Human Action Recognition from Various Data Modalities: A Review
This is a review paper summarizing existing work for researchers in computer vision interested in Human Action Recognition.
This paper reviews recent progress in deep learning methods for Human Action Recognition (HAR) across various data modalities like RGB, skeleton, and depth. It surveys mainstream deep learning approaches for single and multiple data modalities, including fusion-based and co-learning-based frameworks, and presents comparative results on benchmark datasets.
Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this paper, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions.