Sign in

Motion-aware Contrastive Video Representation Learning via Foreground-background Merging.

Shuangrui DingMaomao LiTianyu YangRui QianHaohang XuQingyi ChenJue WangHongkai Xiong
Published in: CVPR (2022)
Keyphrases
  • video representation
  • prior knowledge
  • moving objects
  • spatio temporal
  • space time
  • state space
  • motion estimation
  • camera motion
  • spatial and temporal
  • video analysis