Existing visual tracking methods are challenged by object and background appearance variations, which often occur in a long duration tracking. In this paper, we propose a combined ...
We present a study on the importance of psycho-acoustic transformations for effective audio feature calculation. From the results, both crucial and problematic parts of the algori...
Text categorisation relies heavily on feature selection. Both the possible reduction in dimensionality as well as improvements in classification performance are highly desirable. ...
A number of approaches to Automatic MT Evaluation based on deep linguistic knowledge have been suggested. However, n-gram based metrics are still today the dominant approach. The ...
A wide variety of texture feature extraction methods have been proposed for texture based image classification and segmentation. These methods are typically evaluated over windows...