—When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstru...
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
Abstract. A novel approach to create a general vision system is presented. The proposed method is based on a visual grammar representation which is transformed to a Bayesian networ...
While Boltzmann Machines have been successful at unsupervised learning and density modeling of images and speech data, they can be very sensitive to noise in the data. In this pap...
Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hi...
We present a new approach, called local discriminant embedding (LDE), to manifold learning and pattern classification. In our framework, the neighbor and class relations of data a...