Sciweavers

1085 search results - page 148 / 217
» On the performance of one-to-many data transformations
Sort
View
CLUSTER
2004
IEEE
14 years 23 days ago
Predicting memory-access cost based on data-access patterns
Improving memory performance at software level is more effective in reducing the rapidly expanding gap between processor and memory performance. Loop transformations (e.g. loop un...
Surendra Byna, Xian-He Sun, William Gropp, Rajeev ...
ICCV
2009
IEEE
15 years 2 months ago
Efficient subset selection based on the Renyi entropy
Many machine learning algorithms require the summation of Gaussian kernel functions, an expensive operation if implemented straightforwardly. Several methods have been proposed t...
Vlad I. Morariu1, Balaji V. Srinivasan, Vikas C. R...
MEDIAFORENSICS
2010
13 years 10 months ago
Forensic hash for multimedia information
Digital multimedia such as images and videos are prevalent on today's internet and cause significant social impact, which can be evidenced by the proliferation of social netw...
Wenjun Lu, Avinash L. Varna, Min Wu
VMV
2004
208views Visualization» more  VMV 2004»
13 years 10 months ago
Fourier Volume Rendering on the GPU Using a Split-Stream-FFT
The Fourier volume rendering technique operates in the frequency domain and creates line integral projections of a 3D scalar field. These projections can be efficiently generated ...
Thomas Jansen, Bartosz von Rymon-Lipinski, Nils Ha...
ICCV
2007
IEEE
14 years 11 months ago
An Invariant Large Margin Nearest Neighbour Classifier
The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...