Abstract. The problem of searching for a model-based scene interpretation is analyzed within a probabilistic framework. Object models are formulated as generative models for range ...
We present BayesMD, a Bayesian Motif Discovery model with several new features. Three different types of biological a priori knowledge are built into the framework in a modular fa...
Abstract. This paper proposes an approach to classify human arm motion using qualitative normalized templates. The proposed method consists of construction of human arm model, qual...
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...
Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional ...