{"id":"https://openalex.org/W2049951199","doi":"https://doi.org/10.1109/cvpr.2012.6247990","title":"Top-down and bottom-up cues for scene text recognition","display_name":"Top-down and bottom-up cues for scene text recognition","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2049951199","doi":"https://doi.org/10.1109/cvpr.2012.6247990","mag":"2049951199"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2012.6247990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00818178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075621328","display_name":"Anand Mishra","orcid":"https://orcid.org/0000-0002-7806-2557"},"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"]},{"id":"https://openalex.org/I4210115791","display_name":"Center for Visual Communication (United States)","ror":"https://ror.org/02dhkpg18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210115791"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"A. Mishra","raw_affiliation_strings":["CVIT, IIIT-Hyderabad, India","Center for Visual Information Technology [Hyderabad]"],"affiliations":[{"raw_affiliation_string":"CVIT, IIIT-Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Center for Visual Information Technology [Hyderabad]","institution_ids":["https://openalex.org/I4210115791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049440980","display_name":"Karteek Alahari","orcid":"https://orcid.org/0000-0002-1838-5936"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"K. Alahari","raw_affiliation_strings":["INRIA-WILLOW/ \u00c9cole Normale Sup\u00e9rieure, Paris, France","Laboratoire d'informatique de l'\u00e9cole normale sup\u00e9rieure","Models of visual object recognition and scene understanding"],"affiliations":[{"raw_affiliation_string":"INRIA-WILLOW/ \u00c9cole Normale Sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Laboratoire d'informatique de l'\u00e9cole normale sup\u00e9rieure","institution_ids":["https://openalex.org/I4210103330"]},{"raw_affiliation_string":"Models of visual object recognition and scene understanding","institution_ids":[]}]},{"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/I4210115791","display_name":"Center for Visual Communication (United States)","ror":"https://ror.org/02dhkpg18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210115791"]},{"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","US"],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["CVIT, IIIT-Hyderabad, India","Center for Visual Information Technology [Hyderabad]"],"affiliations":[{"raw_affiliation_string":"CVIT, IIIT-Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Center for Visual Information Technology [Hyderabad]","institution_ids":["https://openalex.org/I4210115791"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075621328"],"corresponding_institution_ids":["https://openalex.org/I4210115791","https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":31.103,"has_fulltext":false,"cited_by_count":349,"citation_normalized_percentile":{"value":0.99781482,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2687","last_page":"2694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9976000189781189,"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/conditional-random-field","display_name":"Conditional random field","score":0.8218427896499634},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.8066785335540771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7649118900299072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6519298553466797},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6455007791519165},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5720537900924683},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5330257415771484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.482825368642807},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4695760905742645},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.46074071526527405},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45346155762672424},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.44613462686538696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4005734920501709},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34238749742507935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10507655143737793},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07472419738769531}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8218427896499634},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.8066785335540771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649118900299072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6519298553466797},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6455007791519165},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5720537900924683},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5330257415771484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.482825368642807},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4695760905742645},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.46074071526527405},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45346155762672424},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44613462686538696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4005734920501709},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34238749742507935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10507655143737793},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07472419738769531},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2012.6247990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.7881","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.7881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.di.ens.fr/~alahari/papers/mishra12.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00818178v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00818178","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, United States. ⟨10.1109/CVPR.2012.6247990⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00818178v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00818178","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, United States. ⟨10.1109/CVPR.2012.6247990⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W568057840","https://openalex.org/W956551720","https://openalex.org/W1488125194","https://openalex.org/W1510835000","https://openalex.org/W1521064364","https://openalex.org/W1579279110","https://openalex.org/W1610707153","https://openalex.org/W1913356549","https://openalex.org/W1969735849","https://openalex.org/W1973772835","https://openalex.org/W1998042868","https://openalex.org/W2031489346","https://openalex.org/W2054279472","https://openalex.org/W2066134726","https://openalex.org/W2076014259","https://openalex.org/W2131673214","https://openalex.org/W2135431879","https://openalex.org/W2141493963","https://openalex.org/W2142037471","https://openalex.org/W2142159465","https://openalex.org/W2147880316","https://openalex.org/W2151698683","https://openalex.org/W2152162047","https://openalex.org/W2152513128","https://openalex.org/W2153635508","https://openalex.org/W2159080219","https://openalex.org/W2161969291","https://openalex.org/W2164598857","https://openalex.org/W2164918853","https://openalex.org/W2168356304","https://openalex.org/W4213116910","https://openalex.org/W6625044600","https://openalex.org/W6629021407","https://openalex.org/W6631165897","https://openalex.org/W6639824712","https://openalex.org/W6649973027","https://openalex.org/W6679774445","https://openalex.org/W6996185213"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Scene":[0],"text":[1,17,41,113],"recognition":[2,27],"has":[3],"gained":[4],"significant":[5,130],"attention":[6],"from":[7,43,62,66,97],"the":[8,26,37,67,82,85,88,105,112,119,124],"computer":[9],"vision":[10],"community":[11],"in":[12,132],"recent":[13],"years.":[14],"Recognizing":[15],"such":[16],"is":[18,115],"a":[19,48,71,98],"challenging":[20,136],"problem,":[21],"even":[22],"more":[23],"so":[24],"than":[25],"of":[28,39,84],"scanned":[29],"documents.":[30],"In":[31],"this":[32],"work,":[33],"we":[34],"focus":[35],"on":[36,76,104,134],"problem":[38],"recognizing":[40],"extracted":[42],"street":[44],"images.":[45],"We":[46,69,92,128],"present":[47],"framework":[49],"that":[50],"exploits":[51],"both":[52],"bottom-up":[53,58],"and":[54,87,145],"top-down":[55,94],"cues.":[56],"The":[57,107],"cues":[59,95],"are":[60],"derived":[61],"individual":[63],"character":[64],"detections":[65,78,86],"image.":[68],"build":[70],"Conditional":[72],"Random":[73],"Field":[74],"model":[75,81],"these":[77],"to":[79,123],"jointly":[80],"strength":[83],"interactions":[89],"between":[90],"them.":[91],"impose":[93],"obtained":[96,116],"lexicon-based":[99],"prior,":[100],"i.e.":[101],"language":[102],"statistics,":[103],"model.":[106,127],"optimal":[108],"word":[109],"represented":[110],"by":[111,117],"image":[114],"minimizing":[118],"energy":[120],"function":[121],"corresponding":[122],"random":[125],"field":[126],"show":[129],"improvements":[131],"accuracies":[133],"two":[135],"public":[137],"datasets,":[138],"namely":[139],"Street":[140],"View":[141],"Text":[142],"(over":[143],"15%)":[144],"ICDAR":[146],"2003":[147],"(nearly":[148],"10%).":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":36},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":36},{"year":2015,"cited_by_count":41},{"year":2014,"cited_by_count":42},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}