Multitask Representation Learning for Multimodal Estimation of Depression Level

We propose a novel multitask learning attention -based deep neural network model, which facilitates the fusion of various modalities. In particular, we use this network to both regress and classify the level of depression. Acoustic, textual, and visual modalities have been used to train our proposed...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE intelligent systems 2019-09, Vol.34 (5), p.45-52
Hauptverfasser: Qureshi, Syed Arbaaz, Saha, Sriparna, Hasanuzzaman, Mohammed, Dias, Gael, Cambria, Erik
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 52
container_issue 5
container_start_page 45
container_title IEEE intelligent systems
container_volume 34
creator Qureshi, Syed Arbaaz
Saha, Sriparna
Hasanuzzaman, Mohammed
Dias, Gael
Cambria, Erik
description We propose a novel multitask learning attention -based deep neural network model, which facilitates the fusion of various modalities. In particular, we use this network to both regress and classify the level of depression. Acoustic, textual, and visual modalities have been used to train our proposed network. Various experiments have been carried out on the benchmark dataset, namely, Distress Analysis Interview Corpus -a Wizard of Oz. From the results, we empirically justify that a) multitask learning networks cotrained over regression and classification have better performance compared to single -task networks, and b) the fusion of all the modalities helps in giving the most accurate estimation of depression with respect to regression.
doi_str_mv 10.1109/MIS.2019.2925204
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_MIS_2019_2925204</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8910655</ieee_id><sourcerecordid>2317729674</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-56e2a24cda72d0e94bdcd8bf958cf3b2df803c591f04a07f89b493600b8ac1b3</originalsourceid><addsrcrecordid>eNo9kM9LwzAUx4MoOKd3wUvBc-vLrzY5ypw62Bjo7iFNE-mszUw6wf_ebB2e3vfw-bz3-CJ0i6HAGOTDavFeEMCyIJJwAuwMTbBkOMdEsvOU-SGXFblEVzFuAQgFLCZovdp3Qzvo-Jm92V2w0faDHlrfZ0urQ9_2H5nzITtSX77RXTaPKY2Id9nTUYqj8GO7a3ThdBftzWlO0eZ5vpm95sv1y2L2uMwNkXjIeWmJJsw0uiINWMnqxjSidpIL42hNGieAGi6xA6ahckLWTNISoBba4JpO0f24dhf8997GQW39PvTpoiIUVxWRZcUSBSNlgo8xWKd2If0efhUGdWhNpdbUoTV1ai0pd6PSWmv_cSExlJzTP361aXE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2317729674</pqid></control><display><type>article</type><title>Multitask Representation Learning for Multimodal Estimation of Depression Level</title><source>IEEE Electronic Library (IEL)</source><creator>Qureshi, Syed Arbaaz ; Saha, Sriparna ; Hasanuzzaman, Mohammed ; Dias, Gael ; Cambria, Erik</creator><contributor>Erik Cambria</contributor><creatorcontrib>Qureshi, Syed Arbaaz ; Saha, Sriparna ; Hasanuzzaman, Mohammed ; Dias, Gael ; Cambria, Erik ; Erik Cambria</creatorcontrib><description>We propose a novel multitask learning attention -based deep neural network model, which facilitates the fusion of various modalities. In particular, we use this network to both regress and classify the level of depression. Acoustic, textual, and visual modalities have been used to train our proposed network. Various experiments have been carried out on the benchmark dataset, namely, Distress Analysis Interview Corpus -a Wizard of Oz. From the results, we empirically justify that a) multitask learning networks cotrained over regression and classification have better performance compared to single -task networks, and b) the fusion of all the modalities helps in giving the most accurate estimation of depression with respect to regression.</description><identifier>ISSN: 1541-1672</identifier><identifier>EISSN: 1941-1294</identifier><identifier>DOI: 10.1109/MIS.2019.2925204</identifier><identifier>CODEN: IISYF7</identifier><language>eng</language><publisher>Los Alamitos: IEEE</publisher><subject>Affective computing ; Depression ; Estimation ; Learning systems ; Medical conditions</subject><ispartof>IEEE intelligent systems, 2019-09, Vol.34 (5), p.45-52</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-56e2a24cda72d0e94bdcd8bf958cf3b2df803c591f04a07f89b493600b8ac1b3</citedby><cites>FETCH-LOGICAL-c291t-56e2a24cda72d0e94bdcd8bf958cf3b2df803c591f04a07f89b493600b8ac1b3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8910655$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8910655$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><contributor>Erik Cambria</contributor><creatorcontrib>Qureshi, Syed Arbaaz</creatorcontrib><creatorcontrib>Saha, Sriparna</creatorcontrib><creatorcontrib>Hasanuzzaman, Mohammed</creatorcontrib><creatorcontrib>Dias, Gael</creatorcontrib><creatorcontrib>Cambria, Erik</creatorcontrib><title>Multitask Representation Learning for Multimodal Estimation of Depression Level</title><title>IEEE intelligent systems</title><addtitle>MIS</addtitle><description>We propose a novel multitask learning attention -based deep neural network model, which facilitates the fusion of various modalities. In particular, we use this network to both regress and classify the level of depression. Acoustic, textual, and visual modalities have been used to train our proposed network. Various experiments have been carried out on the benchmark dataset, namely, Distress Analysis Interview Corpus -a Wizard of Oz. From the results, we empirically justify that a) multitask learning networks cotrained over regression and classification have better performance compared to single -task networks, and b) the fusion of all the modalities helps in giving the most accurate estimation of depression with respect to regression.</description><subject>Affective computing</subject><subject>Depression</subject><subject>Estimation</subject><subject>Learning systems</subject><subject>Medical conditions</subject><issn>1541-1672</issn><issn>1941-1294</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kM9LwzAUx4MoOKd3wUvBc-vLrzY5ypw62Bjo7iFNE-mszUw6wf_ebB2e3vfw-bz3-CJ0i6HAGOTDavFeEMCyIJJwAuwMTbBkOMdEsvOU-SGXFblEVzFuAQgFLCZovdp3Qzvo-Jm92V2w0faDHlrfZ0urQ9_2H5nzITtSX77RXTaPKY2Id9nTUYqj8GO7a3ThdBftzWlO0eZ5vpm95sv1y2L2uMwNkXjIeWmJJsw0uiINWMnqxjSidpIL42hNGieAGi6xA6ahckLWTNISoBba4JpO0f24dhf8997GQW39PvTpoiIUVxWRZcUSBSNlgo8xWKd2If0efhUGdWhNpdbUoTV1ai0pd6PSWmv_cSExlJzTP361aXE</recordid><startdate>20190901</startdate><enddate>20190901</enddate><creator>Qureshi, Syed Arbaaz</creator><creator>Saha, Sriparna</creator><creator>Hasanuzzaman, Mohammed</creator><creator>Dias, Gael</creator><creator>Cambria, Erik</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>E3H</scope><scope>F2A</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20190901</creationdate><title>Multitask Representation Learning for Multimodal Estimation of Depression Level</title><author>Qureshi, Syed Arbaaz ; Saha, Sriparna ; Hasanuzzaman, Mohammed ; Dias, Gael ; Cambria, Erik</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-56e2a24cda72d0e94bdcd8bf958cf3b2df803c591f04a07f89b493600b8ac1b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Affective computing</topic><topic>Depression</topic><topic>Estimation</topic><topic>Learning systems</topic><topic>Medical conditions</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Qureshi, Syed Arbaaz</creatorcontrib><creatorcontrib>Saha, Sriparna</creatorcontrib><creatorcontrib>Hasanuzzaman, Mohammed</creatorcontrib><creatorcontrib>Dias, Gael</creatorcontrib><creatorcontrib>Cambria, Erik</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Library &amp; Information Sciences Abstracts (LISA)</collection><collection>Library &amp; Information Science Abstracts (LISA)</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE intelligent systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Qureshi, Syed Arbaaz</au><au>Saha, Sriparna</au><au>Hasanuzzaman, Mohammed</au><au>Dias, Gael</au><au>Cambria, Erik</au><au>Erik Cambria</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multitask Representation Learning for Multimodal Estimation of Depression Level</atitle><jtitle>IEEE intelligent systems</jtitle><stitle>MIS</stitle><date>2019-09-01</date><risdate>2019</risdate><volume>34</volume><issue>5</issue><spage>45</spage><epage>52</epage><pages>45-52</pages><issn>1541-1672</issn><eissn>1941-1294</eissn><coden>IISYF7</coden><abstract>We propose a novel multitask learning attention -based deep neural network model, which facilitates the fusion of various modalities. In particular, we use this network to both regress and classify the level of depression. Acoustic, textual, and visual modalities have been used to train our proposed network. Various experiments have been carried out on the benchmark dataset, namely, Distress Analysis Interview Corpus -a Wizard of Oz. From the results, we empirically justify that a) multitask learning networks cotrained over regression and classification have better performance compared to single -task networks, and b) the fusion of all the modalities helps in giving the most accurate estimation of depression with respect to regression.</abstract><cop>Los Alamitos</cop><pub>IEEE</pub><doi>10.1109/MIS.2019.2925204</doi><tpages>8</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1541-1672
ispartof IEEE intelligent systems, 2019-09, Vol.34 (5), p.45-52
issn 1541-1672
1941-1294
language eng
recordid cdi_crossref_primary_10_1109_MIS_2019_2925204
source IEEE Electronic Library (IEL)
subjects Affective computing
Depression
Estimation
Learning systems
Medical conditions
title Multitask Representation Learning for Multimodal Estimation of Depression Level
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T04%3A50%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multitask%20Representation%20Learning%20for%20Multimodal%20Estimation%20of%20Depression%20Level&rft.jtitle=IEEE%20intelligent%20systems&rft.au=Qureshi,%20Syed%20Arbaaz&rft.date=2019-09-01&rft.volume=34&rft.issue=5&rft.spage=45&rft.epage=52&rft.pages=45-52&rft.issn=1541-1672&rft.eissn=1941-1294&rft.coden=IISYF7&rft_id=info:doi/10.1109/MIS.2019.2925204&rft_dat=%3Cproquest_RIE%3E2317729674%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2317729674&rft_id=info:pmid/&rft_ieee_id=8910655&rfr_iscdi=true