We propose a new method for handwritten word-spotting which does not require prior training or gathering examples for querying. More precisely, a model is trained "on the fly...
We present a probabilistic generative model of visual attributes, together with an efficient learning algorithm. Attributes are visual qualities of objects, such as ‘red’, ...
Virtual evidence (VE), first introduced by (Pearl, 1988), provides a convenient way of incorporating prior knowledge into Bayesian networks. This work generalizes the use of VE to...
—Inexpensive RGB-D cameras that give an RGB image together with depth data have become widely available. We use this data to build 3D point clouds of a full scene. In this paper,...
Hema Swetha Koppula, Abhishek Anand, Thorsten Joac...
This paper presents a novel approach to pedestrian classification which involves utilizing the synthesized virtual samples of a learned generative model to enhance the classificat...