{"id":"https://openalex.org/W3133428700","doi":"https://doi.org/10.1109/icmla51294.2020.00223","title":"SAFL: A Self-Attention Scene Text Recognizer with Focal Loss","display_name":"SAFL: A Self-Attention Scene Text Recognizer with Focal Loss","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3133428700","doi":"https://doi.org/10.1109/icmla51294.2020.00223","mag":"3133428700"},"language":"en","primary_location":{"id":"doi:10.1109/icmla51294.2020.00223","doi":"https://doi.org/10.1109/icmla51294.2020.00223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla51294.2020.00223","pdf_url":null,"source":{"id":"https://openalex.org/S4306419645","display_name":"International Conference on Machine Learning and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.00132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056033008","display_name":"Bao Hieu Tran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405277486","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc Khoa h\u1ecdc v\u00e0 C\u00f4ng ngh\u1ec7 H\u00e0 N\u1ed9i","ror":"https://ror.org/02wdwrr89","country_code":"VN","type":"education","lineage":["https://openalex.org/I4405277486"]},{"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":"Bao Hieu Tran","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4405277486","https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013306670","display_name":"Thanh Le-Cong","orcid":"https://orcid.org/0000-0002-9566-324X","observed_orcids":["https://orcid.org/0000-0002-9566-324X"]},"institutions":[{"id":"https://openalex.org/I4405277486","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc Khoa h\u1ecdc v\u00e0 C\u00f4ng ngh\u1ec7 H\u00e0 N\u1ed9i","ror":"https://ror.org/02wdwrr89","country_code":"VN","type":"education","lineage":["https://openalex.org/I4405277486"]},{"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":"Thanh Le-Cong","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4405277486","https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huu Manh Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405277486","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc Khoa h\u1ecdc v\u00e0 C\u00f4ng ngh\u1ec7 H\u00e0 N\u1ed9i","ror":"https://ror.org/02wdwrr89","country_code":"VN","type":"education","lineage":["https://openalex.org/I4405277486"]},{"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":"Huu Manh Nguyen","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4405277486","https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103029566","display_name":"Duc Anh Le","orcid":"https://orcid.org/0009-0006-4201-0305","observed_orcids":["https://orcid.org/0009-0006-4201-0305"]},"institutions":[{"id":"https://openalex.org/I4405277486","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc Khoa h\u1ecdc v\u00e0 C\u00f4ng ngh\u1ec7 H\u00e0 N\u1ed9i","ror":"https://ror.org/02wdwrr89","country_code":"VN","type":"education","lineage":["https://openalex.org/I4405277486"]},{"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":"Duc Anh Le","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4405277486","https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077593563","display_name":"Thanh-Hung Nguyen","orcid":"https://orcid.org/0000-0003-4865-7127","observed_orcids":["https://orcid.org/0000-0003-4865-7127","https://orcid.org/0000-0001-6290-2841","https://orcid.org/0000-0002-7405-2984","https://orcid.org/0000-0002-4847-0269"]},"institutions":[{"id":"https://openalex.org/I4405277486","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc Khoa h\u1ecdc v\u00e0 C\u00f4ng ngh\u1ec7 H\u00e0 N\u1ed9i","ror":"https://ror.org/02wdwrr89","country_code":"VN","type":"education","lineage":["https://openalex.org/I4405277486"]},{"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":"Thanh Hung Nguyen","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4405277486","https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058485829","display_name":"Phi Le Nguyen","orcid":"https://orcid.org/0000-0001-6547-7641","observed_orcids":["https://orcid.org/0000-0001-6547-7641"]},"institutions":[{"id":"https://openalex.org/I4405277486","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc Khoa h\u1ecdc v\u00e0 C\u00f4ng ngh\u1ec7 H\u00e0 N\u1ed9i","ror":"https://ror.org/02wdwrr89","country_code":"VN","type":"education","lineage":["https://openalex.org/I4405277486"]},{"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":"Phi Le Nguyen","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4405277486","https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1541,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.50758057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1440","last_page":"1445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0006000000284984708,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/scene-text-recognition","display_name":"scene text recognition","score":1.0},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.9879999756813049},{"id":"https://openalex.org/keywords/focal-loss","display_name":"focal loss","score":1.0},{"id":"https://openalex.org/keywords/spatial-transformer-network","display_name":"spatial transformer network","score":0.8769999742507935},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.7730000019073486},{"id":"https://openalex.org/keywords/text-distortion","display_name":"text distortion","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8418335914611816},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7967960238456726},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7940807342529297},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5963397026062012},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.587835431098938},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5666413307189941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5312625765800476},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5228122472763062},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4974682629108429},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4910545349121094},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.48385488986968994},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3540194630622864},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3244580030441284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18151599168777466},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla51294.2020.00223","doi":"https://doi.org/10.1109/icmla51294.2020.00223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla51294.2020.00223","pdf_url":null,"source":{"id":"https://openalex.org/S4306419645","display_name":"International Conference on Machine Learning and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.00132","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.00132","pdf_url":"https://arxiv.org/pdf/2201.00132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2201.00132","doi":"https://doi.org/10.48550/arxiv.2201.00132","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2201.00132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.00132","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.00132","pdf_url":"https://arxiv.org/pdf/2201.00132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W654550266","https://openalex.org/W1491389626","https://openalex.org/W1521064364","https://openalex.org/W1686810756","https://openalex.org/W1812645736","https://openalex.org/W1971822075","https://openalex.org/W1978729128","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2049951199","https://openalex.org/W2099247484","https://openalex.org/W2107878631","https://openalex.org/W2135231474","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2626778328","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2788069964","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2884561390","https://openalex.org/W2928555987","https://openalex.org/W2951005624","https://openalex.org/W2962790387","https://openalex.org/W2963233387","https://openalex.org/W2963327605","https://openalex.org/W2963351448","https://openalex.org/W2963517393","https://openalex.org/W2963712589","https://openalex.org/W2964199361","https://openalex.org/W2965066169","https://openalex.org/W3004846386","https://openalex.org/W3030520226","https://openalex.org/W3037932933","https://openalex.org/W4295224299"],"related_works":["https://openalex.org/W2984470164","https://openalex.org/W3034784202","https://openalex.org/W2593572697","https://openalex.org/W3160573439","https://openalex.org/W3043311956","https://openalex.org/W2990832606","https://openalex.org/W3198037736","https://openalex.org/W4226085172","https://openalex.org/W3163848781","https://openalex.org/W2806488338"],"abstract_inverted_index":{"In":[0,94],"the":[1,13,52,106,115,118,131,143,159,167,170,184],"last":[2],"decades,":[3],"scene":[4,35,110],"text":[5,36,111,155],"recognition":[6,37,160],"has":[7],"gained":[8],"worldwide":[9],"attention":[10],"from":[11,70],"both":[12],"academic":[14],"community":[15],"and":[16,78,92,145],"actual":[17],"users":[18],"due":[19,40,74],"to":[20,41,75,113,140,153,158,165],"its":[21],"importance":[22],"in":[23,31],"a":[24,88,100],"wide":[25],"range":[26],"of":[27,51,117,123,127,169],"applications.":[28],"Despite":[29],"achievements":[30],"optical":[32],"character":[33],"recognition,":[34,112],"remains":[38],"challenging":[39],"inherent":[42],"problems":[43,80],"such":[44],"as":[45,81],"distortions":[46,144],"or":[47,58,84],"irregular":[48,146],"layout.":[49],"Most":[50],"existing":[53,119],"approaches":[54],"mainly":[55],"leverage":[56],"recurrence":[57],"convolution-based":[59],"neural":[60,65,102],"networks.":[61],"However,":[62],"while":[63],"recurrent":[64],"networks":[66],"(RNNs)":[67],"usually":[68],"suffer":[69],"slow":[71],"training":[72],"speed":[73],"sequential":[76],"computation":[77],"encounter":[79],"vanishing":[82],"gradient":[83],"bottleneck,":[85],"CNN":[86],"endures":[87],"trade-off":[89],"between":[90],"complexity":[91],"performance.":[93,186],"this":[95],"paper,":[96],"we":[97,148],"introduce":[98],"SAFL,":[99],"self-attention-based":[101],"network":[103],"model":[104,132,172,182],"with":[105,142,173],"focal":[107,124],"loss":[108,125],"for":[109],"overcome":[114],"limitation":[116],"approaches.":[120],"The":[121,176],"use":[122],"instead":[126],"negative":[128],"log-likelihood":[129],"helps":[130],"focus":[133],"more":[134],"on":[135],"low-frequency":[136],"samples":[137],"training.":[138],"Moreover,":[139],"deal":[141],"texts,":[147],"exploit":[149],"Spatial":[150],"TransformerNetwork":[151],"(STN)":[152],"rectify":[154],"before":[156],"passing":[157],"network.":[161],"We":[162],"perform":[163],"experiments":[164],"compare":[166],"performance":[168],"proposed":[171],"seven":[174],"benchmarks.":[175],"numerical":[177],"results":[178],"show":[179],"that":[180],"our":[181],"achieves":[183],"best":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2021-03-01T00:00:00"}
