Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition.
Sherif AzaryAndreas E. SavakisPublished in: CVPR Workshops (2013)
Keyphrases
- action recognition
- sparse representation
- recognizing human actions
- recognition of human actions
- static images
- subspace learning
- dictionary learning
- action recognition in videos
- depth sensors
- human actions
- view invariant
- sparse coding
- action primitives
- depth cameras
- computer vision
- motion history images
- bag of words
- human motion
- image classification
- activity recognition
- image sequences
- signal processing
- face recognition
- space time
- action classification
- motion estimation
- three dimensional
- high dimensional data
- video sequences
- image patches
- body parts
- object tracking
- camera motion
- dimensionality reduction
- range data
- depth map
- image representation
- structure from motion
- scene flow
- moving objects
- pattern recognition
- feature extraction