Sciweavers

310 search results - page 40 / 62
» MuFeSaC: Learning When to Use Which Feature Detector
Sort
View
JRTIP
2007
109views more  JRTIP 2007»
13 years 7 months ago
Robust GPU-assisted camera tracking using free-form surface models
We propose a marker-less model-based camera tracking approach, which makes use of GPU-assisted analysis-by-synthesis methods on a very wide field of view (e.g. fish-eye) camera. ...
Kevin Köser, Bogumil Bartczak, Reinhard Koch
CIKM
2010
Springer
13 years 6 months ago
Learning to rank relevant and novel documents through user feedback
We consider the problem of learning to rank relevant and novel documents so as to directly maximize a performance metric called Expected Global Utility (EGU), which has several de...
Abhimanyu Lad, Yiming Yang
ICMCS
2007
IEEE
95views Multimedia» more  ICMCS 2007»
14 years 2 months ago
The Role of Visual Content and Style for Concert Video Indexing
This paper contributes to the automatic indexing of concert video. In contrast to traditional methods, which rely primarily on audio information for summarization applications, we...
Cees G. M. Snoek, Marcel Worring, Arnold W. M. Sme...
ICML
2005
IEEE
14 years 8 months ago
Supervised dimensionality reduction using mixture models
Given a classification problem, our goal is to find a low-dimensional linear transformation of the feature vectors which retains information needed to predict the class labels. We...
Sajama, Alon Orlitsky
ECCV
2010
Springer
14 years 13 days ago
Geometric Constraints for Human Detection in Aerial Imagery
In this paper, we propose a method for detecting humans in imagery taken from a UAV. This is a challenging problem due to small number of pixels on target, which makes it more di...