{"id":"https://openalex.org/W4404914524","doi":"https://doi.org/10.1109/access.2024.3509678","title":"PuzText: Self-Supervised Learning of Permuted Texture Representation for Multilingual Text Recognition","display_name":"PuzText: Self-Supervised Learning of Permuted Texture Representation for Multilingual Text Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404914524","doi":"https://doi.org/10.1109/access.2024.3509678"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3509678","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3509678","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3509678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047437281","display_name":"Minjun Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minjun Lu","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521046","display_name":"Shugong Xu","orcid":"https://orcid.org/0000-0003-1905-6269"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shugong Xu","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1905-6269","affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102964955","display_name":"Xuefan Zhang","orcid":"https://orcid.org/0000-0002-2893-9963"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefan Zhang","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047437281"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2317,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54577057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"182883","last_page":"182893"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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":0.9968000054359436,"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":0.7789232134819031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6486623883247375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5624877214431763},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.55821692943573},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.4918820858001709},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.491389662027359},{"id":"https://openalex.org/keywords/intermediate-language","display_name":"Intermediate language","score":0.4335331320762634},{"id":"https://openalex.org/keywords/self-representation","display_name":"Self representation","score":0.4286551773548126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.383034884929657},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32416123151779175},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1675530970096588},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06803146004676819}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789232134819031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6486623883247375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5624877214431763},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.55821692943573},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.4918820858001709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.491389662027359},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.4335331320762634},{"id":"https://openalex.org/C2988612419","wikidata":"https://www.wikidata.org/wiki/Q7448312","display_name":"Self representation","level":2,"score":0.4286551773548126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.383034884929657},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32416123151779175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1675530970096588},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06803146004676819},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3509678","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3509678","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cd16815665cd4274be199a71050d60b8","is_oa":true,"landing_page_url":"https://doaj.org/article/cd16815665cd4274be199a71050d60b8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 182883-182893 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3509678","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3509678","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G2792895487","display_name":null,"funder_award_id":"2022YFB2902002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8043748112","display_name":null,"funder_award_id":"TC220H07D","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["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/W2810983211","https://openalex.org/W2875814315","https://openalex.org/W2963114696","https://openalex.org/W2963526661","https://openalex.org/W2965066169","https://openalex.org/W2978036638","https://openalex.org/W3003642782","https://openalex.org/W3003868038","https://openalex.org/W3034414401","https://openalex.org/W3087822568","https://openalex.org/W3110267192","https://openalex.org/W3138516171","https://openalex.org/W3152774549","https://openalex.org/W3175855397","https://openalex.org/W3176276424","https://openalex.org/W3177505580","https://openalex.org/W3179897446","https://openalex.org/W3181186176","https://openalex.org/W3196976036","https://openalex.org/W3198910523","https://openalex.org/W4226374800","https://openalex.org/W4281616076","https://openalex.org/W4283709535","https://openalex.org/W4283821822","https://openalex.org/W4307157288","https://openalex.org/W4312787220","https://openalex.org/W4312879041","https://openalex.org/W4313252151","https://openalex.org/W4318474097","https://openalex.org/W4320855770","https://openalex.org/W4361858559","https://openalex.org/W4390102031","https://openalex.org/W4390874533","https://openalex.org/W4394625882","https://openalex.org/W6793513153","https://openalex.org/W6850778630"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W358455808","https://openalex.org/W2795079307","https://openalex.org/W2054068410","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2605677994","https://openalex.org/W3120327675","https://openalex.org/W2116310671","https://openalex.org/W1483168212"],"abstract_inverted_index":{"In":[0,32],"recent":[1],"years,":[2],"text":[3,60,79,158],"recognition":[4,104],"has":[5],"made":[6],"significant":[7],"progress":[8],"with":[9,124],"the":[10,64,82],"booming":[11],"development":[12],"of":[13,45,59,77,86,90,102],"deep":[14],"learning":[15],"techniques":[16],"including":[17],"pre-training":[18,27,40],"schemes.":[19],"However,":[20],"for":[21,43,136],"texts":[22],"in":[23,120],"different":[24,53,75,107,121,137],"languages,":[25,92,108],"previous":[26,153],"methods":[28],"treat":[29],"them":[30],"separately.":[31],"this":[33],"paper,":[34],"we":[35,109],"propose":[36,110],"a":[37,111,128],"unified":[38,129],"self-supervised":[39],"method,":[41],"PuzText,":[42],"understanding":[44],"textures":[46],"and":[47,71,97],"strokes":[48],"which":[49],"are":[50],"consistent":[51],"across":[52],"languages.":[54,122],"By":[55],"reconstructing":[56,87],"permuted":[57],"patches":[58],"images,":[61],"PuzText":[62],"forces":[63],"model":[65,131],"to":[66,116],"learn":[67,117],"about":[68],"positional":[69],"relationships":[70],"fine-grained":[72],"details":[73],"from":[74],"parts":[76],"input":[78],"images.":[80],"Furthermore,":[81],"method":[83,150],"is":[84],"capable":[85],"never-before-seen":[88],"images":[89],"human":[91],"demonstrating":[93],"its":[94],"powerful":[95],"generalization":[96],"application":[98],"prospects.":[99],"Besides,":[100],"instead":[101],"multiplexed":[103],"heads":[105],"on":[106,143,155],"global":[112],"Character-Aware":[113],"Gate":[114],"(CAG)":[115],"characters":[118],"utilized":[119],"Fused":[123],"implicit":[125],"character-aware":[126],"representations,":[127],"language":[130],"will":[132],"construct":[133],"semantic":[134],"information":[135],"languages":[138],"within":[139],"specific":[140],"characters.":[141],"Experiments":[142],"several":[144],"public":[145],"benchmarks":[146],"show":[147],"that":[148],"our":[149],"significantly":[151],"outperforms":[152],"approaches":[154],"end-to-end":[156],"multilingual":[157],"recognition.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}