{"id":"https://openalex.org/W7098536107","doi":null,"title":"Synthetic data and artificial neural networks for natural scene text recognition.\" arXiv preprint arXiv:1406.2227","display_name":"Synthetic data and artificial neural networks for natural scene text recognition.\" arXiv preprint arXiv:1406.2227","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W7098536107"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.747.1366","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.747.1366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1406.2227.pdf","raw_type":"text"},"volume":null,"type":"preprint","indexed_in":[],"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/A5004153109","display_name":"Max Jaderberg","orcid":"https://orcid.org/0000-0002-9033-2695","observed_orcids":["https://orcid.org/0000-0002-9033-2695"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Max Jaderberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004625775","display_name":"Karen Simonyan","orcid":"https://orcid.org/0000-0003-0787-5507","observed_orcids":["https://orcid.org/0000-0003-0787-5507"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Simonyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060511349","display_name":"Andrea Vedaldi","orcid":"https://orcid.org/0000-0003-1374-2858","observed_orcids":["https://orcid.org/0000-0003-1374-2858"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Vedaldi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573","observed_orcids":["https://orcid.org/0000-0002-8945-8573"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0006000000284984708,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/synthetic-data","display_name":"synthetic data","score":0.6930000185966492},{"id":"https://openalex.org/keywords/synthetic-text-generation","display_name":"synthetic text generation","score":0.8510000109672546},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.7670000195503235},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.7279999852180481},{"id":"https://openalex.org/keywords/dictionary-encoding","display_name":"dictionary encoding","score":0.7699999809265137},{"id":"https://openalex.org/keywords/training-data-generation","display_name":"training data generation","score":0.46299999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831000089645386},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.722100019454956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6687999963760376},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5631999969482422},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4830000102519989},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C43169469","wikidata":"https://www.wikidata.org/wiki/Q580922","display_name":"Preprint","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.31949999928474426},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.747.1366","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.747.1366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1406.2227.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1491389626","https://openalex.org/W3194290481","https://openalex.org/W3013262970","https://openalex.org/W3003307646","https://openalex.org/W7165753481","https://openalex.org/W3216375096","https://openalex.org/W3090134383","https://openalex.org/W2988536940","https://openalex.org/W3184557382","https://openalex.org/W3013447421"],"abstract_inverted_index":{"In":[0,114],"this":[1],"work":[2],"we":[3,90,125],"present":[4],"a":[5,52,101],"framework":[6],"for":[7,84],"the":[8,26,30,35,41,115],"recognition":[9,24,38,86,124],"of":[10,40,74,79,117],"natural":[11],"scene":[12],"text.":[13],"We":[14],"use":[15],"purely":[16],"data-driven,":[17],"deep":[18],"learning":[19],"models":[20,44],"to":[21,66],"perform":[22],"word":[23,85],"on":[25,48,129],"whole":[27],"image":[28],"at":[29],"same":[31],"time,":[32],"departing":[33],"from":[34],"character":[36,108],"based":[37,119],"systems":[39],"past.":[42],"These":[43],"are":[45],"trained":[46],"solely":[47],"data":[49,59,80],"produced":[50],"by":[51],"syn-thetic":[53],"text":[54,123],"generation":[55],"engine":[56],"\u2013":[57],"synthetic":[58],"that":[60],"is":[61],"highly":[62],"realistic":[63],"and":[64,88,111,120,137],"sufficient":[65],"replace":[67],"real":[68],"data,":[69],"giving":[70],"us":[71],"infinite":[72],"amounts":[73],"training":[75],"data.":[76],"This":[77],"excess":[78],"exposes":[81],"new":[82],"possibilities":[83],"models,":[87,94],"here":[89],"introduce":[91],"three":[92],"novel":[93],"each":[95],"one":[96],"\u201creading":[97],"\u201d":[98],"words":[99],"in":[100],"complementary":[102],"way:":[103],"via":[104],"large-scale":[105],"dictionary":[106],"encoding,":[107,110],"sequence":[109],"bag-of-N-gram":[112],"en-coding.":[113],"scenarios":[116],"language/lexicon":[118],"completely":[121],"unconstrained":[122],"demonstrate":[126],"state-of-the-art":[127],"performance":[128],"standard":[130],"datasets,":[131],"using":[132],"our":[133],"fast,":[134],"simple":[135],"machinery":[136],"requiring":[138],"zero":[139],"data-acquisition":[140],"costs.":[141],"1":[142]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}