TY - GEN
T1 - ITI-CERTH participation in TRECVID 2016
AU - Markatopoulou, Foteini
AU - Moumtzidou, Anastasia
AU - Galanopoulos, D
AU - Mironidis, T
AU - Kaltsa, V
AU - Ioannidou, A
AU - Symeonidis, S
AU - Avgerinakis, K
AU - Andreadis, S
AU - Gialampoukidis, I
AU - Vrochidis, S
AU - Briassouli, Alexia
AU - Mezaris, V
AU - Kompatsiaris, I
AU - Patras, I
PY - 2016
Y1 - 2016
N2 - 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.
AB - 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.
M3 - Conference article in proceeding
BT - Proceedings TRECVID 2016 Workshop
ER -