Tensor Manifold Discriminant Projections for Acceleration-Based Human Activity Recognition.
Yanan GuoDapeng TaoJun ChengAlan William DoughertyYaotang LiKun YueBob ZhangPublished in: IEEE Trans. Multim. (2016)
Keyphrases
- human activity recognition
- low dimensional
- activity recognition
- tensor space
- human activities
- dimensionality reduction
- riemannian manifolds
- higher order tensors
- order tensor
- high dimensional
- manifold learning
- symmetric positive definite
- three dimensional
- visual surveillance
- locality preserving projections
- diffusion tensor
- principal component analysis
- feature extraction
- euclidean space
- riemannian metric
- graph embedding
- learning algorithm
- feature space
- active learning
- data points
- action recognition
- high dimensional data
- sensor networks