In recent research, we have proposed a high-accuracy bottom-up detection-based paradigm for continuous phone speech recognition. The key component of our system was a bank of arti...
In the near future, homes are envisioned to be equipped with numerous intelligent communicating devices. Such smart home needs to exhibit highly adaptive behavior to meet the inha...
We present a novel local region approach for statistically characterizing appearance in the context of medical image segmentation via deformable models. Our appearance model refl...
Joshua Stough, Robert E. Broadhurst, Stephen M. Pi...
Several problems in text categorization are too hard to be solved by standard bag-of-words representations. Work in kernel-based learning has approached this problem by (i) consid...
—In this paper, we address the key problem in real-time video coding, the rate-distortion (R-D) tradeoff. As most video coding applications employ color images, we analyze the R-...