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.
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
