Page
%P
-
Chapter and Conference Paper
Sliding Covariance Matrix: Co-learning Spatiotemporal Geometry Feature for Skeleton Based Action Recognition
The covariance matrix is a generic feature representation in vision applications. It can accurately and efficiently capture geometric features of Riemannian manifold especially in the condition of data size is...
-
Chapter and Conference Paper
Adapting ELM to Time Series Classification: A Novel Diversified Top-k Shapelets Extraction Method
Extreme Learning Machine (ELM for shot) is a single hidden layer feed-forward network, where the weights between input and hidden layer are initialized randomly. ELM is efficient due to its utilization of the ...