View-Invariant Deep Architecture for Human Action Recognition Using Two-Stream Motion and Shape Temporal Dynamics.
Chhavi DhimanDinesh Kumar VishwakarmaPublished in: IEEE Trans. Image Process. (2020)
Keyphrases
- view invariant
- action recognition
- human motion
- human motion analysis
- single view
- multi view
- human actions
- arbitrary viewpoint
- shape model
- data streams
- motion estimation
- space time
- image sequences
- optical flow
- motion sequences
- motion capture data
- spatio temporal
- humanoid robot
- multiple viewpoints
- motion capture
- viewpoint
- motion analysis
- motion model
- human body
- motion patterns
- moving objects
- shape descriptors
- visual hull
- computer vision
- video sequences
- low level