{"id":"https://openalex.org/W27675589","doi":null,"title":"Parameter Learning and Convergent Inference for Dense Random Fields","display_name":"Parameter Learning and Convergent Inference for Dense Random Fields","publication_year":2013,"publication_date":"2013-06-16","ids":{"openalex":"https://openalex.org/W27675589","mag":"27675589"},"language":"en","primary_location":{"id":"mag:27675589","doi":null,"is_oa":false,"landing_page_url":"http://jmlr.csail.mit.edu/proceedings/papers/v28/kraehenbuehl13.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5057535281","display_name":"Philipp Kr\u00e4henb\u00fchl","orcid":"https://orcid.org/0000-0002-9846-4369","observed_orcids":["https://orcid.org/0000-0002-9846-4369"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philipp Kraehenbuehl","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford CA 94305, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford CA 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006181255","display_name":"Vladlen Koltun","orcid":"https://orcid.org/0000-0003-0858-0970","observed_orcids":["https://orcid.org/0000-0003-0858-0970"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladlen Koltun","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford CA 94305, USA"],"raw_orcid":"https://orcid.org/0000-0003-0858-0970","affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford CA 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":11.1041,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.99090201,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"513","last_page":"521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.8705999851226807,"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"}},"topics":[{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.8705999851226807,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05480000004172325,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.019099999219179153,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parameter-learning","display_name":"parameter learning","score":0.7990000247955322},{"id":"https://openalex.org/keywords/mean-field-inference","display_name":"mean-field inference","score":0.9639999866485596},{"id":"https://openalex.org/keywords/pair-potential","display_name":"pair potential","score":0.8849999904632568},{"id":"https://openalex.org/keywords/joint-parameter-estimation","display_name":"joint parameter estimation","score":0.7559999823570251},{"id":"https://openalex.org/keywords/gradient-computation","display_name":"gradient computation","score":0.5830000042915344},{"id":"https://openalex.org/keywords/computer-vision-models","display_name":"computer vision models","score":0.6650000214576721}],"concepts":[{"id":"https://openalex.org/C130402806","wikidata":"https://www.wikidata.org/wiki/Q5361768","display_name":"Random field","level":2,"score":0.811102032661438},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7899731397628784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6009439826011658},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5548096895217896},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.5516230463981628},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5224315524101257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49976611137390137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4467931091785431},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4458846151828766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35988205671310425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3380105495452881},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14852872490882874},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:27675589","doi":null,"is_oa":false,"landing_page_url":"http://jmlr.csail.mit.edu/proceedings/papers/v28/kraehenbuehl13.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W35586085","https://openalex.org/W114565888","https://openalex.org/W136290230","https://openalex.org/W150235323","https://openalex.org/W1497499643","https://openalex.org/W1857926807","https://openalex.org/W1969735849","https://openalex.org/W2054279472","https://openalex.org/W2095844239","https://openalex.org/W2096920988","https://openalex.org/W2099608971","https://openalex.org/W2104650092","https://openalex.org/W2109189215","https://openalex.org/W2116877738","https://openalex.org/W2120340025","https://openalex.org/W2127856808","https://openalex.org/W2130184048","https://openalex.org/W2130248603","https://openalex.org/W2137853299","https://openalex.org/W2147102238","https://openalex.org/W2159992248","https://openalex.org/W2161236525","https://openalex.org/W2161914416","https://openalex.org/W2167219413","https://openalex.org/W2171650716"],"related_works":["https://openalex.org/W2574864235","https://openalex.org/W7100240784","https://openalex.org/W2099608971","https://openalex.org/W7100561478","https://openalex.org/W2104650092","https://openalex.org/W2252343674","https://openalex.org/W2324118725","https://openalex.org/W2904369601","https://openalex.org/W7099829801","https://openalex.org/W7097351367"],"abstract_inverted_index":{"Dense":[0],"random":[1,28,51,70,130],"fields":[2,29,52,131],"are":[3,11,74],"models":[4,37],"in":[5,26,42,68,115],"which":[6],"all":[7],"pairs":[8],"of":[9,86,89,111],"variables":[10],"directly":[12,107],"connected":[13],"by":[14],"pairwise":[15],"potentials.":[16],"It":[17],"has":[18],"recently":[19],"been":[20],"shown":[21],"that":[22,35,84,106,132],"mean":[23,94,112],"field":[24,95,113],"inference":[25,114,126],"dense":[27,50,69,129],"can":[30,97],"be":[31,98],"performed":[32],"efficiently":[33],"and":[34],"these":[36],"enable":[38],"significant":[39],"accuracy":[40],"gains":[41],"computer":[43],"vision":[44],"applications.":[45],"However,":[46],"parameter":[47],"estimation":[48],"for":[49,65,128],"is":[53,133],"still":[54],"poorly":[55],"understood.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,122],"present":[61,123],"an":[62,124],"efficient":[63,125],"algorithm":[64,103,127],"learning":[66],"parameters":[67,73,105],"fields.":[71],"All":[72],"estimated":[75],"jointly,":[76],"thus":[77],"capturing":[78],"dependencies":[79],"between":[80],"them.":[81],"We":[82],"show":[83],"gradients":[85],"a":[87,119],"variety":[88],"loss":[90],"functions":[91],"over":[92],"the":[93,109,116],"marginals":[96],"computed":[99],"efficiently.":[100],"The":[101],"resulting":[102],"learns":[104],"optimize":[108],"performance":[110],"model.":[117],"As":[118],"supporting":[120],"result,":[121],"guaranteed":[134],"to":[135],"converge.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}