Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition.

Jinwoo Choi Chen Gao Joseph C. E. Messou Jia-Bin Huang

Published in: NeurIPS (2019)

Keyphrases

action recognition
learning algorithm
computer vision
bag of words
image classification
viewpoint
body parts
spatial temporal
human detection
static images
optical flow
input image
multi view
single image
three dimensional
activity recognition
scene classification
motion features