Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics.
Jiangliu WangJianbo JiaoLinchao BaoShengfeng HeYunhui LiuWei LiuPublished in: CVPR (2019)
Keyphrases
- spatio temporal
- video representation
- temporal domain
- learning process
- learning algorithm
- optical flow
- image sequences
- recognition of human actions
- spatial and temporal
- moving objects
- motion estimation
- static images
- space time
- motion model
- mobile robot
- motion analysis
- object motion
- temporal structure
- video sequences
- spatio temporal patterns
- perceptual information
- periodic motion
- reinforcement learning