Constrained Maximum Likelihood Linear Regression (CMLLR) is a widely used speaker adaptation technique in which an affine transform of the features is estimated for each speaker....
Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires mode...
In this paper we propose a set of algorithms that combine the anisotropic smoothing using the heat kernel with the outlier rejection capability of robust statistics. The proposed ...
Complex diffusion was introduced in the image processing literature as a means to achieve simultaneous denoising and enhancement of scalar valued images. In this paper, we present ...
Analyzing videos of human activities involves not only
recognizing actions (typically based on their appearances),
but also determining the story/plot of the video. The storyline...
Abhinav Gupta (University of Maryland), Praveen Sr...