{"id":"https://openalex.org/W3163848781","doi":"https://doi.org/10.1109/icpr48806.2021.9412037","title":"Weakly Supervised Attention Rectification for Scene Text Recognition","display_name":"Weakly Supervised Attention Rectification for Scene Text Recognition","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3163848781","doi":"https://doi.org/10.1109/icpr48806.2021.9412037","mag":"3163848781"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412037","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":"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/A5019447181","display_name":"Chengyu Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Gu","raw_affiliation_strings":["School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717685","display_name":"Shilin Wang","orcid":"https://orcid.org/0000-0002-8214-6809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Wang","raw_affiliation_strings":["School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529317","display_name":"Yiwei Zhu","orcid":"https://orcid.org/0000-0001-9524-4726"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Zhu","raw_affiliation_strings":["School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103055957","display_name":"Zheng Huang","orcid":"https://orcid.org/0009-0003-2994-8030"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Huang","raw_affiliation_strings":["School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437924","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6384-0355"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electric Information and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1212 5701","issue":null,"first_page":"779","last_page":"786"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9926000237464905,"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":0.9904999732971191,"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":0.8448238968849182},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.699837327003479},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.6445468068122864},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6119874715805054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5776759386062622},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5294387340545654},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.5200350284576416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4847095012664795},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4482387602329254},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43668442964553833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4259519577026367},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4146368205547333},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22093543410301208},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.0881388783454895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448238968849182},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.699837327003479},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.6445468068122864},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6119874715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5776759386062622},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5294387340545654},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.5200350284576416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4847095012664795},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4482387602329254},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43668442964553833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4259519577026367},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4146368205547333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22093543410301208},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0881388783454895},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412037","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":[{"display_name":"Responsible consumption and production","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W70975097","https://openalex.org/W603908379","https://openalex.org/W1491389626","https://openalex.org/W1607307044","https://openalex.org/W1895191496","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1978729128","https://openalex.org/W1981283549","https://openalex.org/W1988461287","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2043075591","https://openalex.org/W2061802763","https://openalex.org/W2099247484","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2298368322","https://openalex.org/W2343052201","https://openalex.org/W2526425061","https://openalex.org/W2626778328","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2788069964","https://openalex.org/W2795619303","https://openalex.org/W2798484463","https://openalex.org/W2809273748","https://openalex.org/W2810983211","https://openalex.org/W2899771611","https://openalex.org/W2927058921","https://openalex.org/W2952302849","https://openalex.org/W2952439627","https://openalex.org/W2963327605","https://openalex.org/W2963517393","https://openalex.org/W2964308564","https://openalex.org/W2965066169","https://openalex.org/W2966666886","https://openalex.org/W2971325593","https://openalex.org/W2979371747","https://openalex.org/W3004846386","https://openalex.org/W3005436539","https://openalex.org/W3106271744","https://openalex.org/W4385245566","https://openalex.org/W6600284362","https://openalex.org/W6602936574","https://openalex.org/W6618372016","https://openalex.org/W6629590909","https://openalex.org/W6636382570","https://openalex.org/W6649973027","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6681875759","https://openalex.org/W6739901393","https://openalex.org/W6748446516"],"related_works":["https://openalex.org/W2546942002","https://openalex.org/W2902204561","https://openalex.org/W4211111701","https://openalex.org/W2023510504","https://openalex.org/W2139727660","https://openalex.org/W2369112766","https://openalex.org/W2762942250","https://openalex.org/W42449913","https://openalex.org/W2144168281","https://openalex.org/W2977227451"],"abstract_inverted_index":{"Scene":[0],"text":[1,32,48,143],"recognition":[2,41,49,144],"has":[3,20],"become":[4,21],"a":[5],"hot":[6],"topic":[7],"in":[8,29,138],"recent":[9],"years":[10],"due":[11],"to":[12,73,79],"its":[13],"booming":[14],"real-life":[15],"applications.":[16],"Attention-based":[17],"encoder-decoder":[18,65],"framework":[19],"one":[22],"of":[23],"the":[24,30,35,40,63,75,81,85,113,131,135],"most":[25,44],"popular":[26],"frameworks":[27],"especially":[28],"irregular":[31,142],"scenario.":[33],"However,":[34],"\u201cattention":[36],"drift\u201d":[37],"problem":[38],"hinders":[39],"performance":[42,114],"for":[43,115],"existing":[45,91],"attention-based":[46,64],"scene":[47],"methods.":[50],"To":[51],"solve":[52],"this":[53],"problem,":[54],"we":[55],"propose":[56],"an":[57],"auxiliary":[58],"supervision":[59],"branch":[60],"along":[61],"with":[62,90],"framework.":[66],"A":[67],"new":[68],"loss":[69],"function":[70],"is":[71],"designed":[72],"refine":[74],"feature":[76],"map":[77],"and":[78,118,141],"help":[80],"attention":[82,92],"region":[83],"align":[84],"target":[86],"character":[87],"area.":[88],"Compared":[89],"rectification":[93],"mechanisms,":[94],"our":[95,109],"method":[96,110],"does":[97],"not":[98],"require":[99],"character-level":[100],"annotations":[101],"or":[102],"introduce":[103],"any":[104],"additional":[105],"trainable":[106],"parameter.":[107],"Furthermore,":[108],"can":[111],"improve":[112],"both":[116,139],"RNN-Attention":[117],"Scaled":[119],"Dot-Product":[120],"Attention.":[121],"The":[122],"experiment":[123],"results":[124],"on":[125],"various":[126],"benchmarks":[127],"have":[128],"demonstrated":[129],"that":[130],"proposed":[132],"approach":[133],"outperforms":[134],"state-of-the-art":[136],"methods":[137],"regular":[140],"scenarios.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}