{"id":"https://openalex.org/W2995752927","doi":"https://doi.org/10.1145/3368926.3369689","title":"Improving CRNN with EfficientNet-like feature extractor and multi-head attention for text recognition","display_name":"Improving CRNN with EfficientNet-like feature extractor and multi-head attention for text recognition","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2995752927","doi":"https://doi.org/10.1145/3368926.3369689","mag":"2995752927"},"language":"en","primary_location":{"id":"doi:10.1145/3368926.3369689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","raw_type":"proceedings-article"},"type":"article","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/A5025948040","display_name":"Dinh Viet Sang","orcid":"https://orcid.org/0000-0002-9254-1327"},"institutions":[{"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":true,"raw_author_name":"Dinh Viet Sang","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041088575","display_name":"Le Tran Bao Cuong","orcid":null},"institutions":[{"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":"Le Tran Bao Cuong","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025948040"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.9191,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79882612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"285","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9811000227928162,"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":0.9731000065803528,"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/extractor","display_name":"Extractor","score":0.8626116514205933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8202018737792969},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6823065280914307},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6606138348579407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6124599575996399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5951632857322693},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5911844372749329},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.46543896198272705},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.46194204688072205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36687588691711426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2732456922531128}],"concepts":[{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.8626116514205933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202018737792969},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6823065280914307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6606138348579407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6124599575996399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5951632857322693},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5911844372749329},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.46543896198272705},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.46194204688072205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36687588691711426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2732456922531128},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368926.3369689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1812645736","https://openalex.org/W2097117768","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2606150549","https://openalex.org/W2626778328","https://openalex.org/W2741147179","https://openalex.org/W2946948417","https://openalex.org/W2949608135","https://openalex.org/W2953384591","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2964081807"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W3141979996","https://openalex.org/W3113054633"],"abstract_inverted_index":{"Text":[0],"recognition":[1],"is":[2,92],"one":[3],"of":[4],"the":[5,40,98],"most":[6],"important":[7],"and":[8,47,73,108],"challenging":[9],"tasks":[10],"in":[11,20,83],"image-based":[12],"sequence":[13],"recognition,":[14],"which":[15],"has":[16],"various":[17],"potential":[18],"applications":[19],"real":[21],"life.":[22],"In":[23,75],"this":[24],"paper,":[25],"we":[26,38],"propose":[27,48],"a":[28],"novel":[29],"convolutional-recurrent":[30],"neural":[31],"network":[32],"(CRNN)":[33],"for":[34,43],"text":[35],"recognition.":[36],"Particularly,":[37],"adapt":[39],"EfficientNet":[41],"architecture":[42],"extracting":[44],"deep":[45],"features":[46],"multi-head":[49],"attention":[50],"mechanisms":[51],"to":[52,94],"improve":[53],"character":[54],"localization.":[55],"The":[56],"experiments":[57],"show":[58],"that":[59],"our":[60,77,90],"EfficientNet-like":[61],"feature":[62,69],"extractor":[63],"clearly":[64],"outperforms":[65],"other":[66,86],"previous":[67],"CNN":[68],"extractors":[70],"like":[71],"VGG":[72],"ResNet.":[74],"overall,":[76],"proposed":[78],"method":[79],"yields":[80],"competitive":[81],"performance":[82],"comparison":[84],"with":[85],"state-of-the-art":[87],"approaches.":[88],"Specifically,":[89],"F1-score":[91],"equivalent":[93],"top":[95],"3":[96],"on":[97,104],"ICDAR":[99],"2019":[100],"Robust":[101],"Reading":[102],"Challenge":[103],"Scanned":[105],"Receipts":[106],"OCR":[107],"Information":[109],"Extraction.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}