Abstract
A video human action recognition algorithm based on 3D DenseNet-BC is proposed. The convolution operation is used to acquire the characteristics of human action in video. Based on the connection mode of DenseNet-BC, network level connection is obtained to acquire high-dimensional features, thus constructing 3D DenseNet-BC for human action recognition in video. Tests were carried out on the data sets KTH and UCF-101 respectively. The experimental results show that the constructed network structure has a good recognition effect in the video action recognition task.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
