Research Area:  Machine Learning

Abstract:

Human behavior recognition has always been a hot spot for research in computer vision. With the wide application of behavior recognition in virtual reality and short video in recent years and the rapid development of deep learning algorithms, behavior recognition algorithms based on deep learning have emerged. Compared with traditional methods, behavior recognition algorithms based on deep learning have the advantages of strong robustness and high accuracy. This paper systemizes and introduces behavior recognition algorithms based on deep learning proposed in recent years, then focuses on a series of behavior recognition algorithms based on image and bone data; deeply analyzes their theories and performance, and finally, puts forward further prospects.

Keywords:  
Behavior recognition
Deep learning
Skeleton data
Machine Learning
Deep Learning

Author(s) Name:  Kai Hu, Junlan Jin, Fei Zheng, Liguo Weng & Yiwu Ding

Publisher name:  Springer

DOI:  10.1007/s10462-022-10210-8

Volume Information:  

Paper Link:   https://link.springer.com/article/10.1007/s10462-022-10210-8