{"id":"https://openalex.org/W2194187530","doi":"https://doi.org/10.1109/tpami.2016.2646371","title":"An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition","display_name":"An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition","publication_year":2016,"publication_date":"2016-12-29","ids":{"openalex":"https://openalex.org/W2194187530","doi":"https://doi.org/10.1109/tpami.2016.2646371","mag":"2194187530","pmid":"https://pubmed.ncbi.nlm.nih.gov/28055850"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2016.2646371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2016.2646371","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":["crossref","pubmed"],"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/A5080734619","display_name":"Baoguang Shi","orcid":"https://orcid.org/0000-0001-6886-8189"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoguang Shi","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669593","display_name":"Cong Yao","orcid":"https://orcid.org/0000-0001-6564-4796"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Yao","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":122.5193,"has_fulltext":false,"cited_by_count":3164,"citation_normalized_percentile":{"value":0.99978694,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"39","issue":"11","first_page":"2298","last_page":"2304"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9990000128746033,"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":0.9914000034332275,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7391954064369202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7182372808456421},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6098981499671936},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5778326988220215},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5637760162353516},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.543155312538147},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5011613368988037},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4887113571166992},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4173886179924011},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.41169559955596924}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7391954064369202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182372808456421},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6098981499671936},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5778326988220215},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5637760162353516},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.543155312538147},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5011613368988037},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4887113571166992},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4173886179924011},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.41169559955596924},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2016.2646371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2016.2646371","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:28055850","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28055850","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1063076225","display_name":null,"funder_award_id":"61222308","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6211455402","display_name":null,"funder_award_id":"61573160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W70975097","https://openalex.org/W654550266","https://openalex.org/W753012316","https://openalex.org/W1491389626","https://openalex.org/W1498436455","https://openalex.org/W1557952530","https://openalex.org/W1607307044","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1895191496","https://openalex.org/W1922126009","https://openalex.org/W1922658220","https://openalex.org/W1975453746","https://openalex.org/W1981283549","https://openalex.org/W1988461287","https://openalex.org/W1990550880","https://openalex.org/W1994529543","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2043075591","https://openalex.org/W2045220951","https://openalex.org/W2053317383","https://openalex.org/W2064675550","https://openalex.org/W2099247484","https://openalex.org/W2102605133","https://openalex.org/W2107878631","https://openalex.org/W2112796928","https://openalex.org/W2122221966","https://openalex.org/W2122585011","https://openalex.org/W2127141656","https://openalex.org/W2135231474","https://openalex.org/W2143612262","https://openalex.org/W2153182373","https://openalex.org/W2341629100","https://openalex.org/W2618530766","https://openalex.org/W2963718330","https://openalex.org/W2964300754","https://openalex.org/W4235765578","https://openalex.org/W4285719527","https://openalex.org/W4312531999","https://openalex.org/W6600284362","https://openalex.org/W6602936574","https://openalex.org/W6622239757","https://openalex.org/W6629590909","https://openalex.org/W6633516429","https://openalex.org/W6636382570","https://openalex.org/W6637373629","https://openalex.org/W6638296183","https://openalex.org/W6638667902","https://openalex.org/W6649973027"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3008587939","https://openalex.org/W2949229884","https://openalex.org/W2963400424"],"abstract_inverted_index":{"Image-based":[0],"sequence":[1,34,45],"recognition":[2,126],"has":[3],"been":[4],"a":[5,50],"long-standing":[6],"research":[7],"topic":[8],"in":[9,32,75,95,119,176],"computer":[10],"vision.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15],"investigate":[16],"the":[17,26,63,80,151,160,163,167,171,177,187],"problem":[18],"of":[19,79,162,179,189],"scene":[20,60,124],"text":[21,61,125],"recognition,":[22,62,183],"which":[23,41,137,184],"is":[24,53,72,108,138],"among":[25],"most":[27,78],"important":[28],"and":[29,47,88,115,122,156],"challenging":[30],"tasks":[31],"image-based":[33,180],"recognition.":[35],"A":[36],"novel":[37],"neural":[38],"network":[39],"architecture,":[40],"integrates":[42],"feature":[43],"extraction,":[44],"modeling":[46],"transcription":[48],"into":[49],"unified":[51],"framework,":[52],"proposed.":[54],"Compared":[55],"with":[56],"previous":[57],"systems":[58],"for":[59,141],"proposed":[64,164,172],"architecture":[65],"possesses":[66],"four":[67],"distinctive":[68],"properties:":[69],"(1)":[70],"It":[71,91,107,129],"end-to-end":[73],"trainable,":[74],"contrast":[76],"to":[77,111],"existing":[81],"algorithms":[82],"whose":[83],"components":[84],"are":[85],"separately":[86],"trained":[87],"tuned.":[89],"(2)":[90],"naturally":[92],"handles":[93],"sequences":[94],"arbitrary":[96],"lengths,":[97],"involving":[98],"no":[99],"character":[100],"segmentation":[101],"or":[102],"horizontal":[103],"scale":[104],"normalization.":[105],"(3)":[106],"not":[109],"confined":[110],"any":[112],"predefined":[113],"lexicon":[114],"achieves":[116],"remarkable":[117],"performances":[118],"both":[120],"lexicon-free":[121],"lexicon-based":[123],"tasks.":[127],"(4)":[128],"generates":[130],"an":[131],"effective":[132],"yet":[133],"much":[134],"smaller":[135],"model,":[136],"more":[139],"practical":[140],"real-world":[142],"application":[143],"scenarios.":[144],"The":[145],"experiments":[146],"on":[147],"standard":[148],"benchmarks,":[149],"including":[150],"IIIT-5K,":[152],"Street":[153],"View":[154],"Text":[155],"ICDAR":[157],"datasets,":[158],"demonstrate":[159],"superiority":[161],"algorithm":[165,173],"over":[166],"prior":[168],"arts.":[169],"Moreover,":[170],"performs":[174],"well":[175],"task":[178],"music":[181],"score":[182],"evidently":[185],"verifies":[186],"generality":[188],"it.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":162},{"year":2025,"cited_by_count":344},{"year":2024,"cited_by_count":373},{"year":2023,"cited_by_count":470},{"year":2022,"cited_by_count":432},{"year":2021,"cited_by_count":435},{"year":2020,"cited_by_count":364},{"year":2019,"cited_by_count":330},{"year":2018,"cited_by_count":168},{"year":2017,"cited_by_count":72},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}