Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published March 16, 2022 | Version v1
Conference paper Open

Dual-Head Contrastive Domain Adaptation for Video Action Recognition

  • 1. University of Trento, Italy
  • 2. Universidade Federal do Espírito Santo
  • 3. University of Verona, Italy

Description

Unsupervised domain adaptation (UDA) methods have become very popular in computer vision. However, while several techniques have been proposed for images, much less attention has been devoted to videos. This paper introduces a novel UDA approach for action recognition from videos, inspired by recent literature on contrastive learning. In particular, we propose a novel two-headed deep architecture that simultaneously adopts cross-entropy and contrastive losses from different network branches to robustly learn a target classifier. Moreover, this work introduces a novel large-scale UDA dataset, Mixamo→Kinetics, which, to the best of our knowledge, is the first dataset that considers the domain shift arising when transferring knowledge from synthetic to real video sequences. Our extensive experimental evaluation conducted on three publicly available benchmarks and on our new Mixamo→Kinetics dataset demonstrate the effectiveness of our approach, which outperforms the current state-of-the-art methods. Code is available at https://github.com/vturrisi/CO2A.

Files

da_Costa_Dual-Head_Contrastive_Domain_Adaptation_for_Video_Action_Recognition_WACV_2022_paper (1).pdf

Additional details

Funding

AI4Media – A European Excellence Centre for Media, Society and Democracy 951911
European Commission