We present algorithms for automatic feature selection for unsupervised structure discovery from video sequences. Feature selection in this scenario is hard because of the absence ...
In this paper, we propose a novel method for solving single-image super-resolution problems. Given a low-resolution image as input, we recover its highresolution counterpart using...
Codebook-based representations are widely employed in the classification of complex objects such as images and documents. Most previous codebook-based methods construct a single c...
Wei Zhang, Akshat Surve, Xiaoli Fern, Thomas G. Di...
The `kernel approach' has attracted great attention with the development of support vector machine (SVM) and has been studied in a general way. It offers an alternative soluti...
Inthispaper,weproposeadescriptorcombination method, which enables to improve significantly the recognition rate compared to the recognition rates obtained by each descriptor. This ...