Beyond Two-stream: Skeleton-based Three-stream Networks for Action Recognition in Videos.

Jianfeng Xu Kazuyuki Tasaka Hiromasa Yanagihara

Published in: ICPR (2018)

Keyphrases

data streams
real time
data sets
sliding window
stream processing
database systems
feature extraction
reinforcement learning
object recognition
human computer interaction
action recognition
streaming data
network design
action recognition in videos