We describe feature space and model space discriminative training for a new class of acoustic models called Bayesian sensing hidden Markov models (BS-HMMs). In BS-HMMs, speech dat...
Abstract— GP-BayesFilters are a general framework for integrating Gaussian process prediction and observation models into Bayesian filtering techniques, including particle filt...
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probab...
Abstract. Given an image, digital matting consists in extracting a foreground element from the background. Standard methods are initialized with a trimap, a partition of the image ...
The relation between hard c-means (HCM), fuzzy c-means (FCM), fuzzy learning vector quantization (FLVQ), soft competition scheme (SCS) of Yair et al. (1992) and probabilistic Gaus...