Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group.
Raviteja VemulapalliFelipe ArrateRama ChellappaPublished in: CVPR (2014)
Keyphrases
- action recognition
- lie group
- human activities
- human actions
- activity recognition
- human detection
- computer vision
- body parts
- human pose
- data points
- feature points
- vector field
- parameter space
- point sets
- riemannian manifolds
- euclidean space
- shape analysis
- geometric structure
- keypoints
- video data
- rigid motion
- d objects
- image sequences