Conference paper Open Access

# ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO

Foteini Markatopoulou; Vasileios Mezaris; Ioannis Patras

### 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>Foteini Markatopoulou</dc:creator>
<dc:creator>Vasileios Mezaris</dc:creator>
<dc:creator>Ioannis Patras</dc:creator>
<dc:date>2016-09-25</dc:date>
<dc:description>In this paper we propose an online multi-task learning algorithm for video concept detection. In particular, we extend the Efficient Lifelong Learning Algorithm (ELLA) in the following ways: a) we solve the objective function of ELLA using quadratic programming instead of solving the Lasso problem, b) we add a new label-based constraint that considers concept correlations, c) we use linear SVMs as base learners instead of logistic regression. Experimental results show improvement over both the single-task learning methods typically used in this problem and the original ELLA algorithm.</dc:description>
<dc:identifier>https://zenodo.org/record/159241</dc:identifier>
<dc:identifier>10.1109/ICIP.2016.7532344</dc:identifier>
<dc:identifier>oai:zenodo.org:159241</dc:identifier>
<dc:relation>info:eu-repo/grantAgreement/EC/H2020/687786/</dc:relation>
<dc:relation>url:https://zenodo.org/communities/ecfunded</dc:relation>
<dc:relation>url:https://zenodo.org/communities/invid-h2020</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:subject>Concept detection</dc:subject>
<dc:subject>Video</dc:subject>
<dc:title>ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO</dc:title>
<dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
<dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>

149
118
views