{"id":"https://openalex.org/W4406067002","doi":"https://doi.org/10.1007/s40747-024-01713-8","title":"IMTLM-Net: improved multi-task transformer based on localization mechanism network for handwritten English text recognition","display_name":"IMTLM-Net: improved multi-task transformer based on localization mechanism network for handwritten English text recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406067002","doi":"https://doi.org/10.1007/s40747-024-01713-8"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01713-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01713-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01713-8.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01713-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041938820","display_name":"Qian\u2010Feng Zhang","orcid":"https://orcid.org/0000-0003-0512-8532"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianfeng Zhang","raw_affiliation_strings":["School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100609156","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0003-2005-9117"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011281923","display_name":"Wanru Song","orcid":"https://orcid.org/0000-0002-7067-6108"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wanru Song","raw_affiliation_strings":["School of Educational Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, 210013, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Educational Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing, 210013, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011281923"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":5.3199,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94646466,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"11","issue":"1","first_page":null,"last_page":null},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9896000027656555,"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/transformer","display_name":"Transformer","score":0.6908186674118042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6264522671699524},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.6228498816490173},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5995870232582092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5172170400619507},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5058155059814453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4980130195617676},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4452395439147949},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4048982560634613},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19091147184371948},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15096065402030945},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10930627584457397},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07897329330444336}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6908186674118042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6264522671699524},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.6228498816490173},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5995870232582092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5172170400619507},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5058155059814453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4980130195617676},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4452395439147949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4048982560634613},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19091147184371948},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15096065402030945},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10930627584457397},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07897329330444336},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01713-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01713-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01713-8.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b2e1ad69088943cead926406efc53a21","is_oa":true,"landing_page_url":"https://doaj.org/article/b2e1ad69088943cead926406efc53a21","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 1, Pp 1-18 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01713-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01713-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01713-8.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4009049029","display_name":null,"funder_award_id":"Startup","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6089788172","display_name":null,"funder_award_id":"62307025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6357699058","display_name":null,"funder_award_id":"62177029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7570365276","display_name":null,"funder_award_id":"52002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7677171766","display_name":null,"funder_award_id":"23KJD580","funder_id":"https://openalex.org/F4320327891","funder_display_name":"Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions"},{"id":"https://openalex.org/G984791870","display_name":null,"funder_award_id":"22KJB520025","funder_id":"https://openalex.org/F4320327891","funder_display_name":"Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320327891","display_name":"Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406067002.pdf","grobid_xml":"https://content.openalex.org/works/W4406067002.grobid-xml"},"referenced_works_count":48,"referenced_works":["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/W2152928267","https://openalex.org/W2565262489","https://openalex.org/W2810983211","https://openalex.org/W2908452502","https://openalex.org/W2912420078","https://openalex.org/W2963047498","https://openalex.org/W2963526661","https://openalex.org/W2964018263","https://openalex.org/W2964065044","https://openalex.org/W2964199361","https://openalex.org/W2965066169","https://openalex.org/W2980487166","https://openalex.org/W3003218881","https://openalex.org/W3003711889","https://openalex.org/W3003868038","https://openalex.org/W3003921261","https://openalex.org/W3044641008","https://openalex.org/W3045882047","https://openalex.org/W3110267192","https://openalex.org/W3112478873","https://openalex.org/W3176512504","https://openalex.org/W3177684257","https://openalex.org/W3181186176","https://openalex.org/W3201139606","https://openalex.org/W3204479434","https://openalex.org/W4221004332","https://openalex.org/W4225562651","https://openalex.org/W4241307704","https://openalex.org/W4287024866","https://openalex.org/W4310376791","https://openalex.org/W4312879041","https://openalex.org/W4312950730","https://openalex.org/W4313045695","https://openalex.org/W4317677707","https://openalex.org/W4379143695","https://openalex.org/W4388997040","https://openalex.org/W4391994303","https://openalex.org/W4396934999","https://openalex.org/W4399530116","https://openalex.org/W4405784827","https://openalex.org/W6604896550","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W2382997850","https://openalex.org/W2390968135","https://openalex.org/W2382213751","https://openalex.org/W2351750670","https://openalex.org/W1597848696","https://openalex.org/W2354715126","https://openalex.org/W2388563748","https://openalex.org/W2375179084","https://openalex.org/W2366646518","https://openalex.org/W2370906336"],"abstract_inverted_index":{"Intelligence":[0],"technology":[1],"has":[2],"widely":[3],"empowered":[4],"education.":[5],"As":[6],"an":[7],"example,":[8],"Optical":[9],"Character":[10],"Recognition":[11],"(OCR)":[12],"can":[13],"be":[14],"used":[15],"in":[16,66,168,204,232,252],"smart":[17],"education":[18],"scenarios":[19],"such":[20],"as":[21,44,59,61],"online":[22],"homework":[23],"correction":[24],"and":[25,63,72,106,119,155,174,185,212],"teaching":[26],"data":[27,80,109,113],"analysis.":[28],"One":[29],"of":[30,40,79,121,172],"the":[31,70,73,77,93,97,103,117,122,125,153,169,205,216,235,246],"fundamental":[32],"yet":[33],"challenging":[34],"tasks":[35],"is":[36,49,141,180,191,220],"to":[37,54,86,111,182,222,238],"recognize":[38],"images":[39],"handwritten":[41,51,82,144,253],"English":[42,145],"text":[43,46,52,83,146,173,210,254],"editable":[45],"accurately.":[47],"This":[48],"because":[50],"tends":[53],"have":[55],"different":[56],"writing":[57],"habits":[58],"well":[60],"smearing":[62],"overlapping,":[64],"resulting":[65],"hard":[67],"alignment":[68],"between":[69],"image":[71,213,229],"real":[74],"text.":[75],"Additionally,":[76],"lack":[78],"on":[81,96,124,136,209],"further":[84],"leads":[85],"a":[87,128,162,176,186],"lower":[88],"recognition":[89],"rate.":[90],"To":[91],"address":[92],"above":[94],"issue,":[95],"one":[98],"hand,":[99,127],"this":[100],"paper":[101],"extends":[102],"existing":[104],"dataset":[105],"introduces":[107,161],"hyphenated":[108],"annotation":[110],"provide":[112],"support":[114],"for":[115,143,193],"improving":[116],"robustness":[118],"discrimination":[120],"model;":[123],"other":[126],"novel":[129],"framework":[130],"named":[131],"Improved":[132],"Multi-task":[133],"Transformer":[134,178],"based":[135],"Localization":[137],"Mechanism":[138],"Network":[139],"(IMTLM-Net)":[140],"proposed":[142,247],"recognition.":[147,255],"IMTLM-Net":[148],"contains":[149],"two":[150],"parts,":[151],"namely":[152],"encoding":[154,159],"decoding":[156,206],"modules.":[157],"The":[158],"module":[160],"dual-stream":[163],"processing":[164,171],"mechanism.":[165],"That":[166],"is,":[167],"simultaneous":[170],"images,":[175,184],"Vision":[177],"(VIT)":[179],"utilized":[181],"encode":[183],"Permutation":[187],"Language":[188],"Model":[189],"(PLM)":[190],"designed":[192],"word":[194],"arrangement.":[195],"Two":[196],"Multiple":[197],"Head":[198],"Attention":[199],"(MHA)":[200],"units":[201],"are":[202],"employed":[203],"module,":[207],"focusing":[208],"sequences":[211],"sequences.":[214],"Moreover,":[215],"localization":[217],"mechanism":[218],"(LM)":[219],"applied":[221],"enhance":[223],"font":[224],"structure":[225],"feature":[226],"extraction":[227],"from":[228],"data,":[230],"which":[231],"turn":[233],"improves":[234],"model\u2019s":[236],"ability":[237],"capture":[239],"complex":[240],"details.":[241],"Numerous":[242],"experiments":[243],"demonstrate":[244],"that":[245],"method":[248],"achieves":[249],"state-of-the-art":[250],"results":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
