Conference paper Open Access
ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2021
Konstantinos Gkountakos; Damianos Galanopoulos; Despoina Touska; Konstantinos Ioannidis; Stefanos Vrochidis; Vasileios Mezaris; Ioannis Kompatsiaris
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
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.
| Name | Size | |
|---|---|---|
|
ITI_CERTH_TRECVID2021_zenodo.pdf
md5:b8d277582f110b2a66254ce0d485d28e |
585.4 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 15 | 15 |
| Downloads | 14 | 14 |
| Data volume | 8.2 MB | 8.2 MB |
| Unique views | 13 | 13 |
| Unique downloads | 13 | 13 |
- Publication date:
- March 1, 2022
- DOI:
-
- Keyword(s):
- Activity detection Activity recognition 3D-convolutional neural networks
- Grants:
-
European Commission:
-
PREVISION - Prediction and Visual Intelligence for Security Information (833115)
-
MIRROR - Migration-Related Risks caused by misconceptions of Opportunities and Requirement (832921)
- CONNEXIONs - InterCONnected NEXt-Generation Immersive IoT Platform of Crime and Terrorism DetectiON, PredictiON, InvestigatiON, and PreventiON Services (786731)
-
PREVISION - Prediction and Visual Intelligence for Security Information (833115)
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International