Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optima...
Biometric fusion consolidates the output of multiple biometric classifiers to render a decision about the identity of an individual. We consider the problem of designing a fusion s...
Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...
Abstract: Designing and implementing multimodal applications that take advantage of several recognitionbased interaction techniques (e.g. speech and gesture recognition) is a diffi...
Motion information is a powerful cue for visual perception. In the context of video indexing and retrieval, motion content serves as a useful source for compact video representati...