{"id":"https://openalex.org/W1998981432","doi":"https://doi.org/10.1109/wacv.2014.6836024","title":"Video text detection and recognition: Dataset and benchmark","display_name":"Video text detection and recognition: Dataset and benchmark","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W1998981432","doi":"https://doi.org/10.1109/wacv.2014.6836024","mag":"1998981432"},"language":"en","primary_location":{"id":"doi:10.1109/wacv.2014.6836024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2014.6836024","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"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":"IEEE Winter Conference on Applications of Computer Vision","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/A5103445143","display_name":"Phuc Xuan Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phuc Xuan Nguyen","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, San Diego","Department of Computer Science and Engineering , University of California , San Diego, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of Computer Science and Engineering , University of California , San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766804","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0001-5589-7060"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Google Inc","Google, Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018609918","display_name":"Serge Belongie","orcid":"https://orcid.org/0000-0002-0388-5217"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I76513827","display_name":"New York City College of Technology","ror":"https://ror.org/021a7pw18","country_code":"US","type":"education","lineage":["https://openalex.org/I76513827"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Serge Belongie","raw_affiliation_strings":["Cornell NYC Tech, Cornell University","Cornell NYC Tech, Cornell University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell NYC Tech, Cornell University","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I76513827"]},{"raw_affiliation_string":"Cornell NYC Tech, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4763,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.96923716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"776","last_page":"783"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.994700014591217,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926999807357788,"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":0.8438513278961182},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.7166996598243713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6804857850074768},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6007257699966431},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5708339214324951},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5606440305709839},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5503982901573181},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.5210939645767212},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49372348189353943},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4927699863910675},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44266051054000854},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21997472643852234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438513278961182},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.7166996598243713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6804857850074768},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6007257699966431},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5708339214324951},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5606440305709839},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5503982901573181},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5210939645767212},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49372348189353943},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4927699863910675},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44266051054000854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21997472643852234},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv.2014.6836024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2014.6836024","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"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":"IEEE Winter Conference on Applications of Computer Vision","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.660.7984","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.660.7984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vision.ucsd.edu/sites/default/files/VideoTextWACV.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W349021890","https://openalex.org/W1488125194","https://openalex.org/W1506491340","https://openalex.org/W1521064364","https://openalex.org/W1579279110","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2019830313","https://openalex.org/W2046875449","https://openalex.org/W2049951199","https://openalex.org/W2056435187","https://openalex.org/W2061802763","https://openalex.org/W2076014259","https://openalex.org/W2124781496","https://openalex.org/W2128854450","https://openalex.org/W2131673214","https://openalex.org/W2135431879","https://openalex.org/W2140132917","https://openalex.org/W2141822239","https://openalex.org/W2146835493","https://openalex.org/W2148438840","https://openalex.org/W2155803963","https://openalex.org/W2161969291","https://openalex.org/W4213116910","https://openalex.org/W6629021407","https://openalex.org/W6630223264","https://openalex.org/W6631165897","https://openalex.org/W6649973027","https://openalex.org/W6679774445","https://openalex.org/W6842594352"],"related_works":["https://openalex.org/W4312663241","https://openalex.org/W4221004363","https://openalex.org/W2963299604","https://openalex.org/W3211262047","https://openalex.org/W3163712264","https://openalex.org/W950386562","https://openalex.org/W4306707571","https://openalex.org/W3179897446","https://openalex.org/W4387168087","https://openalex.org/W3107028621"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,75,97,108,122,144],"the":[4,39,76,88,98,127,145],"problem":[5],"of":[6,63,79,129],"text":[7,15,52,80,112,130,141],"detection":[8,16,85],"and":[9,17,70,91,107],"recognition":[10,18,53,131,142],"in":[11,19,25,54,81,132],"videos.":[12,133],"Even":[13],"though":[14],"images":[20,56],"has":[21,31],"seen":[22],"much":[23],"progress":[24],"recent":[26],"years,":[27],"relatively":[28],"little":[29],"work":[30],"been":[32],"done":[33],"to":[34,38,57,73,125],"extend":[35,46],"these":[36],"solutions":[37],"video":[40,105,111,140],"domain.":[41],"In":[42],"this":[43,135],"work,":[44],"we":[45,137],"an":[47],"existing":[48],"end-to-end":[49],"solution":[50],"for":[51,65],"natural":[55],"video.":[58,82],"We":[59,83,114],"explore":[60,71],"a":[61,109,117],"variety":[62],"methods":[64,72],"training":[66],"local":[67],"character":[68],"models":[69],"capitalize":[74],"temporal":[77],"redundancy":[78],"present":[84],"performance":[86,119,128],"using":[87],"Video":[89],"Analysis":[90],"Content":[92],"Extraction":[93],"(VACE)":[94],"benchmarking":[95],"framework":[96],"ICDAR":[99],"2013":[100],"Robust":[101],"Reading":[102],"Challenge":[103],"3":[104],"dataset":[106],"new":[110,118],"dataset.":[113],"also":[115],"propose":[116],"metric":[120],"based":[121],"precision-recall":[123],"curves":[124],"measure":[126],"Using":[134],"metric,":[136],"provide":[138],"early":[139],"results":[143],"above":[146],"mentioned":[147],"datasets.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":6}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}