Software end users are the best testers, who keep revealing bugs in software that has undergone rigorous in-house testing. In order to leverage their testing efforts, failure repor...
Recognition using only visual evidence cannot always be successful due to limitations of information and resources available during training. Considering relation among lexicon en...
The application of semi-supervised learning algorithms to large scale vision problems suffers from the bad scaling behavior of most methods. Based on the Expectation Regularization...
A two layer coding algorithm for high dynamic range images is discussed. In the first layer, a low dynamic range image is encoded by a conventional codec, and then the residual in...
We recently introduced symbolic timing simulation (STS) using data-dependent delays as a tool for verifying the timing of fullcustom transistor-level circuit designs, and for the ...