A review of human action recognition algorithms based on graph neural networks
With the wide application of action recognition technology in the fields of risk monitoring and human-computer interaction,human action recognition based on video data has gradually become a new hotspot in the field of computer vision research.Due to the continuous improvement of graph neural network methods,deep learning methods based on graph neural network have been gradually applied to human bone data in recent years to improve the efficiency of human action recognition algorithms.Therefore,this paper introduces the related methods of human action recognition based on graph neural network,analyzes and summarizes them.Firstly,the development status of human action recognition algorithm based on graph convolutional network is introduced.Then the data sets commonly used in action recognition and their characteristics are proposed.Finally,the future research direction and trend are discussed.
万方数据
维普
