Sciweavers

3109 search results - page 267 / 622
» Hypergraph-Based Image Representation
Sort
View
JMLR
2012
13 years 6 months ago
Deep Learning Made Easier by Linear Transformations in Perceptrons
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Tapani Raiko, Harri Valpola, Yann LeCun
JMLR
2012
13 years 6 months ago
Learning Low-order Models for Enforcing High-order Statistics
Models such as pairwise conditional random fields (CRFs) are extremely popular in computer vision and various other machine learning disciplines. However, they have limited expre...
Patrick Pletscher, Pushmeet Kohli
ICIP
2006
IEEE
16 years 5 months ago
Two-Stage Optimal Component Analysis
Linear techniques are widely used to reduce the dimension of image representation spaces in applications such as image indexing and object recognition. Optimal Component Analysis ...
Yiming Wu, Xiuwen Liu, Washington Mio, Kyle A. Gal...
ICRA
2003
IEEE
131views Robotics» more  ICRA 2003»
15 years 9 months ago
Sky/ground modeling for autonomous MAV flight
Abstract— Recently, we have implemented a computervision based horizon-tracking algorithm for flight stability and autonomy in Micro Air Vehicles (MAVs) [1]. Occasionally, this ...
Sinisa Todorovic, Michael C. Nechyba, Peter G. Ifj...
MICCAI
1998
Springer
15 years 8 months ago
Robust Brain Segmentation Using Histogram Scale-Space Analysis and Mathematical Morphology
Abstract. In this paper, we propose a robust fully non-supervised method dedicated to the segmentation of the brain in T1-weighted MR images. The first step consists in the analysi...
Jean-Francois Mangin, Olivier Coulon, Vincent Frou...