Published March 1, 2022 | Version v1
Conference paper Open

ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2021

Description

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.

Files

ITI_CERTH_TRECVID2021_zenodo.pdf

Files (585.4 kB)

Name Size Download all
md5:b8d277582f110b2a66254ce0d485d28e
585.4 kB Preview Download

Additional details

Funding

PREVISION – Prediction and Visual Intelligence for Security Information 833115
European Commission
MIRROR – Migration-Related Risks caused by misconceptions of Opportunities and Requirement 832921
European Commission
CONNEXIONs – InterCONnected NEXt-Generation Immersive IoT Platform of Crime and Terrorism DetectiON, PredictiON, InvestigatiON, and PreventiON Services 786731
European Commission