In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022. This task aims to adapt an action recognition model trained on a labeled source domain to an unlabeled target domain. To achieve this goal, we propose an action-aware domain adaptation framework that leverages the prior knowledge induced from the action recognition task during the adaptation. Specifically, we disentangle the source features into action-relevant features and action-irrelevant features using the learned action classifier and then align the target features with the action-relevant features. To further improve the action prediction performance, we exploit the verb-noun co-occurrence matrix to constrain and refine the action predictions. Our final submission achieved the first place in terms of top-1 action recognition accuracy.
@article{arxiv.2301.12436,
title = {Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022},
author = {Yi Cheng and Dongyun Lin and Fen Fang and Hao Xuan Woon and Qianli Xu and Ying Sun},
journal= {arXiv preprint arXiv:2301.12436},
year = {2023}
}