Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022

TL;DR

This paper describes a novel unsupervised domain adaptation framework for action recognition in videos, which disentangles features and uses verb-noun co-occurrence to improve accuracy, achieving first place in a challenge.

Contribution

It introduces an action-aware domain adaptation method that disentangles features and leverages verb-noun co-occurrence for improved action recognition in unlabeled target domains.

Findings

Achieved first place in the EPIC-KITCHENS-100 UDA Challenge.

Effective disentanglement of action-relevant and irrelevant features.

Improved action recognition accuracy through co-occurrence constraints.

Abstract

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.