Conference paper Open Access

ITI-CERTH participation in TRECVID 2019

Konstantinos Gkountakos; Konstantinos Ioannidis; Stefanos Vrochidis; Ioannis Kompatsiaris


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Konstantinos Gkountakos</dc:creator>
  <dc:creator>Konstantinos Ioannidis</dc:creator>
  <dc:creator>Stefanos Vrochidis</dc:creator>
  <dc:creator>Ioannis Kompatsiaris</dc:creator>
  <dc:date>2020-03-01</dc:date>
  <dc:description>In this work, an overview of the submitted run to TRECVID 2019 by ITI-CERTH is presented and more specifically, for the task of Activities in Extended Video (ActEV). Towards this objective, we deployed a state-of-the-art architecture for the human action recognition problem and with the application of an encoder-decoder model, we extract a threshold for every activity in order for the framework not only to recognize activities but also to identify them in extended videos.</dc:description>
  <dc:identifier>https://zenodo.org/record/4452098</dc:identifier>
  <dc:identifier>10.5281/zenodo.4452098</dc:identifier>
  <dc:identifier>oai:zenodo.org:4452098</dc:identifier>
  <dc:language>eng</dc:language>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/700475/</dc:relation>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/779962/</dc:relation>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/740593/</dc:relation>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/786731/</dc:relation>
  <dc:relation>doi:10.5281/zenodo.4452097</dc:relation>
  <dc:relation>url:https://zenodo.org/communities/connexions-h2020</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:title>ITI-CERTH participation in TRECVID 2019</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>
130
44
views
downloads
All versions This version
Views 130130
Downloads 4444
Data volume 58.5 MB58.5 MB
Unique views 106106
Unique downloads 3838

Share

Cite as