IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos

Gyeongsik Moon
Gyeongsik Moon
Heeseung Kwon
Heeseung Kwon
Cited by: 0|Views18

Abstract:

Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting contextual information around humans, e.g., human appearance and scene category, they are easily fooled by out-of-context action videos where the contexts do not e...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments