<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<identifier>8JMKD3MGPBW34M/3C92QTP</identifier>
		<repository>sid.inpe.br/sibgrapi/2012/07.10.00.53</repository>
		<lastupdate>2012:07.10.00.53.06 sid.inpe.br/banon/2001/03.30.15.38 jose.jgrimaldo@gmail.com</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2012/07.10.00.53.06</metadatarepository>
		<metadatalastupdate>2020:02.19.02.18.27 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2012}</metadatalastupdate>
		<citationkey>SilvaFoSchnOliv:2012:MuSpRe</citationkey>
		<title>Multi-Scale Spectral Residual Analysis to Speed up Image Object Detection</title>
		<format>DVD, On-line.</format>
		<year>2012</year>
		<numberoffiles>1</numberoffiles>
		<size>4541 KiB</size>
		<author>Silva Filho, José Grimaldo da,</author>
		<author>Schnitman, Leizer,</author>
		<author>Oliveira, Luciano Rebouças de,</author>
		<affiliation>Universidade Federal da Bahia</affiliation>
		<affiliation>Universidade Federal da Bahia</affiliation>
		<affiliation>Universidade Federal da Bahia</affiliation>
		<editor>Freitas, Carla Maria Dal Sasso,</editor>
		<editor>Sarkar, Sudeep,</editor>
		<editor>Scopigno, Roberto,</editor>
		<editor>Silva, Luciano,</editor>
		<e-mailaddress>jose.jgrimaldo@gmail.com</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 25 (SIBGRAPI)</conferencename>
		<conferencelocation>Ouro Preto</conferencelocation>
		<date>Aug. 22-25, 2012</date>
		<booktitle>Proceedings</booktitle>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<tertiarytype>Full Paper</tertiarytype>
		<transferableflag>1</transferableflag>
		<contenttype>External Contribution</contenttype>
		<keywords>multi-scale spectral residue, saliency, person detection.</keywords>
		<abstract>Accuracy in image object detection has been usually achieved at the expense of much computational load. Therefore a trade-off between detection performance and fast execution commonly represents the ultimate goal of an object detector in real life applications. In this present work, we propose a novel method toward that goal. The proposed method was grounded on a multi-scale spectral residual (MSR) analysis for saliency detection. Compared to a regular sliding window search over the images, in our experiments, MSR was able to reduce by 75% (in average) the number of windows to be evaluated by an object detector. The proposed method was thoroughly evaluated over a subset of LabelMe dataset (person images), improving detection performance in most cases.</abstract>
		<language>en</language>
		<targetfile>PID2440145.pdf</targetfile>
		<usergroup>jose.jgrimaldo@gmail.com</usergroup>
		<visibility>shown</visibility>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<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/2012/07.10.00.53</url>
	</metadata>
</metadatalist>