Research Area:  Machine Learning
Human behavior recognition is a research hotspot in the field of computer vision. This paper introduces and analyzes the methods of human motion and behavior recognition in the field of video in recent years, describes the main ways to build the network and the methods to optimize the network parameters to improve the model recognition effect, as well as the commonly used data sets. At present, human behavior recognition still needs to be further studied, and there are still great challenges in accuracy, number of model parameters and calculation amount.
Keywords:  
Behavior recognition
Deep learning
Convolutional neural network
Computer vision
Author(s) Name:   Fang-Fang Hao; Jie Liu; Xiang-Di Chen
Journal name:  
Conferrence name:  2020 International Conference on Artificial Intelligence and Education (ICAIE)
Publisher name:  IEEE
DOI:  10.1109/ICAIE50891.2020.00012
Volume Information:  
Paper Link:   https://ieeexplore.ieee.org/abstract/document/9262481