{"id":"https://openalex.org/W3015688946","doi":"https://doi.org/10.1109/icassp40776.2020.9054269","title":"Scene Text Recognition with Temporal Convolutional Encoder","display_name":"Scene Text Recognition with Temporal Convolutional Encoder","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015688946","doi":"https://doi.org/10.1109/icassp40776.2020.9054269","mag":"3015688946"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047942518","display_name":"Xiangcheng Du","orcid":"https://orcid.org/0000-0002-4268-6114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangcheng Du","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103028836","display_name":"Tianlong Ma","orcid":"https://orcid.org/0000-0003-4079-7897"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlong Ma","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056833841","display_name":"Yingbin Zheng","orcid":"https://orcid.org/0000-0002-5590-9292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingbin Zheng","raw_affiliation_strings":["Videt Tech Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Videt Tech Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427158","display_name":"Hao Ye","orcid":"https://orcid.org/0000-0002-5939-4708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Ye","raw_affiliation_strings":["Videt Tech Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Videt Tech Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043728985","display_name":"Xingjiao Wu","orcid":"https://orcid.org/0000-0001-9146-051X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjiao Wu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100745388","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-6394-8531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2383","last_page":"2387"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9902999997138977,"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/encoder","display_name":"Encoder","score":0.8713762760162354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.824469804763794},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6868898272514343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.676173985004425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5796442031860352},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4949609637260437},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.445487380027771},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.42628616094589233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4178357720375061},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3317405879497528},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.255587100982666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15740156173706055}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8713762760162354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824469804763794},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6868898272514343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.676173985004425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5796442031860352},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4949609637260437},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.445487380027771},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.42628616094589233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4178357720375061},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3317405879497528},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.255587100982666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15740156173706055},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2127141656","https://openalex.org/W2135231474","https://openalex.org/W2140132917","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2510642588","https://openalex.org/W2750938222","https://openalex.org/W2752225195","https://openalex.org/W2752782242","https://openalex.org/W2792764867","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2884585870","https://openalex.org/W2899996070","https://openalex.org/W2911295582","https://openalex.org/W2962790387","https://openalex.org/W2963327605","https://openalex.org/W2963420686","https://openalex.org/W2963526661","https://openalex.org/W2963712589","https://openalex.org/W2965066169","https://openalex.org/W2970971581","https://openalex.org/W3004846386","https://openalex.org/W3018001946","https://openalex.org/W3082397598","https://openalex.org/W3106271744","https://openalex.org/W4295312788","https://openalex.org/W6618372016","https://openalex.org/W6649973027","https://openalex.org/W6681452975","https://openalex.org/W6725336789","https://openalex.org/W6744310024","https://openalex.org/W6752486419","https://openalex.org/W6753412334","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W2610189143","https://openalex.org/W2159424856","https://openalex.org/W4390516098","https://openalex.org/W2132373020","https://openalex.org/W2096049278","https://openalex.org/W39762558","https://openalex.org/W2883195674","https://openalex.org/W2072736607","https://openalex.org/W3080374445","https://openalex.org/W2964790801"],"abstract_inverted_index":{"Texts":[0],"from":[1],"scene":[2],"images":[3],"typically":[4],"consist":[5],"of":[6,77,85,109],"several":[7],"characters":[8],"and":[9,32,103],"exhibit":[10],"a":[11,34],"characteristic":[12],"sequence":[13],"structure.":[14],"Existing":[15],"methods":[16],"capture":[17],"the":[18,21,29,38,41,54,59,65,75,83,104,107],"structure":[19],"with":[20,70],"sequence-to-sequence":[22],"models":[23],"by":[24,52],"an":[25],"encoder":[26,60],"to":[27,36],"have":[28],"visual":[30],"representations":[31],"then":[33],"decoder":[35],"translate":[37],"features":[39],"into":[40],"label":[42],"sequence.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"study":[48,82],"text":[49,78,95],"recognition":[50],"framework":[51],"considering":[53],"long-term":[55],"temporal":[56],"dependencies":[57],"in":[58,89],"stage.":[61],"We":[62,80,97],"demonstrate":[63,106],"that":[64],"proposed":[66,111],"Temporal":[67],"Convolutional":[68],"Encoder":[69],"increased":[71],"sequential":[72],"extents":[73],"improves":[74],"accuracy":[76],"recognition.":[79],"also":[81],"impact":[84],"different":[86],"attention":[87],"modules":[88],"convolutional":[90],"blocks":[91],"for":[92],"learning":[93],"accurate":[94],"representations.":[96],"conduct":[98],"comparisons":[99],"on":[100],"seven":[101],"datasets":[102],"experiments":[105],"effectiveness":[108],"our":[110],"approach.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}