{"id":"https://openalex.org/W3162853402","doi":"https://doi.org/10.1109/icpr48806.2021.9412417","title":"Improving Word Recognition using Multiple Hypotheses and Deep Embeddings","display_name":"Improving Word Recognition using Multiple Hypotheses and Deep Embeddings","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3162853402","doi":"https://doi.org/10.1109/icpr48806.2021.9412417","mag":"3162853402"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085376445","display_name":"Siddhant Bansal","orcid":"https://orcid.org/0000-0003-2636-0066"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siddhant Bansal","raw_affiliation_strings":["CVIT, IIIT, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, IIIT, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043823449","display_name":"Praveen Krishnan","orcid":"https://orcid.org/0000-0003-4620-2292"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Praveen Krishnan","raw_affiliation_strings":["CVIT, IIIT, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, IIIT, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C.V. Jawahar","raw_affiliation_strings":["CVIT, IIIT, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, IIIT, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04893005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9499","last_page":"9506"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944999814033508,"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/word","display_name":"Word (group theory)","score":0.7144807577133179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7071824073791504},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6553165912628174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6079309582710266},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5385322570800781},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5114458799362183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48139429092407227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47744065523147583},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4464930593967438},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.43026307225227356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4231882095336914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18206539750099182}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7144807577133179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071824073791504},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6553165912628174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6079309582710266},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5385322570800781},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5114458799362183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48139429092407227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47744065523147583},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4464930593967438},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.43026307225227356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4231882095336914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18206539750099182},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W1491389626","https://openalex.org/W1529012620","https://openalex.org/W1686810756","https://openalex.org/W1932188282","https://openalex.org/W2001642682","https://openalex.org/W2029861656","https://openalex.org/W2053317383","https://openalex.org/W2061802143","https://openalex.org/W2096733369","https://openalex.org/W2114957138","https://openalex.org/W2116741014","https://openalex.org/W2127141656","https://openalex.org/W2154495259","https://openalex.org/W2158102958","https://openalex.org/W2185167094","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2481930807","https://openalex.org/W2548026590","https://openalex.org/W2573612273","https://openalex.org/W2574733408","https://openalex.org/W2578535984","https://openalex.org/W2787062907","https://openalex.org/W2800613688","https://openalex.org/W2810648379","https://openalex.org/W2904714269","https://openalex.org/W2962835968","https://openalex.org/W2963908984","https://openalex.org/W2963924711","https://openalex.org/W3080529507","https://openalex.org/W3099206234","https://openalex.org/W4238410424","https://openalex.org/W4241698512","https://openalex.org/W6629590909","https://openalex.org/W6637373629","https://openalex.org/W6650820226","https://openalex.org/W6687483927","https://openalex.org/W6721872216","https://openalex.org/W6731713104","https://openalex.org/W6746562123"],"related_works":["https://openalex.org/W4288407670","https://openalex.org/W2950396480","https://openalex.org/W947140380","https://openalex.org/W2911655849","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338"],"abstract_inverted_index":{"We":[0,15,55,163],"propose":[1,56,108],"a":[2,17,28,49,62,67,109,171],"novel":[3],"scheme":[4,34],"for":[5,27,65,151,159],"improving":[6],"the":[7,36,41,72,75,81,84,96,105,123,128,135,152,160,176],"word":[8,12,30,42,51,76,191],"recognition":[9,37,192],"accuracy":[10],"using":[11,61],"image":[13,43,52,77],"embeddings.":[14],"use":[16],"trained":[18,50,60],"text":[19,25,45,86,129],"recognizer,":[20],"which":[21,58],"can":[22],"predict":[23],"multiple":[24],"hypothesis":[26],"given":[29],"image.":[31],"Our":[32,179],"fusion":[33],"improves":[35],"process":[38],"by":[39],"utilizing":[40],"and":[44,131,155],"embeddings":[46,136],"obtained":[47,126],"from":[48,127],"embedding":[53,69,73,82,90],"network.":[54],"EmbedNet,":[57],"is":[59],"triplet":[63],"loss":[64],"learning":[66],"suitable":[68],"space":[70,91],"where":[71],"of":[74,83,173,185,190],"lies":[78],"closer":[79],"to":[80,137],"corresponding":[85],"transcription.":[87],"The":[88,118,143],"updated":[89,140,144],"thus":[92],"helps":[93],"in":[94,122,175,188],"choosing":[95],"correct":[97,153],"prediction":[98],"with":[99],"higher":[100,156],"confidence.":[101],"To":[102],"further":[103],"improve":[104],"accuracy,":[106],"we":[107],"plug-and-play":[110],"module":[111,120],"called":[112],"Confidence":[113],"based":[114],"Accuracy":[115],"Booster":[116],"(CAB).":[117],"CAB":[119],"takes":[121],"confidence":[124],"scores":[125],"recognizer":[130],"Euclidean":[132],"distances":[133],"between":[134],"generate":[138],"an":[139,182],"distance":[141,145,149,157],"vector.":[142],"vector":[146],"has":[147],"lower":[148],"values":[150,158],"words":[154],"incorrect":[161],"words.":[162],"rigorously":[164],"evaluate":[165],"our":[166],"proposed":[167],"method":[168,180],"systematically":[169],"on":[170],"collection":[172],"books":[174],"Hindi":[177],"language.":[178],"achieves":[181],"absolute":[183],"improvement":[184],"around":[186],"10%":[187],"terms":[189],"accuracy.":[193]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}