Abstract. We propose a novel probabilistic method, based on latent variable models, for unsupervised topographic visualisation of dynamically evolving, coherent textual information...
Many modern natural language processing applications would benefit from automatic morphological analysis of words, especially when dealing with morphologically rich languages. Con...
In this work, we propose an unsupervised Bayesian model for the detection of moving objects from dynamic scenes. This unsupervised solution is a three-step approach that uses a st...
This paper proposes a new framework to formulate the problem of rushes video summarization as an unsupervised learning problem. We pose the problem of video summarization as one o...
Yang Liu, Feng Zhou, Wei Liu, Fernando De la Torre...
Automatic facial action unit (AU) detection from video is a long-standing problem in computer vision. Two main approaches have been pursued: (1) static modeling--typically posed a...
Tomas Simon, Nguyen Minh, Fernando De la Torre, Je...