Conference paper Open Access

ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2021

Konstantinos Gkountakos; Damianos Galanopoulos; Despoina Touska; Konstantinos Ioannidis; Stefanos Vrochidis; Vasileios Mezaris; Ioannis Kompatsiaris

In this report, the overview of the runs during the TRECVID 2021 by the ITI-CERTH team are presented. ITI-CERTH participated in the Ad-hoc Video Search (AVS) and Activities in Extended Video (ActEV) tasks. For the AVS task, our participation is based on an attention-based cross-modal deep network architecture. As part of training this architecture, we experimented with a new hard negative
mining approach. For the ActEV task, we improve our framework, in terms of more accurate performance, by addressing the classification problem as multi-label rather than a single-label.

Files (585.4 kB)
Name Size
585.4 kB Download
All versions This version
Views 9999
Downloads 5757
Data volume 33.4 MB33.4 MB
Unique views 7474
Unique downloads 5454


Cite as