{"id":"https://openalex.org/W4312403814","doi":"https://doi.org/10.1109/icpr56361.2022.9956488","title":"Arbitrary Shape Text Detection using Transformers","display_name":"Arbitrary Shape Text Detection using Transformers","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312403814","doi":"https://doi.org/10.1109/icpr56361.2022.9956488"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956488","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-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/A5034906156","display_name":"Zobeir Raisi","orcid":"https://orcid.org/0000-0002-1591-4492"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zobeir Raisi","raw_affiliation_strings":["University of Waterloo,Waterloo,ON,Canada,N2L 3G1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Waterloo,ON,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904133","display_name":"Georges Younes","orcid":"https://orcid.org/0000-0002-3344-4703"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Georges Younes","raw_affiliation_strings":["University of Waterloo,Waterloo,ON,Canada,N2L 3G1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Waterloo,ON,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077041853","display_name":"John Zelek","orcid":"https://orcid.org/0000-0002-8138-3546"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"John Zelek","raw_affiliation_strings":["University of Waterloo,Waterloo,ON,Canada,N2L 3G1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Waterloo,ON,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034906156"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.9595,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83530586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3238","last_page":"3245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9919000267982483,"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":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7337938547134399},{"id":"https://openalex.org/keywords/b\u00e9zier-curve","display_name":"B\u00e9zier curve","score":0.649321973323822},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5668221116065979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4867227375507355},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.48445701599121094},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.47264212369918823},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4620359241962433},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4360215961933136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42327386140823364},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.410851389169693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3423492908477783},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3237566649913788},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17781603336334229},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10985150933265686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337938547134399},{"id":"https://openalex.org/C206423108","wikidata":"https://www.wikidata.org/wiki/Q214728","display_name":"B\u00e9zier curve","level":2,"score":0.649321973323822},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5668221116065979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867227375507355},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.48445701599121094},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.47264212369918823},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4620359241962433},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4360215961933136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42327386140823364},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.410851389169693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3423492908477783},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3237566649913788},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17781603336334229},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10985150933265686},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956488","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1972065312","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2550687635","https://openalex.org/W2565639579","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2766895242","https://openalex.org/W2772800855","https://openalex.org/W2784050770","https://openalex.org/W2786148769","https://openalex.org/W2810028092","https://openalex.org/W2902494497","https://openalex.org/W2908510526","https://openalex.org/W2953106684","https://openalex.org/W2953606406","https://openalex.org/W2962810613","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963299604","https://openalex.org/W2963353821","https://openalex.org/W2963647456","https://openalex.org/W2967615747","https://openalex.org/W2982121427","https://openalex.org/W2988098900","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W3030520226","https://openalex.org/W3033633564","https://openalex.org/W3034514377","https://openalex.org/W3034792612","https://openalex.org/W3035222584","https://openalex.org/W3035679705","https://openalex.org/W3082397598","https://openalex.org/W3092462694","https://openalex.org/W3093046205","https://openalex.org/W3102695566","https://openalex.org/W3106250896","https://openalex.org/W3117450517","https://openalex.org/W3118760421","https://openalex.org/W3123709332","https://openalex.org/W3181016597","https://openalex.org/W3184923351","https://openalex.org/W3196976036","https://openalex.org/W4237918430","https://openalex.org/W4297812995","https://openalex.org/W6620707391","https://openalex.org/W6639824700","https://openalex.org/W6642972425","https://openalex.org/W6687483927","https://openalex.org/W6746206475","https://openalex.org/W6752143097","https://openalex.org/W6757817989","https://openalex.org/W6778485988","https://openalex.org/W6779399279","https://openalex.org/W6784094891","https://openalex.org/W6785652829","https://openalex.org/W6788071488","https://openalex.org/W6795297120","https://openalex.org/W6910730993"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Recent":[0],"text":[1,26,49,68,158],"detection":[2,159],"frameworks":[3],"require":[4],"several":[5],"handcrafted":[6],"components":[7],"such":[8],"as":[9],"anchor":[10],"generation,":[11],"non-maximum":[12],"suppression":[13],"(NMS),":[14],"or":[15],"multiple":[16],"processing":[17],"stages":[18],"(e.g.":[19],"label":[20],"generation)":[21],"to":[22,80],"detect":[23],"arbitrarily":[24],"shaped":[25],"images.":[27],"In":[28],"contrast,":[29],"we":[30],"propose":[31],"an":[32],"end-to-end":[33],"trainable":[34],"architecture":[35],"based":[36],"on":[37],"Detection":[38],"using":[39,129],"Transformers":[40],"(DETR),":[41],"that":[42,62,89,147],"outperforms":[43,151],"previous":[44,153],"state-of-the-art":[45,154],"methods":[46,155],"in":[47,71,156],"arbitrary-shaped":[48],"detection.At":[50],"its":[51],"core,":[52],"our":[53,126],"proposed":[54,97,127,149],"method":[55,150],"leverages":[56],"a":[57,81,102,105,116],"bounding":[58],"box":[59],"loss":[60,98,107],"function":[61,99],"accurately":[63],"measures":[64],"the":[65,110,120,148,152],"arbitrary":[66],"detected":[67],"regions\u2019":[69],"changes":[70],"scale":[72],"and":[73,113,131,137,139,145],"aspect":[74],"ratio.":[75],"This":[76],"is":[77,100],"possible":[78],"due":[79],"hybrid":[82],"shape":[83],"representation":[84],"made":[85],"from":[86],"Bezier":[87,121],"curves,":[88],"are":[90],"further":[91],"split":[92],"into":[93],"piece-wise":[94,111],"polygons.":[95],"The":[96],"then":[101],"combination":[103],"of":[104],"generalized-split-intersection-over-union":[106],"defined":[108],"over":[109,119],"polygons,":[112],"regularized":[114],"by":[115],"Smooth-ln":[117],"regression":[118],"curve\u2019s":[122],"control":[123],"points.We":[124],"evaluate":[125],"model":[128],"Total-Text":[130],"CTW-1500":[132],"datasets":[133,141],"for":[134,142],"curved":[135],"text,":[136,144],"MSRA-TD500":[138],"ICDAR15":[140],"multi-oriented":[143],"show":[146],"arbitrary-shape":[157],"tasks.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
