200498
doi
10.5281/zenodo.200498
oai:zenodo.org:200498
user-moving-h2020
user-invid-h2020
user-eu
Anastasia Moumtzidou
Information Technologies Institute (ITI), CERTH
Damianos Galanopoulos
Information Technologies Institute (ITI), CERTH
Theodoros Mironidis
Information Technologies Institute (ITI), CERTH
Vagia Kaltsa
Information Technologies Institute (ITI), CERTH
Anastasia Ioannidou
Information Technologies Institute (ITI), CERTH
Spyridon Symeonidis
Information Technologies Institute (ITI), CERTH
Konstantinos Avgerinakis
Information Technologies Institute (ITI), CERTH
Stelios Andreadis
Information Technologies Institute (ITI), CERTH
Ilias Gialampoukidis
Information Technologies Institute (ITI), CERTH
Stefanos Vrochidis
Information Technologies Institute (ITI), CERTH
Alexia Briassouli
Information Technologies Institute (ITI), CERTH
Vasileios Mezaris
Information Technologies Institute (ITI), CERTH
Ioannis Kompatsiaris
Information Technologies Institute (ITI), CERTH
Ioannis Patras
Queen Mary University of London, Mile end Campus, UK
ITI-CERTH participation in TRECVID 2016
Foteini Markatopoulou
Information Technologies Institute (ITI), CERTH, Queen Mary University of London, Mile end Campus, UK
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Multimedia Event Detection (MED)
Ad-hoc Video Search (AVS)
Instance Search (INS)
Surveillance Event Detection (SED)
Kernel Kub class Discriminant Analysis method (KSDA)
Motion Boundary Activity Areas (MBAA)
VERGE
<p>This paper provides an overview of the runs submitted to TRECVID 2016 by ITI-CERTH. ITI-CERTH participated in the Ad-hoc Video Search (AVS), Multimedia Event Detection (MED), Instance Search (INS) and Surveillance Event Detection (SED) tasks. Our AVS task participation is based on a method that combines the linguistic analysis of the query and the concept-based annotation of video fragments. In the MED task, in 000Ex task we exploit the textual description of an event class in order retrieve related videos, without using positive samples. Furthermore, in 010Ex and 100Ex tasks, a kernel sub class version of our discriminant analysis method (KSDA) combined with a fast linear SVM is employed. The INS task is performed by employing VERGE, which is an interactive retrieval application that integrates retrieval functionalities that consider only visual information. For the SED task, we deploy a novel activity detection algorithm that is based on Motion Boundary Activity Areas (MBAA), dense trajectories, Fisher vectors and an overlapping sliding window.</p>
Zenodo
2016-11-30
info:eu-repo/semantics/conferencePaper
689329
user-moving-h2020
user-invid-h2020
user-eu
award_title=Training towards a society of data-savvy information professionals to enable open leadership innovation; award_number=693092; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/693092; funder_id=00k4n6c32; funder_name=European Commission;
1579541846.759767
9133278
md5:ff2eddf1592049a04951974503250ff6
https://zenodo.org/records/200498/files/ITI-CERTH_trecvid2016.pdf
public
isVersionOf
doi