The bag-of-visual-words (BOVW) approaches are widely used in human action recognition. Usually, large vocabulary size of the BOVW is more discriminative for inter-class action clas...
The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
If you were told that some object A was perfectly (or somewhat, or not at all) in some direction (e.g., west, above-right) of some reference object B, where in space would you loo...
In this paper we propose a new framework for modeling 2D shapes. A shape is first described by a sequence of local features (e.g., curvature) of the shape boundary. The resulting ...
Head pose estimation from images has recently attracted much attention in computer vision due to its diverse applications in face recognition, driver monitoring and human computer...
Dong Huang, Markus Storer, Fernando DelaTorre, Hor...