{"id":"https://openalex.org/W4385767840","doi":"https://doi.org/10.24963/ijcai.2023/189","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","display_name":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767840","doi":"https://doi.org/10.24963/ijcai.2023/189"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/189","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/189","pdf_url":"https://www.ijcai.org/proceedings/2023/0189.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0189.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040360450","display_name":"Boqiang Zhang","orcid":"https://orcid.org/0000-0002-5314-4054"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqiang Zhang","raw_affiliation_strings":["University of Science and Technology of China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101832741","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0003-2311-9082"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427468","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-0228-6220"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["University of Science and Technology of China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101531218","display_name":"Jianjun Xu","orcid":"https://orcid.org/0000-0001-6398-3364"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjun Xu","raw_affiliation_strings":["University of Science and Technology of China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101832741"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.7564,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94865545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1704","last_page":"1712"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9939000010490417,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7508682608604431},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6102704405784607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5620400905609131},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.538458526134491},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5181254744529724},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4520367383956909},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4483337998390198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4472818076610565},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41630643606185913},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32879310846328735},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21539118885993958},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08618688583374023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508682608604431},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6102704405784607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5620400905609131},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.538458526134491},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5181254744529724},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4520367383956909},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4483337998390198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4472818076610565},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41630643606185913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32879310846328735},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21539118885993958},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08618688583374023},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/189","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/189","pdf_url":"https://www.ijcai.org/proceedings/2023/0189.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/189","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/189","pdf_url":"https://www.ijcai.org/proceedings/2023/0189.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3316061764","display_name":null,"funder_award_id":"62022076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4897510482","display_name":null,"funder_award_id":"62232006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6179918720","display_name":null,"funder_award_id":"U1936210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6695563415","display_name":null,"funder_award_id":"2022YFB3104700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767840.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1522301498","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2750938222","https://openalex.org/W2810983211","https://openalex.org/W2896457183","https://openalex.org/W2952285877","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3096609285","https://openalex.org/W3110267192","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W4292825881","https://openalex.org/W4304091443","https://openalex.org/W4308291331","https://openalex.org/W4312843595","https://openalex.org/W4386410320"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W3147584709","https://openalex.org/W2795079307","https://openalex.org/W2977677679","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2055929693"],"abstract_inverted_index":{"Vision":[0,87],"model":[1,88,97],"have":[2],"gained":[3],"increasing":[4],"attention":[5,43,120],"due":[6,19],"to":[7,20,138],"their":[8],"simplicity":[9],"and":[10,27,50,118,125],"efficiency":[11],"in":[12,42,59,71,150],"Scene":[13],"Text":[14],"Recognition":[15],"(STR)":[16],"task.":[17],"However,":[18],"lacking":[21],"the":[22,37,63,69,92,104,140,147,151,164],"perception":[23],"of":[24,95,142],"linguistic":[25,54,93,126,148],"knowledge":[26],"information,":[28],"recent":[29],"vision":[30,96],"models":[31],"suffer":[32],"from":[33,168],"two":[34],"problems:":[35],"(1)":[36],"pure":[38],"vision-based":[39],"query":[40],"results":[41,175],"drift,":[44],"which":[45,90,154],"usually":[46],"causes":[47],"poor":[48],"recognition":[49,70],"is":[51,66,136,187],"summarized":[52],"as":[53],"insensitive":[55],"drift":[56],"(LID)":[57],"problem":[58],"this":[60],"paper.":[61],"(2)":[62],"visual":[64,143,152,157],"feature":[65],"suboptimal":[67],"for":[68,98],"some":[72],"vision-missing":[73],"cases":[74],"(e.g.":[75],"occlusion,":[76],"etc.).":[77],"To":[78,102],"address":[79],"these":[80],"issues,":[81],"we":[82,107],"propose":[83],"a":[84,109,130],"Linguistic":[85,132],"Perception":[86],"(LPV),":[89],"explores":[91],"capability":[94],"accurate":[99,119],"text":[100],"recognition.":[101],"alleviate":[103],"LID":[105],"problem,":[106],"introduce":[108],"Cascade":[110],"Position":[111],"Attention":[112],"(CPA)":[113],"mechanism":[114],"that":[115],"obtains":[116,173],"high-quality":[117],"maps":[121],"through":[122],"step-wise":[123],"optimization":[124],"information":[127,149],"mining.":[128],"Furthermore,":[129],"Global":[131],"Reconstruction":[133],"Module":[134],"(GLRM)":[135],"proposed":[137],"improve":[139],"representation":[141],"features":[144,158],"by":[145],"perceiving":[146],"space,":[153],"gradually":[155],"converts":[156],"into":[159],"semantically":[160],"rich":[161],"ones":[162],"during":[163],"cascade":[165],"process.":[166],"Different":[167],"previous":[169],"methods,":[170],"our":[171],"method":[172],"SOTA":[174],"while":[176],"keeping":[177],"low":[178],"complexity":[179],"(92.4%":[180],"accuracy":[181],"with":[182],"only":[183],"8.11M":[184],"parameters).":[185],"Code":[186],"available":[188],"at":[189],"https://github.com/CyrilSterling/LPV.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
