{"id":"https://openalex.org/W3160318025","doi":"https://doi.org/10.1109/icpr48806.2021.9412536","title":"Sample-aware Data Augmentor for Scene Text Recognition","display_name":"Sample-aware Data Augmentor for Scene Text Recognition","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3160318025","doi":"https://doi.org/10.1109/icpr48806.2021.9412536","mag":"3160318025"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5102398518","display_name":"Guanghao Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanghao Meng","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023762528","display_name":"Tao Dai","orcid":"https://orcid.org/0000-0003-0594-6404"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Dai","raw_affiliation_strings":["PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026555998","display_name":"Shudeng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shudeng Wu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427338","display_name":"Bin Chen","orcid":"https://orcid.org/0000-0002-4798-230X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Chen","raw_affiliation_strings":["PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066196985","display_name":"Jian L\u00fc","orcid":"https://orcid.org/0000-0003-4599-7281"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Lu","raw_affiliation_strings":["Shenzhen Key Laboratory of Advanced Machine Learning and Applications, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Advanced Machine Learning and Applications, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101656023","display_name":"Yong Jiang","orcid":"https://orcid.org/0000-0003-4482-1559"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Jiang","raw_affiliation_strings":["PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034104790","display_name":"Shu\u2010Tao Xia","orcid":"https://orcid.org/0000-0002-8639-982X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu-Tao Xia","raw_affiliation_strings":["PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"PCL Research Center of Networks and Communications, Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102398518"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59364379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3978","last_page":"3985"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9948999881744385,"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":0.994700014591217,"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":0.8408124446868896},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.787979245185852},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.7740485668182373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.648571789264679},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.628115177154541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4755803644657135},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4641609787940979},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4303743541240692},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.4148145914077759},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23305779695510864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8408124446868896},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.787979245185852},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7740485668182373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.648571789264679},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.628115177154541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4755803644657135},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4641609787940979},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4303743541240692},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.4148145914077759},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23305779695510864},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1729927818","display_name":null,"funder_award_id":"61771273","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4948596372","display_name":null,"funder_award_id":"2019M660645","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W603908379","https://openalex.org/W654550266","https://openalex.org/W1491389626","https://openalex.org/W1971822075","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2015475217","https://openalex.org/W2049951199","https://openalex.org/W2099247484","https://openalex.org/W2128409098","https://openalex.org/W2144554289","https://openalex.org/W2145221928","https://openalex.org/W2146835493","https://openalex.org/W2156163116","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2547875792","https://openalex.org/W2588788622","https://openalex.org/W2593572697","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2775795276","https://openalex.org/W2788069964","https://openalex.org/W2795619303","https://openalex.org/W2798484463","https://openalex.org/W2804047946","https://openalex.org/W2810983211","https://openalex.org/W2884751099","https://openalex.org/W2891939579","https://openalex.org/W2894730515","https://openalex.org/W2952179044","https://openalex.org/W2954930822","https://openalex.org/W2963233387","https://openalex.org/W2963299454","https://openalex.org/W2963327605","https://openalex.org/W2963468256","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2965066169","https://openalex.org/W2987903634","https://openalex.org/W3007630669","https://openalex.org/W3008987259","https://openalex.org/W3011015840","https://openalex.org/W3035363555","https://openalex.org/W3035682737","https://openalex.org/W3149347034","https://openalex.org/W4295727797","https://openalex.org/W6687615561","https://openalex.org/W6690311100","https://openalex.org/W6734085379","https://openalex.org/W6748446516"],"related_works":["https://openalex.org/W2765965840","https://openalex.org/W2012941781","https://openalex.org/W2374519217","https://openalex.org/W2159704347","https://openalex.org/W2393271921","https://openalex.org/W2089133691","https://openalex.org/W2156949561","https://openalex.org/W2586460527","https://openalex.org/W2041526955","https://openalex.org/W2048936104"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"been":[5],"widely":[6],"used":[7],"in":[8,37],"scene":[9,18,51,189,205],"text":[10,19,52,79,190,206],"recognition,":[11],"and":[12,32,62,72,81,115,162,182],"achieved":[13],"remarkable":[14],"performance.":[15],"Such":[16],"DNN-based":[17],"recognizers":[20],"usually":[21,35],"require":[22],"plenty":[23],"of":[24,70,78,100,107,131,142,159,203],"training":[25,160,168],"data":[26,30,43,56,90,104,121,149,197],"for":[27],"training,":[28],"but":[29],"collection":[31],"annotation":[33],"is":[34,45],"cost-expensive":[36],"practice.":[38],"To":[39],"alleviate":[40],"this":[41,84],"issue,":[42],"augmentation":[44,57],"often":[46],"applied":[47],"to":[48,75,92,138,178],"train":[49],"the":[50,68,76,98,129,140,145,157,163,167,180,183,201],"recognizers.":[53],"However,":[54],"existing":[55],"methods":[58,65],"including":[59],"affine":[60,112,123],"transformation":[61,64,113,117,124,135,152],"elastic":[63,116,134],"suffer":[66],"from":[67],"problems":[69],"under-":[71],"over-diversity,":[73],"due":[74],"complexity":[77],"contents":[80,99],"shapes.":[82],"In":[83,119],"paper,":[85],"we":[86],"propose":[87],"a":[88],"sample-aware":[89,196],"augmentor":[91,105,150,181,198],"transform":[93],"samples":[94,161],"adaptively":[95,154],"based":[96,155],"on":[97,127,156,188],"samples.":[101,143],"Specifically,":[102],"our":[103,120,148,171,195],"consists":[106],"three":[108],"parts:":[109],"gated":[110,146],"module,":[111,114,147],"module.":[118],"augmentor,":[122],"module":[125,136],"focuses":[126],"keeping":[128],"affinity":[130],"samples,":[132],"while":[133],"aims":[137],"improve":[139],"diversity":[141],"With":[144],"determines":[151],"type":[153],"properties":[158],"recognizer":[164,184],"capability":[165],"during":[166],"process.":[169],"Besides,":[170],"framework":[172],"introduces":[173],"an":[174],"adversarial":[175],"learning":[176],"strategy":[177],"optimize":[179],"jointly.":[185],"Extensive":[186],"experiments":[187],"recognition":[191],"benchmarks":[192],"show":[193],"that":[194],"significantly":[199],"improves":[200],"performance":[202],"state-of-the-art":[204],"recognizer.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}