{"id":"https://openalex.org/W2148463593","doi":null,"title":"Improved Multimodal Deep Learning with Variation of Information","display_name":"Improved Multimodal Deep Learning with Variation of Information","publication_year":2014,"publication_date":"2014-12-08","ids":{"openalex":"https://openalex.org/W2148463593","mag":"2148463593"},"language":"en","primary_location":{"id":"mag:2148463593","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/5279-improved-multimodal-deep-learning-with-variation-of-information.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","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/A5072573916","display_name":"Kihyuk Sohn","orcid":"https://orcid.org/0000-0003-4303-8319","observed_orcids":["https://orcid.org/0000-0003-4303-8319"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kihyuk Sohn","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI;"],"raw_orcid":"https://orcid.org/0000-0003-4303-8319","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI;","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019584508","display_name":"Wenling Shang","orcid":"https://orcid.org/0000-0001-9973-3092","observed_orcids":["https://orcid.org/0000-0001-9973-3092"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenling Shang","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI;"],"raw_orcid":"https://orcid.org/0000-0001-9973-3092","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI;","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108652283","display_name":"Honglak Lee","orcid":"https://orcid.org/0000-0002-4109-327X","observed_orcids":["https://orcid.org/0000-0002-4109-327X"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Honglak Lee","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI;","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":14.0285,"has_fulltext":false,"cited_by_count":145,"citation_normalized_percentile":{"value":0.99215173,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"2141","last_page":"2149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"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":0.0017000000225380063,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0007999999797903001,"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/multimodal-representation-learning","display_name":"multimodal representation learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/variation-of-information","display_name":"variation of information","score":0.9639999866485596},{"id":"https://openalex.org/keywords/joint-distribution-estimation","display_name":"joint distribution estimation","score":0.722000002861023},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"restricted Boltzmann machine","score":0.9449999928474426},{"id":"https://openalex.org/keywords/contrastive-divergence","display_name":"contrastive divergence","score":0.9779999852180481},{"id":"https://openalex.org/keywords/visual-recognition","display_name":"visual recognition","score":0.49300000071525574},{"id":"https://openalex.org/keywords/textual-features","display_name":"text features","score":0.6639999747276306},{"id":"https://openalex.org/keywords/pascal-voc-2007","display_name":"Pascal VOC 2007","score":0.9639999866485596}],"concepts":[{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.7853533029556274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727037668228149},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7138145565986633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7108108401298523},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.6653152108192444},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6607950925827026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5629380345344543},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.51173996925354},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5086449384689331},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.49690011143684387},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46169838309288025},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4357988238334656},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.41554051637649536},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41065242886543274},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40042349696159363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3665202260017395},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2148463593","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/5279-improved-multimodal-deep-learning-with-variation-of-information.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W182048296","https://openalex.org/W189596042","https://openalex.org/W391578156","https://openalex.org/W1202180536","https://openalex.org/W1566135517","https://openalex.org/W1697053819","https://openalex.org/W1860991815","https://openalex.org/W1981613567","https://openalex.org/W1999156278","https://openalex.org/W2009059481","https://openalex.org/W2022799064","https://openalex.org/W2036109700","https://openalex.org/W2082277036","https://openalex.org/W2098617596","https://openalex.org/W2100002341","https://openalex.org/W2100495367","https://openalex.org/W2107215754","https://openalex.org/W2108598243","https://openalex.org/W2109506130","https://openalex.org/W2112796928","https://openalex.org/W2116064496","https://openalex.org/W2116825644","https://openalex.org/W2126398289","https://openalex.org/W2135354436","https://openalex.org/W2148596671","https://openalex.org/W2151691375","https://openalex.org/W2155803963","https://openalex.org/W2163605009","https://openalex.org/W2164587673","https://openalex.org/W2170942078","https://openalex.org/W2184188583","https://openalex.org/W2552605897","https://openalex.org/W2953267151","https://openalex.org/W2953360861","https://openalex.org/W3038830718"],"related_works":["https://openalex.org/W2946165673","https://openalex.org/W154472438","https://openalex.org/W7096684434","https://openalex.org/W2919655474","https://openalex.org/W3205589360","https://openalex.org/W4414587871","https://openalex.org/W2766788829","https://openalex.org/W2557865186","https://openalex.org/W4403012134","https://openalex.org/W4213299273"],"abstract_inverted_index":{"Deep":[0],"learning":[1,9,16,80,89,111,134],"has":[2],"been":[3],"successfully":[4],"applied":[5],"to":[6,15,39,59,97,115,128,147,154],"multimodal":[7,54,78,122],"representation":[8,79],"problems,":[10],"with":[11,90,150,176],"a":[12,36,41,49,76,105],"common":[13],"strategy":[14],"joint":[17,119],"representations":[18],"that":[19,82],"are":[20],"shared":[21],"across":[22],"multiple":[23],"modalities":[24],"on":[25,137,168],"top":[26],"of":[27,29,53,68,101,121],"layers":[28],"modality-specific":[30],"networks.":[31],"Nonetheless,":[32],"there":[33],"still":[34],"remains":[35],"question":[37],"how":[38],"learn":[40],"good":[42,50],"association":[43],"between":[44],"data":[45,55,63,69],"modalities;":[46],"in":[47],"particular,":[48],"generative":[51],"model":[52,96],"should":[56],"be":[57],"able":[58],"reason":[60],"about":[61],"missing":[62],"modality":[64],"given":[65],"the":[66,95,99,109,117,156,163],"rest":[67],"modalities.":[70],"In":[71,143,159],"this":[72,85],"paper,":[73],"we":[74,93,145,161],"propose":[75],"novel":[77],"framework":[81],"explicitly":[83],"aims":[84],"goal.":[86],"Rather":[87],"than":[88],"maximum":[91],"likelihood,":[92],"train":[94],"minimize":[98],"variation":[100],"information.":[102],"We":[103,124],"provide":[104],"theoretical":[106],"insight":[107],"why":[108],"proposed":[110],"objective":[112],"is":[113],"sufficient":[114],"estimate":[116],"data-generating":[118],"distribution":[120],"data.":[123],"apply":[125],"our":[126],"method":[127],"restricted":[129],"Boltzmann":[130],"machines":[131],"and":[132,140,171,177],"introduce":[133],"methods":[135],"based":[136],"contrastive":[138],"divergence":[139],"multi-prediction":[141],"training.":[142],"addition,":[144],"extend":[146],"deep":[148],"networks":[149],"recurrent":[151],"encoding":[152],"structure":[153],"finetune":[155],"whole":[157],"network.":[158],"experiments,":[160],"demonstrate":[162],"state-of-the-art":[164],"visual":[165],"recognition":[166],"performance":[167],"MIR-Flickr":[169],"database":[170,175],"PASCAL":[172],"VOC":[173],"2007":[174],"without":[178],"text":[179],"features.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":6}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}