{"id":"https://openalex.org/W7160302029","doi":"https://doi.org/10.1109/wacv61042.2026.00200","title":"CURIO: Curvature-Aligned and Efficient OCR for Low-Resource Historical Manuscripts","display_name":"CURIO: Curvature-Aligned and Efficient OCR for Low-Resource Historical Manuscripts","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160302029","doi":"https://doi.org/10.1109/wacv61042.2026.00200"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5135352881","display_name":"Sai Madhusudan Gunda","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sai Madhusudan Gunda","raw_affiliation_strings":["International Institute of Information Technology Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135324539","display_name":"Tathagata Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tathagata Ghosh","raw_affiliation_strings":["International Institute of Information Technology Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135363089","display_name":"Simran Singh Sandral","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Simran Singh Sandral","raw_affiliation_strings":["International Institute of Information Technology Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038936106","display_name":"Ravi Kiran Sarvadevabhatla","orcid":"https://orcid.org/0000-0003-4134-1154"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Kiran Sarvadevabhatla","raw_affiliation_strings":["International Institute of Information Technology Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68961461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2011","last_page":"2021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.64410001039505,"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":0.64410001039505,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.042399998754262924,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.03240000084042549,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25850000977516174},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.24809999763965607},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.23770000040531158},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.22619999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5605999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40630000829696655},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2687000036239624},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24809999763965607},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.23770000040531158},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.23729999363422394},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.22619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4705840051174164,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W189028356","https://openalex.org/W1523191460","https://openalex.org/W2127141656","https://openalex.org/W2134560790","https://openalex.org/W2168270109","https://openalex.org/W2194775991","https://openalex.org/W2252269695","https://openalex.org/W2343052201","https://openalex.org/W2781760569","https://openalex.org/W2786974559","https://openalex.org/W2789003796","https://openalex.org/W2795753477","https://openalex.org/W2810983211","https://openalex.org/W2889985731","https://openalex.org/W2963526661","https://openalex.org/W2967615747","https://openalex.org/W3003428515","https://openalex.org/W3003543339","https://openalex.org/W3003773614","https://openalex.org/W3031548983","https://openalex.org/W3034904792","https://openalex.org/W3035165720","https://openalex.org/W3109645351","https://openalex.org/W3211950664","https://openalex.org/W4229453476","https://openalex.org/W4281968684","https://openalex.org/W4285213101","https://openalex.org/W4312933868","https://openalex.org/W4365508696","https://openalex.org/W4382202677","https://openalex.org/W4385990946","https://openalex.org/W4388642413","https://openalex.org/W4391217927","https://openalex.org/W4392911146","https://openalex.org/W4401043150","https://openalex.org/W4402191334","https://openalex.org/W4404239097","https://openalex.org/W4404970028","https://openalex.org/W4414192441"],"related_works":[],"abstract_inverted_index":{"We":[0,128],"present":[1],"CURIO,":[2],"an":[3],"OCR":[4,37],"system":[5],"for":[6,125],"low-resource":[7],"historical":[8],"manuscripts.":[9],"In":[10],"many":[11],"challenging":[12,133],"cases,":[13],"manuscripts":[14],"feature":[15],"curved":[16],"text":[17,92],"lines,":[18],"unsegmented":[19],"lines":[20,47,102,158],"with":[21,76,114,122,152],"lack":[22],"of":[23],"spacing":[24],"between":[25],"words,":[26],"and":[27,48,100,120,141,149,159],"highly":[28],"variable":[29],"line":[30,86],"lengths":[31],"\u2014":[32],"conditions":[33],"under":[34],"which":[35],"existing":[36],"methods":[38],"fail.":[39],"To":[40,79],"tackle":[41],"this":[42],"challenge,":[43],"we":[44,72,84],"first":[45],"extract":[46],"corresponding":[49],"curvature":[50,106],"profiles":[51],"from":[52],"manuscripts,":[53],"then":[54],"straighten":[55],"them":[56],"using":[57],"a":[58,111,139],"rectification":[59],"procedure":[60],"to":[61,166],"reduce":[62],"redundant":[63],"background":[64],"within":[65],"each":[66],"line.":[67],"Because":[68],"data":[69,75],"is":[70,110],"scarce,":[71],"compliment":[73],"real":[74,99],"synthetic":[77,101],"data.":[78],"bridge":[80],"the":[81,94,153],"synthetic\u2013real":[82],"gap,":[83],"generate":[85],"images":[87],"by":[88],"warping":[89],"rendered":[90],"straight":[91],"along":[93],"rectified":[95],"profiles,":[96],"ensuring":[97],"both":[98],"align":[103],"in":[104,137],"their":[105],"characteristics.":[107],"Our":[108],"recognizer":[109],"lightweight":[112],"CNN\u2013Transformer":[113],"padding-aware":[115],"null":[116],"activations,":[117],"sparse":[118],"attention":[119],"optimized":[121],"CTC":[123],"loss":[124],"efficient":[126],"training.":[127],"evaluate":[129],"our":[130],"method":[131],"on":[132,156],"manuscript":[134,173],"collections":[135],"written":[136],"Sharada,":[138],"rare":[140],"endangered":[142],"Indic":[143],"script.":[144],"CURIO":[145,162],"outperforms":[146],"strong":[147],"CNN+RNN":[148],"Transformer":[150],"baselines,":[151],"largest":[154],"gains":[155],"high-curvature":[157],"long":[160],"lines.":[161],"further":[163],"transfers":[164],"zero-shot":[165],"printed":[167],"Sharada":[168],"text,":[169],"indicating":[170],"robustness":[171],"beyond":[172],"domain.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}