Conference paper Open Access

ITI-CERTH participation in TRECVID 2019

Konstantinos Gkountakos; Konstantinos Ioannidis; Stefanos Vrochidis; Ioannis Kompatsiaris

In this work, an overview of the submitted run to TRECVID 2019 by ITI-CERTH is presented and more specifically, for the task of Activities in Extended Video (ActEV). Towards this objective, we deployed a state-of-the-art architecture for the human action recognition problem and with the application of an encoder-decoder model, we extract a threshold for every activity in order for the framework not only to recognize activities but also to identify them in extended videos.

Files (1.3 MB)
Name Size
ITI_CERTH_TRECVID2019v0.1.pdf
md5:d3001463b2f203401e9976f0d6c2447c
1.3 MB Download
113
42
views
downloads
All versions This version
Views 113113
Downloads 4242
Data volume 55.8 MB55.8 MB
Unique views 9292
Unique downloads 3636

Share

Cite as