{"id":"https://openalex.org/W1998042868","doi":"https://doi.org/10.1109/iccv.2011.6126402","title":"End-to-end scene text recognition","display_name":"End-to-end scene text recognition","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W1998042868","doi":"https://doi.org/10.1109/iccv.2011.6126402","mag":"1998042868"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2011.6126402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2011.6126402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on 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/A5100437036","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-6170-4744"},"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":"Kai Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, San Diego, USA","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, USA","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/A5051339229","display_name":"Boris Babenko","orcid":"https://orcid.org/0000-0002-3013-3678"},"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":"Boris Babenko","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, San Diego, USA","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, USA","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":"last","author":{"id":"https://openalex.org/A5018609918","display_name":"Serge Belongie","orcid":"https://orcid.org/0000-0002-0388-5217"},"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":"Serge Belongie","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, San Diego, USA","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, USA","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1121,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1457","last_page":"1464"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973999857902527,"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":0.8190082311630249},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.690842866897583},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.653274655342102},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.6416298151016235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6333743929862976},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.6118556261062622},{"id":"https://openalex.org/keywords/sketch-recognition","display_name":"Sketch recognition","score":0.603722870349884},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5658838152885437},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5412148833274841},{"id":"https://openalex.org/keywords/intelligent-character-recognition","display_name":"Intelligent character recognition","score":0.5275152325630188},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.5144920349121094},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49700573086738586},{"id":"https://openalex.org/keywords/3d-single-object-recognition","display_name":"3D single-object recognition","score":0.4926198124885559},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4621236324310303},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43545016646385193},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4348859488964081},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4273890256881714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41483426094055176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4078047573566437},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3665695786476135},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.27075129747390747},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.26309043169021606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190082311630249},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.690842866897583},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.653274655342102},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.6416298151016235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6333743929862976},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.6118556261062622},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.603722870349884},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5658838152885437},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5412148833274841},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.5275152325630188},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.5144920349121094},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49700573086738586},{"id":"https://openalex.org/C14551309","wikidata":"https://www.wikidata.org/wiki/Q4636325","display_name":"3D single-object recognition","level":4,"score":0.4926198124885559},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4621236324310303},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43545016646385193},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4348859488964081},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4273890256881714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41483426094055176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4078047573566437},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3665695786476135},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.27075129747390747},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.26309043169021606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2011.6126402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2011.6126402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on Computer Vision","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1488125194","https://openalex.org/W1521064364","https://openalex.org/W1579279110","https://openalex.org/W1663973292","https://openalex.org/W1834846564","https://openalex.org/W2030536784","https://openalex.org/W2031489346","https://openalex.org/W2100588357","https://openalex.org/W2101886560","https://openalex.org/W2127095579","https://openalex.org/W2131673214","https://openalex.org/W2135431879","https://openalex.org/W2140132917","https://openalex.org/W2142159465","https://openalex.org/W2148596671","https://openalex.org/W2149251234","https://openalex.org/W2153062878","https://openalex.org/W2161969291","https://openalex.org/W2164598857","https://openalex.org/W2168356304","https://openalex.org/W2594639291","https://openalex.org/W3141021069","https://openalex.org/W4213116910","https://openalex.org/W6629021407","https://openalex.org/W6631165897","https://openalex.org/W6679774445"],"related_works":["https://openalex.org/W4312663241","https://openalex.org/W3164639770","https://openalex.org/W3103048049","https://openalex.org/W4221004363","https://openalex.org/W2963299604","https://openalex.org/W3211262047","https://openalex.org/W950386562","https://openalex.org/W4297798696","https://openalex.org/W1998042868","https://openalex.org/W3095058371"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3],"the":[4,33,39,70,89,129,150,162,173],"problem":[5,15,72],"of":[6,38,73,99,120,152],"word":[7,48,74],"detection":[8,44,101],"and":[9,26,45,82],"recognition":[10,138,169],"in":[11,23,53,114,124,181],"natural":[12],"images.":[13],"The":[14,86,108],"is":[16,60,62,93,110],"significantly":[17],"more":[18],"challenging":[19],"than":[20],"reading":[21],"text":[22,43,100,137,168],"scanned":[24],"documents,":[25],"has":[27,139],"only":[28],"recently":[29],"gained":[30],"attention":[31],"from":[32,172],"computer":[34,155],"vision":[35,156],"community.":[36],"Sub-components":[37],"problem,":[40],"such":[41],"as":[42],"cropped":[46],"image":[47],"recognition,":[49,117],"have":[50,177],"been":[51,141,178],"studied":[52],"isolation":[54],"[7,":[55],"4,":[56],"20].":[57],"However,":[58],"what":[59],"unclear":[61],"how":[63],"these":[64],"recent":[65],"approaches":[66],"contribute":[67],"to":[68,170],"solving":[69],"end-to-end":[71],"recognition.":[75,183],"We":[76,126],"fill":[77],"this":[78,159],"gap":[79],"by":[80,103],"constructing":[81],"evaluating":[83],"two":[84,95],"systems.":[85],"first,":[87],"representing":[88],"de":[90],"facto":[91],"state-of-the-art,":[92],"a":[94,104,111],"stage":[96],"pipeline":[97],"consisting":[98],"followed":[102],"leading":[105],"OCR":[106],"engine.":[107],"second":[109],"system":[112],"rooted":[113],"generic":[115,154],"object":[116,182],"an":[118],"extension":[119],"our":[121,147],"previous":[122],"work":[123],"[20].":[125],"show":[127],"that":[128,176],"latter":[130],"approach":[131,160],"achieves":[132],"superior":[133],"performance.":[134],"While":[135],"scene":[136,167],"generally":[140],"treated":[142],"with":[143],"highly":[144],"domain-specific":[145],"methods,":[146],"results":[148],"demonstrate":[149],"suitability":[151],"applying":[153],"methods.":[157],"Adopting":[158],"opens":[161],"door":[163],"for":[164],"real":[165],"world":[166],"benefit":[171],"rapid":[174],"advances":[175],"taking":[179],"place":[180]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":54},{"year":2023,"cited_by_count":68},{"year":2022,"cited_by_count":58},{"year":2021,"cited_by_count":154},{"year":2020,"cited_by_count":114},{"year":2019,"cited_by_count":123},{"year":2018,"cited_by_count":106},{"year":2017,"cited_by_count":83},{"year":2016,"cited_by_count":92},{"year":2015,"cited_by_count":83},{"year":2014,"cited_by_count":64},{"year":2013,"cited_by_count":45},{"year":2012,"cited_by_count":22}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}