Sciweavers

727 search results - page 64 / 146
» Two thresholds are better than one
Sort
View
ICCV
2009
IEEE
15 years 1 months ago
What is the Best Multi-Stage Architecture for Object Recognition?
In many recent object recognition systems, feature extraction stages are generally composed of a filter bank, a non-linear transformation, and some sort of feature pooling layer...
Kevin Jarrett, Koray Kavukcuoglu, Marc’Aurelio R...
CVPR
2010
IEEE
14 years 5 months ago
Pareto-optimal Dictionaries for Signatures
We present an effective method to optimize over the parameters of an image patch descriptor to obtain one that is computationally more efficient while maintaining a high recogniti...
Michael Calonder, Vincent Lepetit, Pascal Fua
ICMCS
2006
IEEE
129views Multimedia» more  ICMCS 2006»
14 years 3 months ago
Directional Discrete Cosine Transforms for Image Coding
- Nearly all block-based transform schemes for image and video coding developed so far choose the 2-D discrete cosine transform (DCT) of a square block shape. With almost no except...
Bing Zeng, Jingjing Fu
CVPR
2010
IEEE
14 years 2 months ago
Pushing the Envelope of Modern Methods for Bundle Adjustment
In this paper, we present results and experiments with several methods for bundle adjustment, producing the fastest bundle adjuster ever published. The fastest methods work with t...
Yekeun Jeong, David Nister, Drew Steedly, Richard ...
ISVLSI
2002
IEEE
104views VLSI» more  ISVLSI 2002»
14 years 1 months ago
Scalable VLSI Architecture for GF(p) Montgomery Modular Inverse Computation
Modular inverse computation is needed in several public key cryptographic applications. In this work, we present two VLSI hardware implementations used in the calculation of Montg...
Adnan Abdul-Aziz Gutub, Alexandre F. Tenca, &Ccedi...