{"id":"https://openalex.org/W2164452159","doi":"https://doi.org/10.1109/icdar.2007.4378728","title":"Energy-Based Models in Document Recognition and Computer Vision","display_name":"Energy-Based Models in Document Recognition and Computer Vision","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2164452159","doi":"https://doi.org/10.1109/icdar.2007.4378728","mag":"2164452159"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4378728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378728","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","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/A5001226970","display_name":"Yann LeCun","orcid":null},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. LeCun","raw_affiliation_strings":["The Courant Institute of Mathematical Sciences, New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Courant Institute of Mathematical Sciences, New York University, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078511139","display_name":"Sumit Chopra","orcid":"https://orcid.org/0009-0009-6637-2230"},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Chopra","raw_affiliation_strings":["The Courant Institute of Mathematical Sciences, New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Courant Institute of Mathematical Sciences, New York University, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112227538","display_name":"M. Ranzato","orcid":null},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Ranzato","raw_affiliation_strings":["The Courant Institute of Mathematical Sciences, New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Courant Institute of Mathematical Sciences, New York University, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102159709","display_name":"Fu-Shin Huang","orcid":"https://orcid.org/0009-0008-7230-8342"},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F.-J. Huang","raw_affiliation_strings":["The Courant Institute of Mathematical Sciences, New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Courant Institute of Mathematical Sciences, New York University, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9976000189781189,"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":0.7930347919464111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7426071166992188},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5934514403343201},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.5910214781761169},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.5841548442840576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5803884863853455},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5555753111839294},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5423120260238647},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.48682230710983276},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4829065799713135},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4653957784175873},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.45366954803466797},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4528648257255554},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.44911232590675354},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4116798937320709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930347919464111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7426071166992188},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5934514403343201},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.5910214781761169},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.5841548442840576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5803884863853455},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5555753111839294},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5423120260238647},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.48682230710983276},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4829065799713135},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4653957784175873},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.45366954803466797},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4528648257255554},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.44911232590675354},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4116798937320709},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2007.4378728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378728","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W107591854","https://openalex.org/W840664383","https://openalex.org/W1877570817","https://openalex.org/W2008652694","https://openalex.org/W2092650846","https://openalex.org/W2100495367","https://openalex.org/W2102252988","https://openalex.org/W2105644991","https://openalex.org/W2110798204","https://openalex.org/W2111488376","https://openalex.org/W2112504244","https://openalex.org/W2112796928","https://openalex.org/W2122342900","https://openalex.org/W2125653371","https://openalex.org/W2127661044","https://openalex.org/W2133233905","https://openalex.org/W2134557905","https://openalex.org/W2136922672","https://openalex.org/W2138621090","https://openalex.org/W2139427956","https://openalex.org/W2147800946","https://openalex.org/W2147880316","https://openalex.org/W2149381250","https://openalex.org/W2156163116","https://openalex.org/W2161914416","https://openalex.org/W2170599822","https://openalex.org/W2172174689","https://openalex.org/W2504108613","https://openalex.org/W2616465717","https://openalex.org/W6675760969","https://openalex.org/W6676481782","https://openalex.org/W6678219993","https://openalex.org/W6679135890","https://openalex.org/W6682082992","https://openalex.org/W6682739439","https://openalex.org/W6683825394"],"related_works":["https://openalex.org/W3003949997","https://openalex.org/W2110485610","https://openalex.org/W3199359807","https://openalex.org/W3047607512","https://openalex.org/W4390983538","https://openalex.org/W2744690920","https://openalex.org/W2787081548","https://openalex.org/W183832189","https://openalex.org/W2536878212","https://openalex.org/W3005534356"],"abstract_inverted_index":{"The":[0,21,120],"machine":[1],"learning":[2,19,61,122,188],"and":[3,15,46,92,103,161,163,175],"pattern":[4],"recognition":[5,90,136,211],"communities":[6,49],"are":[7],"facing":[8],"two":[9],"challenges:":[10],"solving":[11,16],"the":[12,17,27,44,67,85,88,113,127,132,191,199,210,216],"normalization":[13,22],"problem,":[14],"deep":[18,121,155,195],"problem.":[20],"problem":[23,57,123],"is":[24,69,124],"related":[25,125],"to":[26,54,126,189],"difficulty":[28],"of":[29,77,116,129,134,193,202,212],"training":[30,130,181,203],"probabilistic":[31],"models":[32,62,78,111],"over":[33],"large":[34],"spaces":[35],"while":[36],"keeping":[37],"them":[38],"properly":[39],"normalized.":[40],"In":[41],"recent":[42],"years,":[43],"ML":[45],"natural":[47],"language":[48],"have":[50],"devoted":[51],"considerable":[52],"efforts":[53],"circumventing":[55],"this":[56],"by":[58],"developing":[59],"\"un-normalized\"":[60],"for":[63,154,173,206],"tasks":[64,208],"in":[65,80,87,144],"which":[66],"output":[68],"highly":[70],"structured":[71],"(e.g.":[72,138],"English":[73],"sentences).":[74],"This":[75],"class":[76],"was":[79],"fact":[81],"originally":[82],"developed":[83],"during":[84],"90's":[86],"handwriting":[89,174],"community,":[91],"includes":[93],"graph":[94],"transformer":[95],"networks,":[96],"conditional":[97],"random":[98],"fields,":[99],"hidden":[100],"Markov":[101,106],"SVMs,":[102],"maximum":[104],"margin":[105],"networks.":[107],"We":[108,148,183],"describe":[109],"these":[110],"within":[112],"unifying":[114],"framework":[115],"\"energy-based":[117],"models\"":[118],"(EBM).":[119],"issue":[128],"all":[131],"levels":[133],"a":[135,194],"system":[137],"segmentation,":[139],"feature":[140],"extraction,":[141],"recognition,":[142,177],"etc)":[143],"an":[145],"integrated":[146],"fashion.":[147],"first":[149],"consider":[150],"\"":[151],"traditional\"":[152],"methods":[153],"learning,":[156],"such":[157,207],"as":[158,209],"convolutional":[159],"networks":[160],"back-propagation,":[162],"show":[164,184],"that,":[165],"although":[166],"they":[167,178],"produce":[168],"very":[169],"low":[170],"error":[171],"rates":[172],"object":[176],"require":[179],"many":[180],"samples.":[182],"that":[185],"using":[186],"unsupervised":[187],"initialize":[190],"layers":[192],"network":[196],"dramatically":[197],"reduces":[198],"required":[200],"number":[201],"samples,":[204],"particularly":[205],"everyday":[213],"objects":[214],"at":[215],"category":[217],"level.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}