Login / Signup
Masked Motion Encoding for Self-Supervised Video Representation Learning.
Xinyu Sun
Peihao Chen
Liangwei Chen
Changhao Li
Thomas H. Li
Mingkui Tan
Chuang Gan
Published in:
CVPR (2023)
Keyphrases
</>
video representation
prior knowledge
image sequences
object recognition
spatial and temporal
motion patterns
optical flow
co occurrence
feature points
generative model
spatial information
temporal information
video surveillance