CO2A – Contrastive Conditional domain Alignment

A novel unsupervised domain adaptation approach for action recognition from videos, inspired by recent literature on contrastive learning. It comprises a novel two-headed deep architecture that simultaneously adopts cross-entropy and contrastive losses from different network branches to robustly learn a target classifier.

This repository contains the official implementation for CO2A from Turrisi da Costa, V. G.; Zara, G.; Rota, P.; Santos, T. O.; Sebe, N.; Murino, V.; Ricci, E. - "Dual Contrastive Domain Adaptation for Video Action Recognition" in Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022.