We propose a new discriminative framework, namely Hidden Dynamic Conditional Random Fields (HDCRFs), for building probabilistic models which can capture both internal and external...
Inferences from time-series data can be greatly enhanced by taking into account multiple modalities. In some cases, such as audio of speech and the corresponding video of lip gest...
Trausti T. Kristjansson, Brendan J. Frey, Thomas S...
This paper examines high dimensional regression with noise-contaminated input and output data. Goals of such learning problems include optimal prediction with noiseless query poin...
The intuition that different text classifiers behave in qualitatively different ways has long motivated attempts to build a better metaclassifier via some combination of classifie...
Abstract-- This paper presents a method to associate meanings to words in manipulation tasks. We base our model on an affordance network, i.e., a mapping between robot actions, rob...