Login / Signup
Cross-view motion consistent self-supervised video inter-intra contrastive for action representation understanding.
Shuai Bi
Zhengping Hu
Hehao Zhang
Jirui Di
Zhe Sun
Published in:
Neural Networks (2024)
Keyphrases
</>
recognizing human actions
action recognition
human actions
cross view
space time
video sequences
motion estimation
similarity search
video streams
visual data
image sequences
image representation
optical flow
key frames
video data
dynamic scenes
reference frame
visual cues
similarity measure