Sciweavers

85 search results - page 15 / 17
» Novel maximum-margin training algorithms for supervised neur...
Sort
View
PAMI
2011
12 years 11 months ago
Robust Object Tracking with Online Multiple Instance Learning
In this paper we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques cal...
Boris Babenko, Ming-Hsuan Yang, Serge Belongie

Publication
234views
11 years 11 months ago
Road Scene Understanding from a Single Image
Road scene segmentation is important in computer vision for different applications such as autonomous driving and pedestrian detection. Recovering the 3D structure of road scenes ...
Jose M. Alvarez, Theo Gevers, Yann LeCun, Antonio ...
PAKDD
2000
ACM
161views Data Mining» more  PAKDD 2000»
14 years 4 days ago
Adaptive Boosting for Spatial Functions with Unstable Driving Attributes
Combining multiple global models (e.g. back-propagation based neural networks) is an effective technique for improving classification accuracy by reducing a variance through manipu...
Aleksandar Lazarevic, Tim Fiez, Zoran Obradovic
ICMLA
2008
13 years 10 months ago
Towards On-line Treatment Verification Using cine EPID for Hypofractionated Lung Radiotherapy
We propose a novel approach for on-line treatment verification using cine EPID (Electronic Portal Imaging Device) images for hypofractionated lung radiotherapy based on a machine ...
Xiaoli Tang, Tong Lin, Steve B. Jiang
CEC
2008
IEEE
14 years 3 months ago
Increasing rule extraction accuracy by post-processing GP trees
—Genetic programming (GP), is a very general and efficient technique, often capable of outperforming more specialized techniques on a variety of tasks. In this paper, we suggest ...
Ulf Johansson, Rikard König, Tuve Löfstr...