Self-supervised Video Representation Learning by Context and Motion Decoupling.

Lianghua Huang Yu Liu Bin Wang Pan Pan Yinghui Xu Rong Jin

Published in: CoRR (2021)

Keyphrases

video representation
image sequences
prior knowledge
motion estimation
space time
motion analysis
multiscale
spatio temporal
generative model
camera motion
motion parameters
video analysis
video processing