Seven Basic Expression Recognition Using ResNet-18

We propose to use a ResNet-18 architecture that was pre-trained on the FER+ dataset for tackling the problem of affective behavior analysis in-the-wild (ABAW) for classification of the seven basic expressions, namely, neutral, anger, disgust, fear, happiness, sadness and surprise. As part of the sec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-07
Hauptverfasser: Singh, Satnam, Schicker, Doris
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Singh, Satnam
Schicker, Doris
description We propose to use a ResNet-18 architecture that was pre-trained on the FER+ dataset for tackling the problem of affective behavior analysis in-the-wild (ABAW) for classification of the seven basic expressions, namely, neutral, anger, disgust, fear, happiness, sadness and surprise. As part of the second workshop and competition on affective behavior analysis in-the-wild (ABAW2), a database consisting of 564 videos with around 2.8M frames is provided along with labels for these seven basic expressions. We resampled the dataset to counter class-imbalances by under-sampling the over-represented classes and over-sampling the under-represented classes along with class-wise weights. To avoid overfitting we performed data-augmentation and used L2 regularisation. Our classifier reaches an ABAW2 score of 0.4 and therefore exceeds the baseline results provided by the hosts of the competition.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2550479864</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2550479864</sourcerecordid><originalsourceid>FETCH-proquest_journals_25504798643</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwCk4tS81TcEoszkxWcK0oKEotLs7Mz1MISk3OT8_LLAGxQ4sz89KBIsV-qSW6hhY8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBUPtMPAxNzSwszEmDhVAJxqMzw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2550479864</pqid></control><display><type>article</type><title>Seven Basic Expression Recognition Using ResNet-18</title><source>Open Access: Freely Accessible Journals by multiple vendors</source><creator>Singh, Satnam ; Schicker, Doris</creator><creatorcontrib>Singh, Satnam ; Schicker, Doris</creatorcontrib><description>We propose to use a ResNet-18 architecture that was pre-trained on the FER+ dataset for tackling the problem of affective behavior analysis in-the-wild (ABAW) for classification of the seven basic expressions, namely, neutral, anger, disgust, fear, happiness, sadness and surprise. As part of the second workshop and competition on affective behavior analysis in-the-wild (ABAW2), a database consisting of 564 videos with around 2.8M frames is provided along with labels for these seven basic expressions. We resampled the dataset to counter class-imbalances by under-sampling the over-represented classes and over-sampling the under-represented classes along with class-wise weights. To avoid overfitting we performed data-augmentation and used L2 regularisation. Our classifier reaches an ABAW2 score of 0.4 and therefore exceeds the baseline results provided by the hosts of the competition.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Competition ; Datasets ; Regularization ; Sampling</subject><ispartof>arXiv.org, 2021-07</ispartof><rights>2021. 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><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Singh, Satnam</creatorcontrib><creatorcontrib>Schicker, Doris</creatorcontrib><title>Seven Basic Expression Recognition Using ResNet-18</title><title>arXiv.org</title><description>We propose to use a ResNet-18 architecture that was pre-trained on the FER+ dataset for tackling the problem of affective behavior analysis in-the-wild (ABAW) for classification of the seven basic expressions, namely, neutral, anger, disgust, fear, happiness, sadness and surprise. As part of the second workshop and competition on affective behavior analysis in-the-wild (ABAW2), a database consisting of 564 videos with around 2.8M frames is provided along with labels for these seven basic expressions. We resampled the dataset to counter class-imbalances by under-sampling the over-represented classes and over-sampling the under-represented classes along with class-wise weights. To avoid overfitting we performed data-augmentation and used L2 regularisation. Our classifier reaches an ABAW2 score of 0.4 and therefore exceeds the baseline results provided by the hosts of the competition.</description><subject>Competition</subject><subject>Datasets</subject><subject>Regularization</subject><subject>Sampling</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwCk4tS81TcEoszkxWcK0oKEotLs7Mz1MISk3OT8_LLAGxQ4sz89KBIsV-qSW6hhY8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBUPtMPAxNzSwszEmDhVAJxqMzw</recordid><startdate>20210709</startdate><enddate>20210709</enddate><creator>Singh, Satnam</creator><creator>Schicker, Doris</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>20210709</creationdate><title>Seven Basic Expression Recognition Using ResNet-18</title><author>Singh, Satnam ; Schicker, Doris</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25504798643</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Competition</topic><topic>Datasets</topic><topic>Regularization</topic><topic>Sampling</topic><toplevel>online_resources</toplevel><creatorcontrib>Singh, Satnam</creatorcontrib><creatorcontrib>Schicker, Doris</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>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>Engineering Database</collection><collection>Publicly Available Content Database</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>Singh, Satnam</au><au>Schicker, Doris</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Seven Basic Expression Recognition Using ResNet-18</atitle><jtitle>arXiv.org</jtitle><date>2021-07-09</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>We propose to use a ResNet-18 architecture that was pre-trained on the FER+ dataset for tackling the problem of affective behavior analysis in-the-wild (ABAW) for classification of the seven basic expressions, namely, neutral, anger, disgust, fear, happiness, sadness and surprise. As part of the second workshop and competition on affective behavior analysis in-the-wild (ABAW2), a database consisting of 564 videos with around 2.8M frames is provided along with labels for these seven basic expressions. We resampled the dataset to counter class-imbalances by under-sampling the over-represented classes and over-sampling the under-represented classes along with class-wise weights. To avoid overfitting we performed data-augmentation and used L2 regularisation. Our classifier reaches an ABAW2 score of 0.4 and therefore exceeds the baseline results provided by the hosts of the competition.</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, 2021-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2550479864
source Open Access: Freely Accessible Journals by multiple vendors
subjects Competition
Datasets
Regularization
Sampling
title Seven Basic Expression Recognition Using ResNet-18
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T15%3A16%3A30IST&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=Seven%20Basic%20Expression%20Recognition%20Using%20ResNet-18&rft.jtitle=arXiv.org&rft.au=Singh,%20Satnam&rft.date=2021-07-09&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2550479864%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2550479864&rft_id=info:pmid/&rfr_iscdi=true