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...
We propose an approach to include contextual features for labeling images, in which each pixel is assigned to one of a finite set of labels. The features are incorporated into a p...
While conditional random fields (CRFs) have been applied successfully in a variety of domains, their training remains a challenging task. In this paper, we introduce a novel trai...
Lin Liao, Tanzeem Choudhury, Dieter Fox, Henry A. ...
In this paper, we present a fast approach to obtain semantic scene segmentation with high precision. We employ a two-stage classifier to label all image pixels. First, we use the ...
Wen Yang, Dengxin Dai, Bill Triggs, Gui-Song Xia, ...
Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract a person’s activities and significant plac...