In this paper, we propose a sequential approach to hallucinate/synthesize high-resolution images of multiple facial expressions. We propose an idea of multi-resolution tensor for ...
Can a machine learn to perceive emotions as evoked by an artwork? Here we propose an emotion categorization system, trained by ground truth from psychology studies. The training d...
Victoria Yanulevskaya, Jan van Gemert, Katharina R...
Shannon's Noisy-Channel model, which describes how a corrupted message might be reconstructed, has been the corner stone for much work in statistical language and speech proc...
Clustering is one of the most widely used statistical tools for data analysis. Among all existing clustering techniques, k-means is a very popular method because of its ease of pr...
The conditional distribution of a discrete variable y, given another discrete variable x, is often specified by assigning one multinomial distribution to each state of x. The cost...