This paper presents a novel approach for those applications where vocabulary is defined by a set of acoustic samples. In this approach, the acoustic samples are used as reference...
A major shortcoming of discriminative recognition and detection methods is their noise sensitivity, both during training and recognition. This may lead to very sensitive and britt...
Extracting discriminatory features from images is a crucial task for biometric recognition. For this reason, we have developed a new method for the extraction of features from imag...
We describe an efficient technique to weigh word-based features in binary classification tasks and show that it significantly improves classification accuracy on a range of proble...
Justin Martineau, Tim Finin, Anupam Joshi, Shamit ...
A novel low-computation discriminative feature space is introduced for facial expression recognition capable of robust performance over a rang of image resolutions. Our approach i...