In this paper, we address the problem of visually guiding and controlling a robot in projective three-space using stereo vision. As the proposed method is entirely formulated in pr...
Multi-concept learning is an important problem in multimedia content analysis and retrieval. It connects two key components in the multimedia semantic ecosystem: multimedia lexico...
This work extends and improves a recently introduced (Dec. 2007) dynamic Bayesian network (DBN) based audio-visual automatic speech recognition (AVASR) system. That system models ...
We present an automated algorithm for tissue segmentation of noisy, low contrast magnetic resonance (MR) images of the brain. We use a mixture model composed of a large number of G...
Independent Component Analysis is becoming a popular exploratory method for analysing complex data such as that from FMRI experiments. The application of such `model-free' me...