],"additional":[85],"position-enhancement":[86],"branch":[87],"alleviate":[89],"drift":[91],"dynamically":[93],"fused":[94],"position":[95],"information":[96,99],"visual":[98],"achieve":[101],"better":[102],"accuracy.":[104],"The":[105],"experimental":[106],"demonstrate":[108],"that":[109],"our":[110,128],"model":[111,129],"achieves":[112],"3%":[114],"average":[116],"accuracy":[118],"test":[121],"set":[122],"compared":[123],"baseline.":[126],"Meanwhile,":[127],"maintains":[130],"advantage":[132],"small":[135],"number":[136],"fast":[140],"inference":[141],"speed,":[142,149],"achieving":[143],"good":[145],"balance":[146],"between":[147],"accuracy,":[148],"load.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
