Human Action Recognition From Various Data Modalities: A Review

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 3; pp. 3200 - 3225
• Main Authors: Sun, Zehua, Ke, Qiuhong, Rahmani, Hossein, Bennamoun, Mohammed, Wang, Gang, Liu, Jun
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Algorithms; Computer vision; data modality; Deep learning; Feature extraction; Human action recognition; Human Activities; Human activity recognition; Human motion; Humans; Machine learning; multi-modality; Optical imaging; Pattern Recognition, Automated - methods; Radar; single modality; Skeleton; Teaching methods; Three-dimensional displays; Visualization
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2022.3183112

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 article, 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.