Multi‐stream 3D CNN structure for human action recognition trained by limited data

Multi‐stream 3D CNN structure for human action recognition trained by limited data

Here, the authors proposed a solution to improve the training performance in limited training data case for human action recognition. The authors proposed three different convolutional neural network (CNN) architectures for this purpose. At first, the authors generated four different channels of inf...

Full description

Bibliographic Details
Main Authors: Vahid Ashkani Chenarlogh, Farbod Razzazi
Format: Article
Language:English
Published: Wiley 2019-04-01
Series:IET Computer Vision
Subjects:
multistream 3D CNN structure
human action recognition
training performance
training data case
optical flows
vertical directions
Online Access:https://doi.org/10.1049/iet-cvi.2018.5088

Internet

https://doi.org/10.1049/iet-cvi.2018.5088

Similar Items