Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019

TL;DR

This paper presents Baidu-UTS's winning approach for the EPIC-Kitchens Action Recognition Challenge, utilizing object detection features and a novel Gated Feature Aggregator to improve noun prediction accuracy in complex video data.

Contribution

Introduction of a Gated Feature Aggregator module that enhances interaction between clip and object features in 3D CNNs for action recognition.

Findings

Outperforms other methods on test sets

Effective handling of occlusions and motion blur

Improved noun prediction accuracy

Abstract

In this report, we present the Baidu-UTS submission to the EPIC-Kitchens Action Recognition Challenge in CVPR 2019. This is the winning solution to this challenge. In this task, the goal is to predict verbs, nouns, and actions from the vocabulary for each video segment. The EPIC-Kitchens dataset contains various small objects, intense motion blur, and occlusions. It is challenging to locate and recognize the object that an actor interacts with. To address these problems, we utilize object detection features to guide the training of 3D Convolutional Neural Networks (CNN), which can significantly improve the accuracy of noun prediction. Specifically, we introduce a Gated Feature Aggregator module to learn from the clip feature and the object feature. This module can strengthen the interaction between the two kinds of activations and avoid gradient exploding. Experimental results demonstrate our approach outperforms other methods on both seen and unseen test set.