Fully convolutional networks for action recognition

Fully convolutional networks for action recognition

Human action recognition is an important and challenging topic in computer vision. Recently, convolutional neural networks (CNNs) have established impressive results for many image recognition tasks. The CNNs usually contain million parameters which prone to overfit when training on small datasets....

Full description

Bibliographic Details
Main Authors: Sheng Yu, Yun Cheng, Li Xie, Shao‐Zi Li
Format: Article
Language:English
Published: Wiley 2017-12-01
Series:IET Computer Vision
Subjects:
human action recognition
computer vision
convolutional neural networks
CNN
image recognition tasks
two-stream fully convolutional networks architecture
Online Access:https://doi.org/10.1049/iet-cvi.2017.0005

Internet

https://doi.org/10.1049/iet-cvi.2017.0005

Similar Items