Konstantinos Gkountakos
Damianos Galanopoulos
Despoina Touska
Konstantinos Ioannidis
Stefanos Vrochidis
Vasileios Mezaris
Ioannis Kompatsiaris
2022-03-01
<p>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<br>
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.</p>
https://doi.org/10.5281/zenodo.5817708
oai:zenodo.org:5817708
eng
Zenodo
https://zenodo.org/communities/h2020-mirror-project
https://zenodo.org/communities/connexions-h2020
https://zenodo.org/communities/m4d
https://zenodo.org/communities/eu
https://doi.org/10.5281/zenodo.5817707
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Activity detection
Activity recognition
3D-convolutional neural networks
ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2021
info:eu-repo/semantics/conferencePaper