In this paper, we propose a probabilistic model for web image mining, which is based on concept-sensitive salient regions without human intervene. Our goal is to achieve a middle-...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
A self-adaptive Hidden Markov Model (SA-HMM) based framework is proposed for behavior recognition in this paper. In this model, if an unknown sequence cannot be classified into an...
—We review the principles of Minimum Description Length and Stochastic Complexity as used in data compression and statistical modeling. Stochastic complexity is formulated as the...
This study revisits the face-to-tongue articulatory inversion problem in speech. We compare the Multi Linear Regression method (MLR) with two more sophisticated methods based on H...