Abstract. Moving objects detection is a crucial step for video surveillance systems. The segmentation performed by motion detection algorithms is often noisy, which makes it hard t...
An efficient speech synthesis method that uses subspace constraint in prosody is proposed. Conventional unit selection methods concatenate speech segments stored in database, tha...
Previous works have demonstrated that the face recognition performance can be improved significantly in low dimensional linear subspaces. Conventionally, principal component analy...
This paper presents a method for detecting people based on the co-occurrence of appearance and spatiotemporal features. Histograms of oriented gradients(HOG) are used as appearanc...
This paper presents a new approach to feature analysis in automatic speech recognition (ASR) based on locality preserving projections (LPP). LPP is a manifold based dimensionality...