publication . Article . Conference object . 2021

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;
Open Access
  • Published: 20 Jan 2021
  • Publisher: Zenodo
Abstract
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 algorit...
Subjects
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Funded by
EC| ReTV
Project
ReTV
Enhancing and Re-Purposing TV Content for Trans-Vector Engagement
  • Funder: European Commission (EC)
  • Project Code: 780656
  • Funding stream: H2020 | RIA
,
EC| CONNEXIONs
Project
CONNEXIONs
InterCONnected NEXt-Generation Immersive IoT Platform of Crime and Terrorism DetectiON, PredictiON, InvestigatiON, and PreventiON Services
  • Funder: European Commission (EC)
  • Project Code: 786731
  • Funding stream: H2020 | RIA
,
EC| aqua3S
Project
aqua3S
Enhancing Standardisation strategies to integrate innovative technologies for Safety and Security in existing water networks
  • Funder: European Commission (EC)
  • Project Code: 832876
  • Funding stream: H2020 | IA
Validated by funder
,
EC| PREVISION
Project
PREVISION
Prediction and Visual Intelligence for Security Information
  • Funder: European Commission (EC)
  • Project Code: 833115
  • Funding stream: H2020 | IA
Download fromView all 3 versions
Open Access
https://dx.doi.org/10.5281/zen...
Conference object . 2021
Provider: Datacite
Open Access
ZENODO
Conference object . 2021
Provider: ZENODO
Open Access
https://dx.doi.org/10.5281/zen...
Conference object . 2021
Provider: Datacite
Any information missing or wrong?Report an Issue