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, ...
We describe a robot that is able to autonomously plug itself in to standard, unmodified electrical outlets by sensing the 60Hz electric fields emitted from the outlet. The building...
The huge size of online social networks (OSNs) makes it prohibitively expensive to precisely measure any properties which require the knowledge of the entire graph. To estimate the...
Conventional sentence compression methods employ a syntactic parser to compress a sentence without changing its meaning. However, the reference compressions made by humans do not ...
A parsing makes 1-best search efficient by suppressing unlikely 1-best items. Existing kbest extraction methods can efficiently search for top derivations, but only after an exhau...