Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
Abstract. We present a novel model for object recognition and detection that follows the widely adopted assumption that objects in images can be represented as a set of loosely cou...
Thomas Deselaers, Andre Hegerath, Daniel Keysers, ...
A detailed description of tone and intonation is beneficial for many spoken language processing applications. In traditional methods for tone and pitch accent modeling, prosodic ...
Documents often contain inherently many concepts reflecting specific and generic aspects. To automatically generate a short summary text of documents on similar topics, it is im...
: Computational classification of proteins using methods such as string kernels and Fisher-SVM has demonstrated great success. However, the resulting models do not offer an immedia...