Many facial image analysis methods rely on learningbased techniques such as Adaboost or SVMs to project classifiers based on the selection of local image filters (e.g., Haar and...
In the era of multicores, many applications that tend to require substantial compute power and data crunching (aka Throughput Computing Applications) can now be run on desktop PCs...
Chi-Keung Luk, Ryan Newton, William Hasenplaugh, M...
Image-based representations of an object profit from known geometry. The more accurate this geometry is known, the better corresponding pixels in the different images can be align...
We propose a new local learning scheme that is based on the principle of decisiveness: the learned classifier is expected to exhibit large variability in the direction of the test ...
Data prefetching has been widely used in the past as a technique for hiding memory access latencies. However, data prefetching in multi-threaded applications running on chip multi...
Dhruva Chakrabarti, Mahmut T. Kandemir, Mustafa Ka...