{"id":"https://openalex.org/W4382201018","doi":"https://doi.org/10.1145/3589883.3589914","title":"Are Attention blocks better than BiLSTM for text recognition?\u00a0","display_name":"Are Attention blocks better than BiLSTM for text recognition?\u00a0","publication_year":2023,"publication_date":"2023-03-10","ids":{"openalex":"https://openalex.org/W4382201018","doi":"https://doi.org/10.1145/3589883.3589914"},"language":"en","primary_location":{"id":"doi:10.1145/3589883.3589914","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589883.3589914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 8th International Conference on Machine Learning Technologies","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/A5092275859","display_name":"Amine Mohamed Belhakimi","orcid":"https://orcid.org/0009-0005-7251-0901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amine Mohamed Belhakimi","raw_affiliation_strings":["Idnow center of excellence, Idnow gmbh, France"],"raw_orcid":"https://orcid.org/0009-0005-7251-0901","affiliations":[{"raw_affiliation_string":"Idnow center of excellence, Idnow gmbh, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030515939","display_name":"Guillaume Chiron","orcid":"https://orcid.org/0009-0004-3665-4900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Chiron","raw_affiliation_strings":["Idnow center of excellence, Idnow gmbh, France"],"raw_orcid":"https://orcid.org/0009-0004-3665-4900","affiliations":[{"raw_affiliation_string":"Idnow center of excellence, Idnow gmbh, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019366178","display_name":"Florian Arrestier","orcid":"https://orcid.org/0000-0002-3777-374X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Arrestier","raw_affiliation_strings":["Idnow center of excellence, Idnow gmbh, France"],"raw_orcid":"https://orcid.org/0000-0002-3777-374X","affiliations":[{"raw_affiliation_string":"Idnow center of excellence, Idnow gmbh, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069198157","display_name":"Ahmad Montaser Awal","orcid":"https://orcid.org/0000-0002-0479-6312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad Montaser Awal","raw_affiliation_strings":["Idnow center of excellence, Idnow gmbh, France"],"raw_orcid":"https://orcid.org/0000-0002-0479-6312","affiliations":[{"raw_affiliation_string":"Idnow center of excellence, Idnow gmbh, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"issue":null,"first_page":"201","last_page":"207"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9923999905586243,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9890000224113464,"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":0.8366611003875732},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6380106210708618},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6351309418678284},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6320211291313171},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6180589199066162},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5242096185684204},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.4992353916168213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4860832989215851},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4546007812023163},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4309893250465393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4176400303840637},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.153256356716156},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10707294940948486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366611003875732},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6380106210708618},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6351309418678284},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6320211291313171},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6180589199066162},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5242096185684204},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4992353916168213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860832989215851},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4546007812023163},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4309893250465393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4176400303840637},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.153256356716156},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10707294940948486},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589883.3589914","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589883.3589914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 8th International Conference on Machine Learning Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2085261163","https://openalex.org/W2103828746","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2561907692","https://openalex.org/W2951559648","https://openalex.org/W2984329012","https://openalex.org/W3094502228","https://openalex.org/W3133413699","https://openalex.org/W4256149497","https://openalex.org/W6649973027","https://openalex.org/W6652761251","https://openalex.org/W6744310024","https://openalex.org/W6780493881","https://openalex.org/W6929439978"],"related_works":["https://openalex.org/W4306707571","https://openalex.org/W3179897446","https://openalex.org/W4309224528","https://openalex.org/W1562999394","https://openalex.org/W2970150031","https://openalex.org/W3211896491","https://openalex.org/W3153225109","https://openalex.org/W3163712264","https://openalex.org/W4362605793","https://openalex.org/W3035903760"],"abstract_inverted_index":{"This":[0],"paper":[1,82],"studies":[2],"the":[3,27,40,84,140],"impact":[4],"of":[5,35,43,51,86,116],"using":[6],"Sequential":[7],"Attention":[8,87,93,146],"blocks":[9,88,94,147],"versus":[10],"Bidirectional":[11],"Long-Short-Term":[12],"Memory":[13],"(BiLSTM)":[14],"layers":[15],"for":[16],"Optical":[17],"Character":[18],"Recognition":[19,126],"(OCR).":[20],"The":[21],"main":[22],"target":[23],"is":[24],"to":[25,90,96,99,133,149],"improve":[26],"inference":[28],"time":[29],"\u2013":[30,34],"specifically":[31],"on":[32,58,67,102,111],"CPU":[33],"state-of-the-art":[36],"OCRs,":[37],"with":[38,46],"also":[39],"additional":[41],"constraint":[42],"being":[44,134],"trainable":[45],"only":[47],"a":[48,112],"restricted":[49],"amount":[50],"data.":[52],"While":[53],"OCR":[54],"research":[55],"often":[56],"focuses":[57],"improving":[59],"recognition":[60],"accuracy,":[61],"there":[62],"has":[63],"been":[64],"little":[65],"emphasis":[66],"optimizing":[68],"processing":[69],"speed":[70],"and":[71,107,121,136],"model":[72],"weights.":[73],"In":[74],"this":[75,81],"context,":[76],"experimental":[77],"results":[78],"presented":[79],"in":[80,131],"show":[83],"superiority":[85],"compared":[89],"BiLSTM":[91],"layers.":[92],"appear":[95],"be":[97],"up":[98],"5x":[100],"faster":[101,135],"CPU,":[103],"while":[104],"achieving":[105],"better":[106],"similar":[108],"decoding":[109],"rates":[110],"typical":[113],"industrial":[114],"dataset":[115],"identity":[117],"document":[118],"text":[119],"fields":[120],"publicly":[122],"available":[123],"Scene":[124],"Text":[125],"(STR)":[127],"datasets,":[128],"respectively.":[129],"Also,":[130],"addition":[132],"accurate,":[137],"which":[138],"was":[139],"primary":[141],"goal,":[142],"it":[143],"appears":[144],"that":[145],"lead":[148],"lighter":[150],"models.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}