ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting. (arXiv:2209.00065v1 [cs.CV])

Current self-supervised approaches for skeleton action representation
learning often focus on constrained scenarios, where videos and skeleton data
are recorded in laboratory settings. When dealing with estimated skeleton data
in real-world videos, such methods perform poorly due to the large variations
across subjects and camera viewpoints. To address this issue, we introduce ViA,
a novel View-Invariant Autoencoder for self-supervised skeleton action
representation learning. ViA leverages motion retargeting between different
human performers as a pretext task, in order to disentangle the …

arxiv learning representation representation learning