159241
doi
10.1109/ICIP.2016.7532344
oai:zenodo.org:159241
user-invid-h2020
user-eu
Vasileios Mezaris
Information Technologies Institute (ITI), CERTH
Ioannis Patras
Queen Mary University of London
ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO
Foteini Markatopoulou
Information Technologies Institute (ITI), CERTH, Queen Mary University of London
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Concept detection
Multi-task learning
Video
<p>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.</p>
Zenodo
2016-09-25
info:eu-repo/semantics/conferencePaper
653967
user-invid-h2020
user-eu
award_title=In Video Veritas – Verification of Social Media Video Content for the News Industry; award_number=687786; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/687786; funder_id=00k4n6c32; funder_name=European Commission;
1579533969.017807
632906
md5:2ea63812f644dee948985e9a549b2177
https://zenodo.org/records/159241/files/icip16_1_preprint.pdf
public