Multi-label Relation Modeling in Facial Action Units Detection

This paper describes an approach to the facial action units detections. The involved action units (AU) include AU1 (Inner Brow Raiser), AU2 (Outer Brow Raiser), AU4 (Brow Lowerer), AU6 (Cheek Raise), AU12 (Lip Corner Puller), AU15 (Lip Corner Depressor), AU20 (Lip Stretcher), and AU25 (Lip Part). Ou...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ji, Xianpeng, Ding, Yu, Li, Lincheng, Chen, Yu, Fan, Changjie
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Ji, Xianpeng
Ding, Yu
Li, Lincheng
Chen, Yu
Fan, Changjie
description This paper describes an approach to the facial action units detections. The involved action units (AU) include AU1 (Inner Brow Raiser), AU2 (Outer Brow Raiser), AU4 (Brow Lowerer), AU6 (Cheek Raise), AU12 (Lip Corner Puller), AU15 (Lip Corner Depressor), AU20 (Lip Stretcher), and AU25 (Lip Part). Our work relies on the dataset released by the FG-2020 Competition: Affective Behavior Analysis In-the-Wild (ABAW). The proposed method consists of the data preprocessing, the feature extraction and the AU classification. The data preprocessing includes the detection of face texture and landmarks. The texture static and landmark dynamic features are extracted through neural networks and then fused as the feature latent representation. Finally, the fused feature is taken as the initial hidden state of a recurrent neural network with a trainable lookup AU table. The output of the RNN is the results of AU classification. The detected accuracy is evaluated with 0.5$\times$accuracy + 0.5$\times$F1. Our method achieve 0.56 with the validation data that is specified by the organization committee.
doi_str_mv 10.48550/arxiv.2002.01105
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2002_01105</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2002_01105</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-9ad2df3c876aee2f629e8538673bff3f70e71eec0eb156cc30096ae7b1d28c513</originalsourceid><addsrcrecordid>eNotj81qAjEUhbPpomgfoCvzAjPeJOZnNoJo_QGlUOx6uJO5KYF0lHEU-_bV0dXhcD4OfIy9C8gnTmsYY3uNl1wCyByEAP3Kprtz6mKWsKLEvyhhFw8N3x1qSrH54bHhS_QRE5_5fvluYnfiC-qo70P2EjCd6O2ZA7Zffuzn62z7udrMZ9sMjdVZgbWsg_LOGiSSwciCnFbOWFWFoIIFsoLIA1VCG-8VQHEjbSVq6bwWasBGj9teoDy28Rfbv_IuUvYi6h80vULm</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Multi-label Relation Modeling in Facial Action Units Detection</title><source>arXiv.org</source><creator>Ji, Xianpeng ; Ding, Yu ; Li, Lincheng ; Chen, Yu ; Fan, Changjie</creator><creatorcontrib>Ji, Xianpeng ; Ding, Yu ; Li, Lincheng ; Chen, Yu ; Fan, Changjie</creatorcontrib><description>This paper describes an approach to the facial action units detections. The involved action units (AU) include AU1 (Inner Brow Raiser), AU2 (Outer Brow Raiser), AU4 (Brow Lowerer), AU6 (Cheek Raise), AU12 (Lip Corner Puller), AU15 (Lip Corner Depressor), AU20 (Lip Stretcher), and AU25 (Lip Part). Our work relies on the dataset released by the FG-2020 Competition: Affective Behavior Analysis In-the-Wild (ABAW). The proposed method consists of the data preprocessing, the feature extraction and the AU classification. The data preprocessing includes the detection of face texture and landmarks. The texture static and landmark dynamic features are extracted through neural networks and then fused as the feature latent representation. Finally, the fused feature is taken as the initial hidden state of a recurrent neural network with a trainable lookup AU table. The output of the RNN is the results of AU classification. The detected accuracy is evaluated with 0.5$\times$accuracy + 0.5$\times$F1. Our method achieve 0.56 with the validation data that is specified by the organization committee.</description><identifier>DOI: 10.48550/arxiv.2002.01105</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2020-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2002.01105$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2002.01105$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ji, Xianpeng</creatorcontrib><creatorcontrib>Ding, Yu</creatorcontrib><creatorcontrib>Li, Lincheng</creatorcontrib><creatorcontrib>Chen, Yu</creatorcontrib><creatorcontrib>Fan, Changjie</creatorcontrib><title>Multi-label Relation Modeling in Facial Action Units Detection</title><description>This paper describes an approach to the facial action units detections. The involved action units (AU) include AU1 (Inner Brow Raiser), AU2 (Outer Brow Raiser), AU4 (Brow Lowerer), AU6 (Cheek Raise), AU12 (Lip Corner Puller), AU15 (Lip Corner Depressor), AU20 (Lip Stretcher), and AU25 (Lip Part). Our work relies on the dataset released by the FG-2020 Competition: Affective Behavior Analysis In-the-Wild (ABAW). The proposed method consists of the data preprocessing, the feature extraction and the AU classification. The data preprocessing includes the detection of face texture and landmarks. The texture static and landmark dynamic features are extracted through neural networks and then fused as the feature latent representation. Finally, the fused feature is taken as the initial hidden state of a recurrent neural network with a trainable lookup AU table. The output of the RNN is the results of AU classification. The detected accuracy is evaluated with 0.5$\times$accuracy + 0.5$\times$F1. Our method achieve 0.56 with the validation data that is specified by the organization committee.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81qAjEUhbPpomgfoCvzAjPeJOZnNoJo_QGlUOx6uJO5KYF0lHEU-_bV0dXhcD4OfIy9C8gnTmsYY3uNl1wCyByEAP3Kprtz6mKWsKLEvyhhFw8N3x1qSrH54bHhS_QRE5_5fvluYnfiC-qo70P2EjCd6O2ZA7Zffuzn62z7udrMZ9sMjdVZgbWsg_LOGiSSwciCnFbOWFWFoIIFsoLIA1VCG-8VQHEjbSVq6bwWasBGj9teoDy28Rfbv_IuUvYi6h80vULm</recordid><startdate>20200203</startdate><enddate>20200203</enddate><creator>Ji, Xianpeng</creator><creator>Ding, Yu</creator><creator>Li, Lincheng</creator><creator>Chen, Yu</creator><creator>Fan, Changjie</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200203</creationdate><title>Multi-label Relation Modeling in Facial Action Units Detection</title><author>Ji, Xianpeng ; Ding, Yu ; Li, Lincheng ; Chen, Yu ; Fan, Changjie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-9ad2df3c876aee2f629e8538673bff3f70e71eec0eb156cc30096ae7b1d28c513</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Ji, Xianpeng</creatorcontrib><creatorcontrib>Ding, Yu</creatorcontrib><creatorcontrib>Li, Lincheng</creatorcontrib><creatorcontrib>Chen, Yu</creatorcontrib><creatorcontrib>Fan, Changjie</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ji, Xianpeng</au><au>Ding, Yu</au><au>Li, Lincheng</au><au>Chen, Yu</au><au>Fan, Changjie</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-label Relation Modeling in Facial Action Units Detection</atitle><date>2020-02-03</date><risdate>2020</risdate><abstract>This paper describes an approach to the facial action units detections. The involved action units (AU) include AU1 (Inner Brow Raiser), AU2 (Outer Brow Raiser), AU4 (Brow Lowerer), AU6 (Cheek Raise), AU12 (Lip Corner Puller), AU15 (Lip Corner Depressor), AU20 (Lip Stretcher), and AU25 (Lip Part). Our work relies on the dataset released by the FG-2020 Competition: Affective Behavior Analysis In-the-Wild (ABAW). The proposed method consists of the data preprocessing, the feature extraction and the AU classification. The data preprocessing includes the detection of face texture and landmarks. The texture static and landmark dynamic features are extracted through neural networks and then fused as the feature latent representation. Finally, the fused feature is taken as the initial hidden state of a recurrent neural network with a trainable lookup AU table. The output of the RNN is the results of AU classification. The detected accuracy is evaluated with 0.5$\times$accuracy + 0.5$\times$F1. Our method achieve 0.56 with the validation data that is specified by the organization committee.</abstract><doi>10.48550/arxiv.2002.01105</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2002.01105
ispartof
issn
language eng
recordid cdi_arxiv_primary_2002_01105
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Multi-label Relation Modeling in Facial Action Units Detection
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T08%3A17%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multi-label%20Relation%20Modeling%20in%20Facial%20Action%20Units%20Detection&rft.au=Ji,%20Xianpeng&rft.date=2020-02-03&rft_id=info:doi/10.48550/arxiv.2002.01105&rft_dat=%3Carxiv_GOX%3E2002_01105%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true