Sciweavers

2440 search results - page 167 / 488
» Learn .MT: A New Approach to Incremental Learning
Sort
View
ICPR
2008
IEEE
16 years 7 months ago
Learning weighted distances for relevance feedback in image retrieval
We present a new method for relevance feedback in image retrieval and a scheme to learn weighted distances which can be used in combination with different relevance feedback metho...
Enrique Vidal, Hermann Ney, Roberto Paredes, Thoma...
HICSS
2002
IEEE
128views Biometrics» more  HICSS 2002»
15 years 11 months ago
Flexible Instructional Strategies for E-learning
This paper provides an overview on a German lighthouse research project called L3 in the area of e-learning systems that supply e-learning services via a virtual private network. ...
Michael Altenhofen, Joachim Schaper
CVPR
2007
IEEE
16 years 8 months ago
Learning Features for Tracking
We treat tracking as a matching problem of detected keypoints between successive frames. The novelty of this paper is to learn classifier-based keypoint descriptions allowing to i...
Michael Grabner, Helmut Grabner, Horst Bischof
ICCBR
2010
Springer
15 years 10 months ago
Reducing the Memory Footprint of Temporal Difference Learning over Finitely Many States by Using Case-Based Generalization
In this paper we present an approach for reducing the memory footprint requirement of temporal difference methods in which the set of states is finite. We use case-based generaliza...
Matt Dilts, Héctor Muñoz-Avila
VMV
2008
107views Visualization» more  VMV 2008»
15 years 8 months ago
Learning with Few Examples using a Constrained Gaussian Prior on Randomized Trees
Machine learning with few training examples always leads to over-fitting problems, whereas human individuals are often able to recognize difficult object categories from only one ...
Erik Rodner, Joachim Denzler