— Matching images with large geometric and iconic changes (e.g. faces under different poses and facial expressions) is an open research problem in computer vision. There are two ...
Eigenvalue problems are rampant in machine learning and statistics and appear in the context of classification, dimensionality reduction, etc. In this paper, we consider a cardina...
Bharath K. Sriperumbudur, David A. Torres, Gert R....
A novel scheme is proposed for achieving motion segmentation in low-frame rate videos, with application to temporal super resolution. Probabilistic generative models are commonly ...
Applying learning techniques to acquire action models is an area of intense research interest. Most previous works in this area have assumed that there is a significant amount of...
The meta-learner MLR (Multi-response Linear Regression) has been proposed as a trainable combiner for fusing heterogeneous baselevel classifiers. Although it has interesting prope...