Login / Signup
Spatiotemporal information deep fusion network with frame attention mechanism for video action recognition.
Hongshi Ou
Jifeng Sun
Published in:
J. Electronic Imaging (2019)
Keyphrases
</>
action recognition
human actions
action classification
spatial temporal
bag of words
higher level
multimedia
video content
spatio temporal
real time
video streams
spatial and temporal
video frames
space time
body parts
visual data
static images