{"id":"https://openalex.org/W4392111282","doi":"https://doi.org/10.3233/jifs-237135","title":"Scene text recognition with context-aware autonomous bidirectional iterative models","display_name":"Scene text recognition with context-aware autonomous bidirectional iterative models","publication_year":2024,"publication_date":"2024-02-23","ids":{"openalex":"https://openalex.org/W4392111282","doi":"https://doi.org/10.3233/jifs-237135"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-237135","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-237135","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","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/A5100888911","display_name":"Xiaoqing Zhao","orcid":"https://orcid.org/0009-0009-1574-3484"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Zhao","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074155360","display_name":"Miaomiao Xu","orcid":"https://orcid.org/0000-0001-8544-6754"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaomiao Xu","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673041","display_name":"Yanbing Li","orcid":"https://orcid.org/0000-0001-5368-6921"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanbing Li","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063120015","display_name":"Wushour Silamu","orcid":"https://orcid.org/0000-0003-4592-7806"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wushour Silamu","raw_affiliation_strings":["College of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100673041"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":{"value":4150,"currency":"USD","value_usd":4150},"apc_paid":null,"fwci":0.3092,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48965406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"46","issue":"4","first_page":"8605","last_page":"8616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9905999898910522,"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":0.9854999780654907,"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":0.8353204131126404},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5843223333358765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5386260747909546},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4165736734867096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3219742178916931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353204131126404},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5843223333358765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386260747909546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4165736734867096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3219742178916931},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-237135","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-237135","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W654550266","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W2194187530","https://openalex.org/W2532759528","https://openalex.org/W2749581528","https://openalex.org/W2751169665","https://openalex.org/W2810983211","https://openalex.org/W2963233387","https://openalex.org/W2963587345","https://openalex.org/W2964065044","https://openalex.org/W2997864923","https://openalex.org/W3082397598","https://openalex.org/W4292825881"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747","https://openalex.org/W2170022336"],"abstract_inverted_index":{"This":[0,103],"research":[1],"focuses":[2],"on":[3],"Scene":[4],"Text":[5],"Recognition":[6],"(STR),":[7],"a":[8,62,71,74,78,148,192],"crucial":[9],"component":[10],"in":[11,91,114],"various":[12,182],"applications":[13],"of":[14,38,51,143,166,198,213],"artificial":[15],"intelligence":[16],"such":[17],"as":[18],"image":[19],"retrieval,":[20],"office":[21],"automation,":[22],"and":[23,53,77,107,139,162,200],"intelligent":[24],"traffic":[25],"systems.":[26],"Recent":[27],"studies":[28],"have":[29],"shown":[30,57],"that":[31,66,174],"semantic-aware":[32],"approaches":[33],"significantly":[34],"improve":[35],"the":[36,49,84,88,92,119,122,135,141,144,158,164],"performance":[37],"STR":[39,43,194],"tasks,":[40],"with":[41,98,187,203],"context-aware":[42],"methods":[44],"becoming":[45],"mainstream.":[46],"Among":[47],"these,":[48],"fusion":[50],"visual":[52],"language":[54],"models":[55,168],"has":[56],"remarkable":[58],"effectiveness.":[59],"We":[60],"propose":[61],"novel":[63],"method":[64],"(PABINet)":[65],"incorporates":[67],"three":[68],"key":[69],"components:":[70],"Visual-Language":[72,85,123,145],"Decoder,":[73],"Language":[75,136],"Model,":[76],"Fusion":[79,159],"Model.":[80],"First,":[81],"during":[82],"training,":[83],"Decoder":[86,124],"masks":[87],"original":[89],"labels":[90],"Transformer":[93],"decoder":[94],"using":[95,147],"permutation":[96],"masks,":[97],"each":[99],"mask":[100,150],"being":[101],"unique.":[102],"enhances":[104],"word":[105],"memorization":[106],"learning":[108],"through":[109,169],"contextual":[110],"semantic":[111,116],"information,":[112],"resulting":[113],"robust":[115],"knowledge.":[117],"During":[118],"inference":[120,130],"stage,":[121],"employs":[125],"autonomous":[126],"Autoregressive":[127],"model":[128],"(AR)":[129],"to":[131],"generate":[132],"results.":[133],"Subsequently,":[134],"Model":[137,160],"scrutinizes":[138],"corrects":[140],"output":[142],"Encoder":[146],"cloze":[149],"approach,":[151],"achieving":[152],"context-aware,":[153],"autonomous,":[154],"bidirectional":[155],"inference.":[156],"Finally,":[157],"concatenates":[161],"refines":[163],"outputs":[165],"both":[167],"iterative":[170],"layers.Experimental":[171],"results":[172,210],"demonstrate":[173],"our":[175],"PABINet":[176,190],"performs":[177],"exceptionally":[178],"well":[179],"when":[180,201],"handling":[181],"quality":[183],"images.":[184],"When":[185],"trained":[186,202],"synthetic":[188],"data,":[189,205],"achieves":[191],"new":[193,208],"benchmark":[195],"(average":[196,211],"accuracy":[197,212],"92.41%),":[199],"real":[204],"it":[206],"establishes":[207],"state-of-the-art":[209],"96.28%).":[214]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}