A novel method is introduced to recognize and estimate the scale of time-varying human gestures. It exploits the changes in contours along spatio-temporal directions. Each contour...
The aim of this work is to index images in domain specific databases using colors computed from the object of interest only, instead of the whole image. The main problem in this t...
We present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. In the component system we first...
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to...
This paper presents an approach for modeling landmark sites such as the Statue of Liberty based on large-scale contaminated image collections gathered from the Internet. Our system...
Xiaowei Li, Changchang Wu, Christopher Zach, Svetl...