Conference paper Open Access

ITI-CERTH participation in TRECVID 2020

Gkountakos, Konstantinos; Galanopoulos, Damianos; Mpakratsas, Marios; Touska, Despoina; Moumtzidou, Anastasia; Ioannidis, Konstantinos; Gialampoukidis, Ilias; Vrochidis, Stefanos; Mezaris, Vasileios; Kompatsiaris, Ioannis

This paper provides an overview of the runs submitted to TRECVID 2020 by ITI-CERTH. ITI-CERTH participated in the Ad-hoc Video Search (AVS), Disaster Scene Description and Indexing (DSDI) and Activities in Extended Video (ActEV) tasks. Our AVS task participation is based on an attention-based cross-modal deep network method for retrieving video shots relevant to ad-hoc textual queries. The DSDI task is performed by implementing a multi-label image classification model, trained on all humanly annotated images and estimating the final classes on averaging the predictions on the keyframes of the video shots. For the ActEV task, we deploy an object detection algorithm and then convert the individual detected objects to activities by following an object tracking technique in order to detect human and vehicle-related activities.

Files (2.8 MB)
Name Size
trecvid2020.pdf
md5:1814a4a07ce3e0856e03f3d71e9a62e5 		2.8 MB Download
104
27
views
downloads
All versions This version
Views 104104
Downloads 2727
Data volume 75.6 MB75.6 MB
Unique views 9393
Unique downloads 2626
More info on how stats are collected.
Indexed in
Publication date:
January 20, 2021
DOI:
10.5281/zenodo.4506490

Zenodo DOI Badge

DOI 

10.5281/zenodo.4506490

Markdown 

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4506490.svg)](https://doi.org/10.5281/zenodo.4506490)

reStructedText 

.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.4506490.svg
   :target: https://doi.org/10.5281/zenodo.4506490

HTML 

<a href="https://doi.org/10.5281/zenodo.4506490"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.4506490.svg" alt="DOI"></a>

Image URL 

https://zenodo.org/badge/DOI/10.5281/zenodo.4506490.svg

Target URL 

https://doi.org/10.5281/zenodo.4506490

Grants:
European Commission:
  • ReTV - Enhancing and Re-Purposing TV Content for Trans-Vector Engagement (780656)
  • PREVISION - Prediction and Visual Intelligence for Security Information (833115)
  • aqua3S - Enhancing Standardisation strategies to integrate innovative technologies for Safety and Security in existing water networks (832876)
  • CONNEXIONs - InterCONnected NEXt-Generation Immersive IoT Platform of Crime and Terrorism DetectiON, PredictiON, InvestigatiON, and PreventiON Services (786731)
Meeting:
TRECVID 2020 Workshop, 2020
Communities:
License (for files):
Creative Commons Attribution 4.0 International

Versions

Version 1 10.5281/zenodo.4506490 Jan 20, 2021
Cite all versions? You can cite all versions by using the DOI 10.5281/zenodo.4506489. This DOI represents all versions, and will always resolve to the latest one. Read more.

Share

Cite as

Export