{"id":"https://openalex.org/W4393207191","doi":"https://doi.org/10.1109/lsp.2024.3381893","title":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","display_name":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393207191","doi":"https://doi.org/10.1109/lsp.2024.3381893"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3381893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3381893","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Signal Processing Letters","raw_type":"journal-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/A5103038601","display_name":"Xiaomeng Yang","orcid":"https://orcid.org/0000-0003-4109-1562"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaomeng Yang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026666926","display_name":"Zhi Qiao","orcid":"https://orcid.org/0000-0002-8942-5907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Qiao","raw_affiliation_strings":["Tomorrow Advancing Life, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tomorrow Advancing Life, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674793","display_name":"Wei Jin","orcid":"https://orcid.org/0000-0003-2016-0901"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wei","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016775929","display_name":"Dongbao Yang","orcid":"https://orcid.org/0000-0001-8628-411X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbao Yang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103038601"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":2.2436,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88673614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"964","last_page":"968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9498000144958496,"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":0.9409999847412109,"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":0.7096544504165649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5728065371513367},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5393260717391968},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4967935383319855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4572114944458008},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4334670901298523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3638055920600891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096544504165649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728065371513367},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5393260717391968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4967935383319855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4572114944458008},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4334670901298523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3638055920600891},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3381893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3381893","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G349564040","display_name":null,"funder_award_id":"62376266","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":46,"referenced_works":["https://openalex.org/W654550266","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/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2593572697","https://openalex.org/W2810983211","https://openalex.org/W2963233387","https://openalex.org/W2963587345","https://openalex.org/W2965066169","https://openalex.org/W2979371747","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W2998382406","https://openalex.org/W3004846386","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3203487993","https://openalex.org/W3204479434","https://openalex.org/W3206651063","https://openalex.org/W4225562651","https://openalex.org/W4229030834","https://openalex.org/W4312787220","https://openalex.org/W4312843595","https://openalex.org/W4312868947","https://openalex.org/W4312879041","https://openalex.org/W4378508557","https://openalex.org/W4385767840","https://openalex.org/W4385767967","https://openalex.org/W4390871832","https://openalex.org/W4390872070","https://openalex.org/W6727099177","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6776148200","https://openalex.org/W6788135285","https://openalex.org/W6853204417","https://openalex.org/W6856319407"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W4205958290","https://openalex.org/W4384212932","https://openalex.org/W4390590544","https://openalex.org/W2096195258","https://openalex.org/W2990460313","https://openalex.org/W2973458857"],"abstract_inverted_index":{"Scene":[0],"Text":[1],"Recognition":[2],"(STR)":[3],"is":[4],"challenging":[5,160],"because":[6],"of":[7,17,81,89,134,155],"various":[8],"text":[9],"styles,":[10],"shapes,":[11],"and":[12,61,72,91,146],"backgrounds.":[13],"Although":[14],"the":[15,79,86,97,104,113,132,142,158],"integration":[16],"linguistic":[18],"information":[19,95],"enhances":[20],"models'":[21],"performance,":[22],"existing":[23],"methods":[24,150],"based":[25],"on":[26,141,157],"either":[27],"permuted":[28,62],"language":[29,34],"modeling":[30,35],"(PLM)":[31],"or":[32],"masked":[33,60],"(MLM)":[36],"have":[37],"their":[38],"drawbacks.":[39],"PLM's":[40],"autoregressive":[41],"decoding":[42,98],"lacks":[43],"foresight":[44],"into":[45,96],"subsequent":[46],"characters,":[47],"while":[48],"MLM":[49,73],"overlooks":[50],"intercharacter":[51],"dependencies.":[52],"To":[53],"address":[54],"these":[55],"problems,":[56],"we":[57,111],"propose":[58],"a":[59,75,119,152],"implicit":[63],"context":[64],"learning":[65],"network":[66],"for":[67],"STR,":[68],"which":[69],"unifies":[70],"PLM":[71,90],"within":[74],"single":[76],"decoder,":[77],"inheriting":[78],"advantages":[80],"both":[82],"approaches.":[83],"We":[84],"utilize":[85],"training":[87,115],"procedure":[88],"incorporate":[92],"word":[93],"length":[94,125],"process":[99],"to":[100,117],"integrate":[101],"MLM,":[102],"substituting":[103],"undetermined":[105],"characters":[106],"with":[107,151],"mask":[108],"tokens.":[109],"Besides,":[110],"employ":[112],"perturbation":[114],"technique":[116],"train":[118],"more":[120,159],"robust":[121],"model":[122],"against":[123],"potential":[124],"prediction":[126],"errors.":[127],"Our":[128],"comprehensive":[129],"evaluations":[130],"demonstrate":[131],"performance":[133,140],"our":[135],"model.":[136],"It":[137],"achieves":[138],"superior":[139],"popularly":[143],"used":[144],"benchmarks":[145],"outperforms":[147],"previous":[148],"state-of-the-art":[149],"substantial":[153],"improvement":[154],"9.1%":[156],"Union14M-Benchmark.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}