Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition

no code implementations • 19 Oct 2021 • Mirco Planamente, Chiara Plizzari, Emanuele Alberti, Barbara Caputo

First person action recognition is becoming an increasingly researched area thanks to the rising popularity of wearable cameras.

Action Recognition Domain Generalization +1

PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition

no code implementations • 1 Jul 2021 • Chiara Plizzari, Mirco Planamente, Emanuele Alberti, Barbara Caputo

In this report, we describe the technical details of our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition.

Action Recognition Domain Generalization +2

Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment

no code implementations • 3 Jun 2021 • Mirco Planamente, Chiara Plizzari, Emanuele Alberti, Barbara Caputo

First person action recognition is an increasingly researched topic because of the growing popularity of wearable cameras.

Action Recognition

IDDA: a large-scale multi-domain dataset for autonomous driving

no code implementations • 17 Apr 2020 • Emanuele Alberti, Antonio Tavera, Carlo Masone, Barbara Caputo

To support work in this direction, this paper contributes a new large scale, synthetic dataset for semantic segmentation with more than 100 different source visual domains.

Autonomous Driving Domain Adaptation +2