Sign in
SOR-TC: Self-attentive octave ResNet with temporal consistency for compressed video action recognition.
Junsan Zhang
Xiaomin Wang
Yao Wan
Leiquan Wang
Jian Wang
Philip S. Yu
Published in:
Neurocomputing (2023)
Keyphrases
</>
temporal consistency
compressed video
action recognition
video streams
super resolution
human actions
human detection
video content
activity recognition
bitstream
video frames
computer vision
body parts
visual attention
object detection
frequency domain
high resolution
multiscale