Ideally pattern recognition machines provide constant output when the inputs are transformed under a group G of desired invariances. These invariances can be achieved by enhancing...
Multi-task learning leverages shared information among data sets to improve the learning performance of individual tasks. The paper applies this framework for data where each task ...
We present a method to learn models of human heads for the purpose of detection from different viewing angles. We focus on a model where objects are represented as constellations ...
A central problem in the analysis of motion capture (Mo-
Cap) data is how to decompose motion sequences into primitives.
Ideally, a description in terms of primitives should
fac...