Konstantinos Gkountakos
Damianos Galanopoulos
Despoina Touska
Konstantinos Ioannidis
Stefanos Vrochidis
Vasileios Mezaris
Ioannis Kompatsiaris
2023-03-01
<p>This report presents the overview of the runs related to Ad-hoc Video Search (AVS) and Activities in Extended Video (ActEV) tasks on behalf of the ITI-CERTH team. Our participation in the AVS task is based on a cross-modal deep network architecture utilizing several textual and visual features. As part of the retrieval stage, a dual-softmax approach is utilized to revise the calculated text-video<br>
similarities. For the ActEV task, we adapt our framework to fit the new dataset and overcome the challenges of detecting and recognizing activities in a multi-label manner while experimenting with two separate activity classifiers.</p>
https://doi.org/10.5281/zenodo.7431865
oai:zenodo.org:7431865
eng
Zenodo
https://zenodo.org/communities/m4d
https://zenodo.org/communities/criteria101021866
https://zenodo.org/communities/eu
https://doi.org/10.5281/zenodo.7431864
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 2022
info:eu-repo/semantics/conferencePaper