Existing sequential feature-based registration algorithms involving search typically either select features randomly (eg. the RANSAC[8] approach) or assume a predefined, intuitive...
This paper presents a learning based approach to tracking articulated human body motion from a single camera. In order to address the problem of pose ambiguity, a one-to-many mappi...
We address the problem of accurate depth estimation using multibaseline stereo in the presence of specular reflections. Specular reflections can cause the intensity and color of c...
Yuanzhen Li, Stephen Lin, Hanqing Lu, Sing Bing Ka...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
Given a classification problem, our goal is to find a low-dimensional linear transformation of the feature vectors which retains information needed to predict the class labels. We...