We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...
Modern embedded systems often require high degrees of instruction-level parallelism (ILP) within strict constraints on power consumption and chip cost. Unfortunately, a high-perfo...
Systolic implementations of dynamic programming solutions that utilize a similarity matrix can achieve appreciable performance with both course- and fine-grain parallelization. A ...
In this work we propose a scanline optimization procedure for computational stereo using a linear smoothness cost model performed by programmable graphics hardware. The main idea ...
Abstract. The Ubiquitous Web requires novel programming paradigms and distributed architectures for the support of advanced services to a multitude of user devices and profiles. I...