Facial Action Unit Recognition With Multi-models Ensembling

Facial Action Unit Recognition With Multi-models Ensembling

The Affective Behavior Analysis in-the-wild (ABAW) 2022 Competition gives Affective Computing a large promotion. In this paper, we present our method of AU challenge in this Competition. We use improved IResnet100 as backbone. Then we train AU dataset in Aff-Wild2 on three pertained models pretraine...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-03
Hauptverfasser: Jiang, Wenqiang, Wu, Yannan, Qiao, Fengsheng, Meng, Liyu, Deng, Yuanyuan, Liu, Chuanhe
Format: Artikel
Sprache:eng
Schlagworte:
Affective computing
Competition
Datasets
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 Jiang, Wenqiang
Wu, Yannan
Qiao, Fengsheng
Meng, Liyu
Deng, Yuanyuan
Liu, Chuanhe
description The Affective Behavior Analysis in-the-wild (ABAW) 2022 Competition gives Affective Computing a large promotion. In this paper, we present our method of AU challenge in this Competition. We use improved IResnet100 as backbone. Then we train AU dataset in Aff-Wild2 on three pertained models pretrained by our private au and expression dataset, and Glint360K respectively. Finally, we ensemble the results of our models. We achieved F1 score (macro) 0.731 on AU validation set.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2643125467</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2643125467</sourcerecordid><originalsourceid>FETCH-proquest_journals_26431254673</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdktMzkzMUXBMLsnMz1MIzcssUQhKTc5PBzJAAuGZJRkKvqU5JZm6ufkpqTnFCq55xam5STmZeek8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvZGZibGhkamJmbkycKgDSRDbr</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2643125467</pqid></control><display><type>article</type><title>Facial Action Unit Recognition With Multi-models Ensembling</title><source>Free E- Journals</source><creator>Jiang, Wenqiang ; Wu, Yannan ; Qiao, Fengsheng ; Meng, Liyu ; Deng, Yuanyuan ; Liu, Chuanhe</creator><creatorcontrib>Jiang, Wenqiang ; Wu, Yannan ; Qiao, Fengsheng ; Meng, Liyu ; Deng, Yuanyuan ; Liu, Chuanhe</creatorcontrib><description>The Affective Behavior Analysis in-the-wild (ABAW) 2022 Competition gives Affective Computing a large promotion. In this paper, we present our method of AU challenge in this Competition. We use improved IResnet100 as backbone. Then we train AU dataset in Aff-Wild2 on three pertained models pretrained by our private au and expression dataset, and Glint360K respectively. Finally, we ensemble the results of our models. We achieved F1 score (macro) 0.731 on AU validation set.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Affective computing ; Competition ; Datasets</subject><ispartof>arXiv.org, 2022-03</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>780,784</link.rule.ids></links><search><creatorcontrib>Jiang, Wenqiang</creatorcontrib><creatorcontrib>Wu, Yannan</creatorcontrib><creatorcontrib>Qiao, Fengsheng</creatorcontrib><creatorcontrib>Meng, Liyu</creatorcontrib><creatorcontrib>Deng, Yuanyuan</creatorcontrib><creatorcontrib>Liu, Chuanhe</creatorcontrib><title>Facial Action Unit Recognition With Multi-models Ensembling</title><title>arXiv.org</title><description>The Affective Behavior Analysis in-the-wild (ABAW) 2022 Competition gives Affective Computing a large promotion. In this paper, we present our method of AU challenge in this Competition. We use improved IResnet100 as backbone. Then we train AU dataset in Aff-Wild2 on three pertained models pretrained by our private au and expression dataset, and Glint360K respectively. Finally, we ensemble the results of our models. We achieved F1 score (macro) 0.731 on AU validation set.</description><subject>Affective computing</subject><subject>Competition</subject><subject>Datasets</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdktMzkzMUXBMLsnMz1MIzcssUQhKTc5PBzJAAuGZJRkKvqU5JZm6ufkpqTnFCq55xam5STmZeek8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvZGZibGhkamJmbkycKgDSRDbr</recordid><startdate>20220324</startdate><enddate>20220324</enddate><creator>Jiang, Wenqiang</creator><creator>Wu, Yannan</creator><creator>Qiao, Fengsheng</creator><creator>Meng, Liyu</creator><creator>Deng, Yuanyuan</creator><creator>Liu, Chuanhe</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>20220324</creationdate><title>Facial Action Unit Recognition With Multi-models Ensembling</title><author>Jiang, Wenqiang ; Wu, Yannan ; Qiao, Fengsheng ; Meng, Liyu ; Deng, Yuanyuan ; Liu, Chuanhe</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26431254673</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Affective computing</topic><topic>Competition</topic><topic>Datasets</topic><toplevel>online_resources</toplevel><creatorcontrib>Jiang, Wenqiang</creatorcontrib><creatorcontrib>Wu, Yannan</creatorcontrib><creatorcontrib>Qiao, Fengsheng</creatorcontrib><creatorcontrib>Meng, Liyu</creatorcontrib><creatorcontrib>Deng, Yuanyuan</creatorcontrib><creatorcontrib>Liu, Chuanhe</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</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>Jiang, Wenqiang</au><au>Wu, Yannan</au><au>Qiao, Fengsheng</au><au>Meng, Liyu</au><au>Deng, Yuanyuan</au><au>Liu, Chuanhe</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Facial Action Unit Recognition With Multi-models Ensembling</atitle><jtitle>arXiv.org</jtitle><date>2022-03-24</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>The Affective Behavior Analysis in-the-wild (ABAW) 2022 Competition gives Affective Computing a large promotion. In this paper, we present our method of AU challenge in this Competition. We use improved IResnet100 as backbone. Then we train AU dataset in Aff-Wild2 on three pertained models pretrained by our private au and expression dataset, and Glint360K respectively. Finally, we ensemble the results of our models. We achieved F1 score (macro) 0.731 on AU validation set.</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, 2022-03
issn 2331-8422
language eng
recordid cdi_proquest_journals_2643125467
source Free E- Journals
subjects Affective computing
Competition
Datasets
title Facial Action Unit Recognition With Multi-models Ensembling
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T14%3A23%3A28IST&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=Facial%20Action%20Unit%20Recognition%20With%20Multi-models%20Ensembling&rft.jtitle=arXiv.org&rft.au=Jiang,%20Wenqiang&rft.date=2022-03-24&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2643125467%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2643125467&rft_id=info:pmid/&rfr_iscdi=true