Refined Spatial Network for Human Action Recognition

Refined Spatial Network for Human Action Recognition

Effective video representation is a key ingredient in action recognition, but how to learn effective spatial features remains a fundamental and challenging task. The existing CNN-based methods apply low-resolution feature maps to get the high-level semantic labels. However, the slenderer spatial inf...

Full description

Bibliographic Details
Main Authors: Chunlei Wu, Haiwen Cao, Weishan Zhang, Leiquan Wang, Yiwei Wei, Zexin Peng
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Action recognition
encoder-decoder
spatial features
Online Access:https://ieeexplore.ieee.org/document/8788614/

Internet

https://ieeexplore.ieee.org/document/8788614/

Similar Items