{"id":"https://openalex.org/W2527569769","doi":"https://doi.org/10.48550/arxiv.1609.08976","title":"Variational Autoencoder for Deep Learning of Images, Labels and Captions","display_name":"Variational Autoencoder for Deep Learning of Images, Labels and Captions","publication_year":2016,"publication_date":"2016-09-28","ids":{"openalex":"https://openalex.org/W2527569769","doi":"https://doi.org/10.48550/arxiv.1609.08976","mag":"2527569769"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1609.08976","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.08976","pdf_url":"https://arxiv.org/pdf/1609.08976","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1609.08976","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023417820","display_name":"Yunchen Pu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pu, Yunchen","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","Department of Electrical and Computer Engineering Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066666034","display_name":"Zhe Gan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gan, Zhe","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","Department of Electrical and Computer Engineering Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056639842","display_name":"Ricardo Henao","orcid":"https://orcid.org/0000-0003-4980-845X","observed_orcids":["https://orcid.org/0000-0003-4980-845X"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henao, Ricardo","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","Department of Electrical and Computer Engineering Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015431603","display_name":"Xin Yuan","orcid":"https://orcid.org/0000-0002-8311-7524","observed_orcids":["https://orcid.org/0000-0002-8311-7524"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Xin","raw_affiliation_strings":["[Nokia Bell Labs, Murray Hill]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Nokia Bell Labs, Murray Hill]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107893340","display_name":"Chunyuan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Chunyuan","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","Department of Electrical and Computer Engineering Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024237494","display_name":"Andrew Stevens","orcid":"https://orcid.org/0000-0002-8474-8483","observed_orcids":["https://orcid.org/0000-0002-8474-8483"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stevens, Andrew","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","Department of Electrical and Computer Engineering Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948","observed_orcids":["https://orcid.org/0000-0001-6277-7948"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carin, Lawrence","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","Department of Electrical and Computer Engineering Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Duke University {yp42 , zg27 ,","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":662,"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":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5009999871253967,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5009999871253967,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.20389999449253082,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13539999723434448,"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/variational-autoencoder","display_name":"variational autoencoder","score":0.9990000128746033},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.6060000061988831},{"id":"https://openalex.org/keywords/image-annotation","display_name":"image annotation","score":0.7080000042915344},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.8059999942779541},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.9459999799728394},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.7360000014305115},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.5839999914169312},{"id":"https://openalex.org/keywords/image-encoder","display_name":"image encoder","score":0.6209999918937683}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9543551206588745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8066487312316895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628692388534546},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6806550025939941},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6694669723510742},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6072062849998474},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5825918912887573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.566172182559967},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5555948615074158},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5421373248100281},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5168243050575256},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4290532171726227},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4260317087173462},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4230010509490967},{"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1609.08976","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.08976","pdf_url":"https://arxiv.org/pdf/1609.08976","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2951326654","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1609.08976","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1609.08976","doi":"https://doi.org/10.48550/arxiv.1609.08976","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1609.08976","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1609.08976","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.08976","pdf_url":"https://arxiv.org/pdf/1609.08976","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2527569769.pdf","grobid_xml":"https://content.openalex.org/works/W2527569769.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W830076066","https://openalex.org/W1428434093","https://openalex.org/W1514535095","https://openalex.org/W1576445103","https://openalex.org/W1606347560","https://openalex.org/W1686810756","https://openalex.org/W1691728462","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1959608418","https://openalex.org/W2059503458","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2108501770","https://openalex.org/W2122262818","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2133512280","https://openalex.org/W2147800946","https://openalex.org/W2156909104","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2166049352","https://openalex.org/W2185175083","https://openalex.org/W2273818272","https://openalex.org/W2551446786","https://openalex.org/W2949416428","https://openalex.org/W2950635152","https://openalex.org/W2952229419","https://openalex.org/W2952264928","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W3022399392","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W4400927252","https://openalex.org/W2594337990","https://openalex.org/W2963594498","https://openalex.org/W3088887718","https://openalex.org/W2954490751","https://openalex.org/W2960589896","https://openalex.org/W3003978108","https://openalex.org/W4313449687","https://openalex.org/W3129008098","https://openalex.org/W2987786433"],"abstract_inverted_index":{"A":[0],"novel":[1],"variational":[2],"autoencoder":[3],"is":[4,22,39,47,61,89,98,112,128],"developed":[5],"to":[6,49,64],"model":[7],"images,":[8],"as":[9,11,24,41,101],"well":[10],"associated":[12,122],"labels":[13,68],"or":[14,73],"captions.":[15],"The":[16,58],"Deep":[17],"Generative":[18],"Deconvolutional":[19],"Network":[20,37],"(DGDN)":[21],"used":[23,40,48],"a":[25,33,51,80,83,102,124],"decoder":[26],"of":[27,94,104,114,121],"the":[28,45,54,92,105,110,116,119,135],"latent":[29,55,59,95],"image":[30,43,85,117],"features,":[31],"and":[32],"deep":[34],"Convolutional":[35],"Neural":[36],"(CNN)":[38],"an":[42],"encoder;":[44],"CNN":[46,131,140],"approximate":[50],"distribution":[52,93],"for":[53,67,82,130],"DGDN":[56],"features/code.":[57],"code":[60],"also":[62],"linked":[63],"generative":[65],"models":[66],"(Bayesian":[69],"support":[70],"vector":[71],"machine)":[72],"captions":[74],"(recurrent":[75],"neural":[76],"network).":[77],"When":[78],"predicting":[79],"label/caption":[81],"new":[84,125],"at":[86],"test,":[87],"averaging":[88],"performed":[90],"across":[91],"codes;":[96],"this":[97],"computationally":[99],"efficient":[100],"consequence":[103],"learned":[106],"CNN-based":[107],"encoder.":[108],"Since":[109],"framework":[111,136],"capable":[113],"modeling":[115],"in":[118],"presence/absence":[120],"labels/captions,":[123],"semi-supervised":[126],"setting":[127],"manifested":[129],"learning":[132],"with":[133],"images;":[134],"even":[137],"allows":[138],"unsupervised":[139],"learning,":[141],"based":[142],"on":[143],"images":[144],"alone.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":66},{"year":2023,"cited_by_count":60},{"year":2022,"cited_by_count":82},{"year":2021,"cited_by_count":111},{"year":2020,"cited_by_count":121},{"year":2019,"cited_by_count":91},{"year":2018,"cited_by_count":65},{"year":2017,"cited_by_count":27},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-10-07T00:00:00"}