Sciweavers

NN
2000
Springer
192views Neural Networks» more  NN 2000»
13 years 4 months ago
A new algorithm for learning in piecewise-linear neural networks
Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consistin...
Emad Gad, Amir F. Atiya, Samir I. Shaheen, Ayman E...
PAMI
2008
162views more  PAMI 2008»
13 years 4 months ago
Bayes Optimality in Linear Discriminant Analysis
We present an algorithm which provides the one-dimensional subspace where the Bayes error is minimized for the C class problem with homoscedastic Gaussian distributions. Our main ...
Onur C. Hamsici, Aleix M. Martínez
VMV
2000
121views Visualization» more  VMV 2000»
13 years 5 months ago
Silhouette-Based Multiple-View Camera Calibration
In this paper, we present an efficient method for calibrating many camera views simultaneously. We derive an error function based on the mutual consistency of the object silhouett...
Prashant Ramanathan, Eckehard G. Steinbach, Bernd ...
ECIR
2010
Springer
13 years 6 months ago
Goal-Driven Collaborative Filtering - A Directional Error Based Approach
Collaborative filtering is one of the most effective techniques for making personalized content recommendation. In the literature, a common experimental setup in the modeling phase...
Tamas Jambor, Jun Wang
SIGGRAPH
2010
ACM
13 years 9 months ago
Triangle surfaces with discrete equivalence classes
We propose a technique that takes a triangulated surface as input and outputs a surface with the same topology but altered geometry such that each polygon falls into a set of disc...
Mayank Singh, Scott Schaefer
ICARCV
2006
IEEE
126views Robotics» more  ICARCV 2006»
13 years 10 months ago
Improvement to the Minimization of Hybrid Error Functions for Pose Alignment
— Many problems in computer vision such as pose recovery and structure estimation are formulated as a minimization process. These problems vary in the use of image measurements d...
A. H. Abdul Hafez, C. V. Jawahar
FGR
2006
IEEE
157views Biometrics» more  FGR 2006»
13 years 10 months ago
Evaluating Error Functions for Robust Active Appearance Models
Active appearance models (AAMs) are generative parametric models commonly used to track faces in video sequences. A limitation of AAMs is they are not robust to occlusion. A recen...
Barry-John Theobald, Iain Matthews, Simon Baker