Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021

TL;DR

This paper presents a novel approach for unsupervised domain adaptation in fine-grained action recognition on the EPIC-KITCHENS-100 dataset, leveraging hand-centric features and domain-adaptive hand detection to improve accuracy.

Contribution

It introduces a hand-centric feature learning method combined with a domain-adaptive hand detector for improved unsupervised domain adaptation in action recognition.

Findings

Achieved 1st place in top-1 action recognition accuracy in the challenge.

Utilized limited hand annotations to train a generalizable hand detector.

Enhanced recognition performance by focusing on hand-centric features.

Abstract

In this report, we present the technical details of our approach to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition. The EPIC-KITCHENS-100 dataset consists of daily kitchen activities focusing on the interaction between human hands and their surrounding objects. It is very challenging to accurately recognize these fine-grained activities, due to the presence of distracting objects and visually similar action classes, especially in the unlabelled target domain. Based on an existing method for video domain adaptation, i.e., TA3N, we propose to learn hand-centric features by leveraging the hand bounding box information for UDA on fine-grained action recognition. This helps reduce the distraction from background as well as facilitate the learning of domain-invariant features. To achieve high quality hand localization, we adopt an uncertainty-aware domain adaptation network, i.e., MEAA, to train a domain-adaptive hand detector, which only uses very limited hand bounding box annotations in the source domain but can generalize well to the unlabelled target domain. Our submission achieved the 1st place in terms of top-1 action recognition accuracy, using only RGB and optical flow modalities as input.