Riemannian manifold-valued part-based features and geodesic-induced kernel machine for activity classification dedicated to assisted living.
Yixiao YunIrene Yu-Hua GuPublished in: Comput. Vis. Image Underst. (2017)
Keyphrases
- kernel machines
- assisted living
- feature vectors
- classification accuracy
- feature space
- feature set
- feature extraction
- riemannian manifolds
- support vector
- support vector machine
- euclidean space
- class labels
- decision trees
- pattern recognition
- machine learning
- svm classifier
- supervised learning
- unsupervised learning
- feature selection
- learning tasks
- training samples
- multiple kernel learning
- special case