Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition.

Ding Li Yongqiang Tang Zhizhong Zhang Wensheng Zhang

Published in: CoRR (2023)

Keyphrases

action recognition
data streams
computer vision
spatial temporal
activity recognition
human detection
learning algorithm
viewpoint
low level
bag of words
human actions
keywords
video dataset
recognition of human actions