{"id":"https://openalex.org/W4229030834","doi":"https://doi.org/10.24963/ijcai.2022/124","title":"SVTR: Scene Text Recognition with a Single Visual Model","display_name":"SVTR: Scene Text Recognition with a Single Visual Model","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4229030834","doi":"https://doi.org/10.24963/ijcai.2022/124"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/124","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/124","pdf_url":"https://www.ijcai.org/proceedings/2022/0124.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0124.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102915298","display_name":"Yongkun Du","orcid":"https://orcid.org/0009-0005-3114-2188"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkun Du","raw_affiliation_strings":["Baidu Inc., China","School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080463909","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085282915","display_name":"Caiyan Jia","orcid":"https://orcid.org/0000-0003-0650-9564"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caiyan Jia","raw_affiliation_strings":["School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034820064","display_name":"Xiaoting Yin","orcid":"https://orcid.org/0000-0001-7708-7819"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoting Yin","raw_affiliation_strings":["Baidu Inc., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085762738","display_name":"Tianlun Zheng","orcid":"https://orcid.org/0000-0003-3671-1480"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlun Zheng","raw_affiliation_strings":["Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103082468","display_name":"Chenxia Li","orcid":"https://orcid.org/0000-0003-0321-5675"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxia Li","raw_affiliation_strings":["Baidu Inc., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010944460","display_name":"Yuning Du","orcid":"https://orcid.org/0009-0007-4995-5472"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuning Du","raw_affiliation_strings":["Baidu Inc., China","School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.6795,"has_fulltext":false,"cited_by_count":216,"citation_normalized_percentile":{"value":0.98807665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"884","last_page":"890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9916999936103821,"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":0.9556000232696533,"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":0.8511337041854858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6381872296333313},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5891453623771667},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5675698518753052},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5160353183746338},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.49705770611763},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49598297476768494},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45872968435287476},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44434037804603577},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4215039312839508},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.393414169549942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3627890944480896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20535361766815186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8511337041854858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381872296333313},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5891453623771667},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5675698518753052},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5160353183746338},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49705770611763},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49598297476768494},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45872968435287476},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44434037804603577},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4215039312839508},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.393414169549942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3627890944480896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20535361766815186},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/124","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/124","pdf_url":"https://www.ijcai.org/proceedings/2022/0124.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/124","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/124","pdf_url":"https://www.ijcai.org/proceedings/2022/0124.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4229030834.pdf","grobid_xml":"https://content.openalex.org/works/W4229030834.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1491389626","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/W2537773590","https://openalex.org/W2810983211","https://openalex.org/W2911179793","https://openalex.org/W2965066169","https://openalex.org/W2997864923","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3035449864","https://openalex.org/W3042760913","https://openalex.org/W3094502228","https://openalex.org/W3101411491","https://openalex.org/W3138516171","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W3215384850","https://openalex.org/W4226374800","https://openalex.org/W4287183355","https://openalex.org/W4386410320"],"related_works":["https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W1503216044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2353650902","https://openalex.org/W3125011624","https://openalex.org/W1508631387"],"abstract_inverted_index":{"Dominant":[0],"scene":[1,124],"text":[2,21,67,125],"recognition":[3,45,126],"models":[4],"commonly":[5],"contain":[6],"two":[7],"building":[8],"blocks,":[9],"a":[10,17,38,103,113,146],"visual":[11],"model":[12,19,41],"for":[13,20,42],"feature":[14],"extraction":[15],"and":[16,30,88,98,122,141,161],"sequence":[18],"transcription.":[22],"This":[23],"hybrid":[24],"architecture,":[25],"although":[26],"accurate,":[27],"is":[28,158,173],"complex":[29],"less":[31],"efficient.":[32],"In":[33,154],"this":[34],"study,":[35],"we":[36],"propose":[37],"Single":[39],"Visual":[40],"Scene":[43],"Text":[44],"within":[46],"the":[47,55,96,129],"patch-wise":[48],"image":[49,66],"tokenization":[50],"framework,":[51],"which":[52,165],"dispenses":[53],"with":[54],"sequential":[56],"modeling":[57],"entirely.":[58],"The":[59,171],"method,":[60],"termed":[61],"SVTR,":[62],"firstly":[63],"decomposes":[64],"an":[65,159],"into":[68],"small":[69],"patches":[70],"named":[71],"character":[72,105],"components.":[73],"Afterward,":[74],"hierarchical":[75],"stages":[76],"are":[77,92,110],"recurrently":[78],"carried":[79],"out":[80],"by":[81,112,145],"component-level":[82],"mixing,":[83],"merging":[84],"and/or":[85],"combining.":[86],"Global":[87],"local":[89],"mixing":[90],"blocks":[91],"devised":[93],"to":[94,102],"perceive":[95],"inter-character":[97],"intra-character":[99],"patterns,":[100],"leading":[101],"multi-grained":[104],"component":[106],"perception.":[107],"Thus,":[108],"characters":[109],"recognized":[111],"simple":[114],"linear":[115],"prediction.":[116],"Experimental":[117],"results":[118],"on":[119],"both":[120],"English":[121,140],"Chinese":[123],"tasks":[127],"demonstrate":[128],"effectiveness":[130],"of":[131],"SVTR.":[132],"SVTR-L":[133],"(Large)":[134],"achieves":[135],"highly":[136],"competitive":[137],"accuracy":[138],"in":[139,149],"outperforms":[142],"existing":[143],"methods":[144],"large":[147],"margin":[148],"Chinese,":[150],"while":[151],"running":[152],"faster.":[153],"addition,":[155],"SVTR-T":[156],"(Tiny)":[157],"effective":[160],"much":[162],"smaller":[163],"model,":[164],"shows":[166],"appealing":[167],"speed":[168],"at":[169,176],"inference.":[170],"code":[172],"publicly":[174],"available":[175],"https://github.com/PaddlePaddle/PaddleOCR.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":80},{"year":2024,"cited_by_count":69},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":8}],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2022-05-08T00:00:00"}