We propose a motion deblurring algorithm that exploits sparsity constraints of image patches using one single frame. In our formulation, each image patch is encoded with sparse co...
In this paper we present a new evolutionary method for complex-process optimization. It is partially based on principles of the scatter search methodology, but it makes use of inn...
In kernel-based video object tracking, the use of single kernel often suffers from the occlusion. In order to provide more robust tracking performance, multiple inter-related kern...
In this paper, we first design a more generalized network model, Improved CBP, based on the same structure as Circular BackPropagation (CBP) proposed by Ridella et al. The novelty ...
Discriminative training for language recognition has been a key tool for improving system performance. In addition, recognition directly from shifted-delta cepstral features has p...