{"id":"https://openalex.org/W3112478873","doi":"https://doi.org/10.1109/tpami.2022.3144899","title":"End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network","display_name":"End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network","publication_year":2022,"publication_date":"2022-01-25","ids":{"openalex":"https://openalex.org/W3112478873","doi":"https://doi.org/10.1109/tpami.2022.3144899","mag":"3112478873","pmid":"https://pubmed.ncbi.nlm.nih.gov/35077353"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3144899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3144899","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.03868","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Denis Coquenet","orcid":"https://orcid.org/0000-0001-5203-9423"},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Denis Coquenet","raw_affiliation_strings":["LITIS EA 4108, Saint-Étienne-du-Rouvray, France"],"raw_orcid":"https://orcid.org/0000-0001-5203-9423","affiliations":[{"raw_affiliation_string":"LITIS EA 4108, Saint-Étienne-du-Rouvray, France","institution_ids":["https://openalex.org/I4210108118"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Clement Chatelain","orcid":"https://orcid.org/0000-0001-8377-0630"},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Clement Chatelain","raw_affiliation_strings":["LITIS EA 4108, Saint-Étienne-du-Rouvray, France"],"raw_orcid":"https://orcid.org/0000-0001-8377-0630","affiliations":[{"raw_affiliation_string":"LITIS EA 4108, Saint-Étienne-du-Rouvray, France","institution_ids":["https://openalex.org/I4210108118"]}]},{"author_position":"last","author":{"id":null,"display_name":"Thierry Paquet","orcid":"https://orcid.org/0000-0002-2044-7542"},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thierry Paquet","raw_affiliation_strings":["LITIS EA 4108, Saint-Étienne-du-Rouvray, France"],"raw_orcid":"https://orcid.org/0000-0002-2044-7542","affiliations":[{"raw_affiliation_string":"LITIS EA 4108, Saint-Étienne-du-Rouvray, France","institution_ids":["https://openalex.org/I4210108118"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210108118"],"apc_list":null,"apc_paid":null,"fwci":11.9766,"has_fulltext":true,"cited_by_count":132,"citation_normalized_percentile":{"value":0.99169935,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"45","issue":"1","first_page":"508","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9925000071525574,"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":0.9925000071525574,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0013000000035390258,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.000699999975040555,"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/paragraph","display_name":"Paragraph","score":0.8934000134468079},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6796000003814697},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.5623999834060669},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5555999875068665},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5400999784469604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4778999984264374},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4408999979496002},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4404999911785126},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.43130001425743103},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.8934000134468079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217999935150146},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6796000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6747000217437744},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5130000114440918},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5027999877929688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.3440000116825104},{"id":"https://openalex.org/C17649283","wikidata":"https://www.wikidata.org/wiki/Q6044162","display_name":"Intelligent word recognition","level":5,"score":0.32670000195503235},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C182124507","wikidata":"https://www.wikidata.org/wiki/Q166154","display_name":"Line segment","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tpami.2022.3144899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3144899","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35077353","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35077353","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2012.03868","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.03868","pdf_url":"https://arxiv.org/pdf/2012.03868","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:HAL:hal-05273612v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05273612","pdf_url":"https://hal.science/hal-05273612v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (1), pp.508-524. ⟨10.1109/TPAMI.2022.3144899⟩","raw_type":"Journal articles"},{"id":"pmh:oai:HAL:hal-03413862v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03413862","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, ⟨10.1109/TPAMI.2022.3144899⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.03868","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.03868","pdf_url":"https://arxiv.org/pdf/2012.03868","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"},{"id":"https://openalex.org/F4320329938","display_name":"R\u00e9gion Normandie","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1881338276","https://openalex.org/W1936750108","https://openalex.org/W1982907973","https://openalex.org/W2020407556","https://openalex.org/W2060746081","https://openalex.org/W2098421869","https://openalex.org/W2099070536","https://openalex.org/W2109471037","https://openalex.org/W2114572161","https://openalex.org/W2127141656","https://openalex.org/W2132399877","https://openalex.org/W2133552271","https://openalex.org/W2137361365","https://openalex.org/W2141190215","https://openalex.org/W2141400498","https://openalex.org/W2149319679","https://openalex.org/W2152928267","https://openalex.org/W2531409750","https://openalex.org/W2573601984","https://openalex.org/W2577122925","https://openalex.org/W2786429113","https://openalex.org/W2786974559","https://openalex.org/W2787480186","https://openalex.org/W2798826627","https://openalex.org/W2807321692","https://openalex.org/W2810068724","https://openalex.org/W2895359355","https://openalex.org/W2962707697","https://openalex.org/W2963925710","https://openalex.org/W2973867564","https://openalex.org/W2984329012","https://openalex.org/W2984703264","https://openalex.org/W2987696791","https://openalex.org/W3003428515","https://openalex.org/W3003990305","https://openalex.org/W3021347667","https://openalex.org/W3034726763","https://openalex.org/W3038203375","https://openalex.org/W3041911668","https://openalex.org/W3109563519","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6674330103","https://openalex.org/W6677452488","https://openalex.org/W6679434410","https://openalex.org/W6704241340","https://openalex.org/W6753558063"],"related_works":[],"abstract_inverted_index":{"Unconstrained":[0],"handwritten":[1],"text":[2,11,30,92,107],"recognition":[3,12,121],"remains":[4],"challenging":[5],"for":[6,22,29,140,143,147],"computer":[7],"vision":[8],"systems.":[9],"Paragraph":[10],"is":[13,48],"traditionally":[14],"achieved":[15],"by":[16,57],"two":[17],"models:":[18],"the":[19,26,72,90,114,120],"first":[20],"one":[21,28],"line":[23,31,56,93,103,108],"segmentation":[24],"and":[25,145,152],"second":[27],"recognition.":[32],"We":[33,126],"propose":[34],"a":[35,53,82,99,110,123],"unified":[36],"end-to-end":[37],"model":[38,47,154],"using":[39],"hybrid":[40],"attention":[41,78],"to":[42,50,87,119],"tackle":[43],"this":[44],"task.":[45],"This":[46,95],"designed":[49],"iteratively":[51],"process":[52],"paragraph":[54,74,133],"image":[55],"line.":[58],"It":[59],"can":[60],"be":[61],"split":[62],"into":[63],"three":[64,136],"modules.":[65],"An":[66],"encoder":[67],"generates":[68,81],"feature":[69],"maps":[70],"from":[71],"whole":[73,124],"image.":[75],"Then,":[76],"an":[77],"module":[79,112],"recurrently":[80],"vertical":[83],"weighted":[84],"mask":[85],"enabling":[86],"focus":[88],"on":[89,135],"current":[91],"features.":[94],"way,":[96],"it":[97],"performs":[98],"kind":[100],"of":[101,122],"implicit":[102],"segmentation.":[104],"For":[105],"each":[106],"features,":[109],"decoder":[111],"recognizes":[113],"character":[115,129],"sequence":[116],"associated,":[117],"leading":[118],"paragraph.":[125],"achieve":[127],"state-of-the-art":[128],"error":[130],"rate":[131],"at":[132,158],"level":[134],"popular":[137],"datasets:":[138],"1.91%":[139],"RIMES,":[141],"4.45%":[142],"IAM":[144],"3.59%":[146],"READ":[148],"2016.":[149],"Our":[150],"code":[151],"trained":[153],"weights":[155],"are":[156],"available":[157],"https://github.com/FactoDeepLearning/VerticalAttentionOCR.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":8}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2020-12-21T00:00:00"}