R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition

R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition

Two-stream network architecture has the ability to capture temporal and spatial features from videos simultaneously and has achieved excellent performance on video action recognition tasks. However, there is a fair amount of redundant information in both temporal and spatial dimensions in videos, wh...

Full description

Bibliographic Details
Main Authors: Quanle Liu, Xiangjiu Che, Mei Bie
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Action recognition
convolutional neural network
attention mechanism
two-stream architecture
Online Access:https://ieeexplore.ieee.org/document/8740848/

Internet

https://ieeexplore.ieee.org/document/8740848/

Similar Items