<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>8JMKD3MGPEW34M/45CUNP8</identifier>
		<repository>sid.inpe.br/sibgrapi/2021/09.06.21.37</repository>
		<lastupdate>2021:09.06.21.37.12 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2021/09.06.21.37.12</metadatarepository>
		<metadatalastupdate>2022:06.14.00.00.32 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2021}</metadatalastupdate>
		<doi>10.1109/SIBGRAPI54419.2021.00042</doi>
		<citationkey>Schirmer:2021:SeGrAt</citationkey>
		<title>SGAT: Semantic Graph Attention for 3D human pose estimation</title>
		<format>On-line</format>
		<year>2021</year>
		<numberoffiles>1</numberoffiles>
		<size>26659 KiB</size>
		<author>Schirmer, Luiz,</author>
		<affiliation>PUC-Rio</affiliation>
		<editor>Paiva, Afonso ,</editor>
		<editor>Menotti, David ,</editor>
		<editor>Baranoski, Gladimir V. G. ,</editor>
		<editor>Proença, Hugo Pedro ,</editor>
		<editor>Junior, Antonio Lopes Apolinario ,</editor>
		<editor>Papa, João Paulo ,</editor>
		<editor>Pagliosa, Paulo ,</editor>
		<editor>dos Santos, Thiago Oliveira ,</editor>
		<editor>e Sá, Asla Medeiros ,</editor>
		<editor>da Silveira, Thiago Lopes Trugillo ,</editor>
		<editor>Brazil, Emilio Vital ,</editor>
		<editor>Ponti, Moacir A. ,</editor>
		<editor>Fernandes, Leandro A. F. ,</editor>
		<editor>Avila, Sandra,</editor>
		<e-mailaddress>schirmer.luizj@gmail.com</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 34 (SIBGRAPI)</conferencename>
		<conferencelocation>Gramado, RS, Brazil (virtual)</conferencelocation>
		<date>18-22 Oct. 2021</date>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Full Paper</tertiarytype>
		<transferableflag>1</transferableflag>
		<versiontype>finaldraft</versiontype>
		<keywords>Graph Neural Networks, Pose estimation, Animation, Motion Capture.</keywords>
		<abstract>We propose a novel gating mechanism applied to Semantic Graph Convolutions for 3D applications, named Semantic Graph Attention. Semantic Graph Convolutions learn to capture semantic information such as local and global node relationships, not explicitly represented in graphs. We improve their performance by proposing an attention block to explore channel-wise inter-dependencies. The proposed method performs the unprojection of the points 2d (image) in their 3D version (3d scene). We use it to estimate 3d human pose from 2d images. Both 2D and 3D human poses can be represented as structured graphs, and we explore their particularities in this context. The attention layer improves skeleton estimation accuracy using 58\% fewer parameters than state-of-the-art.</abstract>
		<language>en</language>
		<targetfile>Sibgrapi21_final.pdf</targetfile>
		<usergroup>schirmer.luizj@gmail.com</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPEW34M/45PQ3RS</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/4742MCS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2021/11.12.11.46 4</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2021/09.06.21.37</url>
	</metadata>
</metadatalist>