Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators

In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variat...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-05
Main Authors: Jo, Dae Ung, Lee, ByeongJu, Choi, Jongwon, Yoo, Haanju, Jin Young Choi
Format: Article
Language:English
Subjects:
Bayesian analysis
Brain
Coders
Machine learning
Modal data
Neural networks
Statistical inference
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Jo, Dae Ung
Lee, ByeongJu
Choi, Jongwon
Yoo, Haanju
Jin Young Choi
description In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators. The variational associators transfer the latent spaces between auto-encoders that represent different modalities. The proposed structure successfully associates even heterogeneous modal data and easily incorporates the additional modality to the entire network via the proposed cross-modal associator. Furthermore, the proposed structure can be trained with only a small amount of paired data since auto-encoders can be trained by unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2232979980</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2232979980</sourcerecordid><originalsourceid>FETCH-proquest_journals_22329799803</originalsourceid><addsrcrecordid>eNqNjbEKwjAURYMgWLT_EHAOxBdr27FUxcFNcS2xiZhS-2pegr9vBz_A6Z7hHO6MJaDURhRbgAVLiTopJexyyDKVsEvtkUi80Oie37R3OjgcJq5iQGGHFo31_OPCk-8dBe_uMVjDzzrYIfDLqFtLXA-GV0TYTjV6WrH5Q_dk098u2fp4uNYnMXp8R0uh6TD66YQaAAVlXpaFVP9ZX1YgQGY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2232979980</pqid></control><display><type>article</type><title>Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators</title><source>Publicly Available Content (ProQuest)</source><creator>Jo, Dae Ung ; Lee, ByeongJu ; Choi, Jongwon ; Yoo, Haanju ; Jin Young Choi</creator><creatorcontrib>Jo, Dae Ung ; Lee, ByeongJu ; Choi, Jongwon ; Yoo, Haanju ; Jin Young Choi</creatorcontrib><description>In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators. The variational associators transfer the latent spaces between auto-encoders that represent different modalities. The proposed structure successfully associates even heterogeneous modal data and easily incorporates the additional modality to the entire network via the proposed cross-modal associator. Furthermore, the proposed structure can be trained with only a small amount of paired data since auto-encoders can be trained by unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Bayesian analysis ; Brain ; Coders ; Machine learning ; Modal data ; Neural networks ; Statistical inference</subject><ispartof>arXiv.org, 2019-05</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2232979980?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25744,37003,44581</link.rule.ids></links><search><creatorcontrib>Jo, Dae Ung</creatorcontrib><creatorcontrib>Lee, ByeongJu</creatorcontrib><creatorcontrib>Choi, Jongwon</creatorcontrib><creatorcontrib>Yoo, Haanju</creatorcontrib><creatorcontrib>Jin Young Choi</creatorcontrib><title>Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators</title><title>arXiv.org</title><description>In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators. The variational associators transfer the latent spaces between auto-encoders that represent different modalities. The proposed structure successfully associates even heterogeneous modal data and easily incorporates the additional modality to the entire network via the proposed cross-modal associator. Furthermore, the proposed structure can be trained with only a small amount of paired data since auto-encoders can be trained by unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.</description><subject>Bayesian analysis</subject><subject>Brain</subject><subject>Coders</subject><subject>Machine learning</subject><subject>Modal data</subject><subject>Neural networks</subject><subject>Statistical inference</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjbEKwjAURYMgWLT_EHAOxBdr27FUxcFNcS2xiZhS-2pegr9vBz_A6Z7hHO6MJaDURhRbgAVLiTopJexyyDKVsEvtkUi80Oie37R3OjgcJq5iQGGHFo31_OPCk-8dBe_uMVjDzzrYIfDLqFtLXA-GV0TYTjV6WrH5Q_dk098u2fp4uNYnMXp8R0uh6TD66YQaAAVlXpaFVP9ZX1YgQGY</recordid><startdate>20190530</startdate><enddate>20190530</enddate><creator>Jo, Dae Ung</creator><creator>Lee, ByeongJu</creator><creator>Choi, Jongwon</creator><creator>Yoo, Haanju</creator><creator>Jin Young Choi</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20190530</creationdate><title>Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators</title><author>Jo, Dae Ung ; Lee, ByeongJu ; Choi, Jongwon ; Yoo, Haanju ; Jin Young Choi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_22329799803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Bayesian analysis</topic><topic>Brain</topic><topic>Coders</topic><topic>Machine learning</topic><topic>Modal data</topic><topic>Neural networks</topic><topic>Statistical inference</topic><toplevel>online_resources</toplevel><creatorcontrib>Jo, Dae Ung</creatorcontrib><creatorcontrib>Lee, ByeongJu</creatorcontrib><creatorcontrib>Choi, Jongwon</creatorcontrib><creatorcontrib>Yoo, Haanju</creatorcontrib><creatorcontrib>Jin Young Choi</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest Engineering Database</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jo, Dae Ung</au><au>Lee, ByeongJu</au><au>Choi, Jongwon</au><au>Yoo, Haanju</au><au>Jin Young Choi</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators</atitle><jtitle>arXiv.org</jtitle><date>2019-05-30</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators. The variational associators transfer the latent spaces between auto-encoders that represent different modalities. The proposed structure successfully associates even heterogeneous modal data and easily incorporates the additional modality to the entire network via the proposed cross-modal associator. Furthermore, the proposed structure can be trained with only a small amount of paired data since auto-encoders can be trained by unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2019-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2232979980
source Publicly Available Content (ProQuest)
subjects Bayesian analysis
Brain
Coders
Machine learning
Modal data
Neural networks
Statistical inference
title Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T23%3A02%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Cross-modal%20Variational%20Auto-encoder%20with%20Distributed%20Latent%20Spaces%20and%20Associators&rft.jtitle=arXiv.org&rft.au=Jo,%20Dae%20Ung&rft.date=2019-05-30&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2232979980%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_22329799803%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2232979980&rft_id=info:pmid/&rfr_iscdi=true