NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

TL;DR

This paper introduces NTU RGB+D, a large-scale dataset with over 56,000 videos and 60 action classes for 3D human activity recognition, and proposes a new recurrent neural network for improved classification.

Contribution

The paper provides a comprehensive large-scale dataset for RGB+D action recognition and introduces a novel recurrent neural network architecture to model long-term temporal features.

Findings

Deep learning outperforms hand-crafted features on the dataset

The dataset enables cross-subject and cross-view evaluation

The proposed RNN improves action classification accuracy

Abstract

Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of training samples, distinct class labels, camera views and variety of subjects. In this paper we introduce a large-scale dataset for RGB+D human action recognition with more than 56 thousand video samples and 4 million frames, collected from 40 distinct subjects. Our dataset contains 60 different action classes including daily, mutual, and health-related actions. In addition, we propose a new recurrent neural network structure to model the long-term temporal correlation of the features for each body part, and utilize them for better action classification. Experimental results show the advantages of applying deep learning methods over state-of-the-art hand-crafted features on the suggested cross-subject and cross-view evaluation criteria for our dataset. The introduction of this large scale dataset will enable the community to apply, develop and adapt various data-hungry learning techniques for the task of depth-based and RGB+D-based human activity analysis.