<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<identifier>8JMKD3MGPBW34M/3EEGUEH</identifier>
		<repository>sid.inpe.br/sibgrapi/2013/07.11.03.52</repository>
		<metadatarepository>sid.inpe.br/sibgrapi/2013/07.11.03.52.12</metadatarepository>
		<site>sibgrapi.sid.inpe.br 802</site>
		<citationkey>MotaSouzAraúViei:2013:CoOrTe</citationkey>
		<author>Mota, Virgínia Fernandes,</author>
		<author>Souza, Jéssica Ione Conceição,</author>
		<author>Araújo, Arnaldo de Albuquerque,</author>
		<author>Vieira, Marcelo Bernardes,</author>
		<affiliation>Universidade Federal de Minas Gerais</affiliation>
		<affiliation>Universidade Federal de Minas Gerais</affiliation>
		<affiliation>Universidade Federal de Minas Gerais</affiliation>
		<affiliation>Universidade Federal de Juiz de Fora</affiliation>
		<title>Combining Orientation Tensors for Human Action Recognition</title>
		<conferencename>Conference on Graphics, Patterns and Images, 26 (SIBGRAPI)</conferencename>
		<year>2013</year>
		<editor>Boyer, Kim,</editor>
		<editor>Hirata, Nina,</editor>
		<editor>Nedel, Luciana,</editor>
		<editor>Silva, Claudio,</editor>
		<booktitle>Proceedings</booktitle>
		<date>Aug. 5-8, 2013</date>
		<publisheraddress>Los Alamitos</publisheraddress>
		<publisher>IEEE Computer Society</publisher>
		<conferencelocation>Arequipa, Peru</conferencelocation>
		<keywords>Histogram of gradients, Orientation tensor, Motion description, Human action recognition.</keywords>
		<abstract>This paper presents a new tensor motion descriptor based on histogram of oriented gradients. We model the temporal evolution of gradient distribution with orientation tensors in equally sized blocks throughout the video sequence. Subsequently, these blocks are concatenated to create the final descriptor. Using a SVM classifier, even without any bag-of-feature based approach, our method achieves recognition rates greater than those found by other HOG techniques on KTH dataset and a competitive recognition rate for UCF11 and Hollywood2 datasets.</abstract>
		<language>en</language>
		<tertiarytype>Full Paper</tertiarytype>
		<format>On-line.</format>
		<size>1080 KiB</size>
		<numberoffiles>1</numberoffiles>
		<targetfile>paper_mota_114911.pdf</targetfile>
		<lastupdate>2013:07.11.03.52.12 sid.inpe.br/banon/2001/03.30.15.38 virginiafernandesmota@gmail.com</lastupdate>
		<metadatalastupdate>2020:02.19.03.09.22 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2013}</metadatalastupdate>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<e-mailaddress>virginiafernandesmota@gmail.com</e-mailaddress>
		<usergroup>virginiafernandesmota@gmail.com</usergroup>
		<visibility>shown</visibility>
		<transferableflag>1</transferableflag>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<contenttype>External Contribution</contenttype>
		<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/2013/07.11.03.52</url>
	</metadata>
</metadatalist>