A Comprehensive Survey of Vision-Based Human Action Recognition Methods

By Hongbo Zhang, Yi-Xiang Zhang, Bineng Zhong, Qing Lei, Lijie Yang, Jixiang Du, Duansheng Chen. Italian National Conference on Sensors, 2019

483 citations recorded by the source corpus.

Although widely used in many applications, accurate and efficient human action recognition remains a challenging area of research in the field of computer vision. Most recent surveys have focused on narrow problems such as human action recognition methods using depth data, 3D-skeleton data, still image data, spatiotemporal interest point-based methods, and human walking motion recognition. However, there has been no systematic survey of human action recognition. To this end, we present a thorough review of human action recognition methods and provide a comprehensive overview of recent approaches in human action recognition research, including progress in hand-designed action features in RGB and depth data, current deep learning-based action feature representation methods, advances in human–object interaction recognition methods, and the current prominent research topic of action detection methods. Finally, we present several analysis recommendations for researchers. This survey paper provides an essential reference for those interested in further research on human action recognition.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/c0e55d740d07b16a50b5eb491117b92965d315c9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Jun Liu
2. Qiuhong Ke
3. Hossein Rahmani
4. Zehua Sun
5. Matteo Matteucci
6. Chiara Plizzari
7. Marco Cannici
8. Sergey I. Nikolenko

In Computer Vision and Pattern Recognition

1. Qiuhong Ke
2. Jun Liu
3. Hossein Rahmani
4. Zehua Sun
5. Chiara Plizzari
6. Matteo Matteucci
7. Marco Cannici
8. Sergey I. Nikolenko

In Human-Computer Interaction

1. Jun Liu
2. Qiuhong Ke
3. Matteo Matteucci
4. Sergey I. Nikolenko
5. Hossein Rahmani
6. Chiara Plizzari
7. Zehua Sun
8. Marco Cannici

Citations in the corpus

• Spatial Temporal Transformer Network for Skeleton-based Action Recognition (2020, background): “Nevertheless, several aspects of skeleton-based action recognition still remain open [5]–[7].”
• Synthetic Data for Deep Learning (2019, background): “Moving from still images to videos, we begin with human action recognition [460, 688].”
• Human Action Recognition From Various Data Modalities: A Review (2020, background): “[26] presented a comprehensive survey of human action analysis, including recognition, interaction, and detection.”
• Skeleton-based action recognition via spatial and temporal transformer networks (2020, background): “Nevertheless, several aspects of skeleton-based action recognition still remain open (Zhang et al. (2019); Aggarwal and Ryoo (2011); Ren et al. (2020)).”