We describe a system for automatically extracting dynamics of tongue gestures from ultrasound images of the tongue using translational deep belief networks (tDBNs). In tDBNs, a jo...
We present a general machine learning framework for modelling the phenomenon of missing information in data. We propose a masking process model to capture the stochastic nature of...
—One of the major challenges in multi-view imaging is the definition of a representation that reveals the intrinsic geometry of the visual information. Sparse image representati...
In this paper, we propose a system identification approach for group activity recognition in traffic surveillance. Statistical shape theory is used to extract features, and then...
Abstract For many centuries scientists have wondered how the human brain represents thoughts in terms of the underlying biology of neural activity. Philosophers, linguists, cogniti...