Sciweavers

318 search results - page 35 / 64
» Visual Object Recognition Through One-Class Learning
Sort
View
CVPR
2011
IEEE
14 years 7 months ago
What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
Brian Kulis, Kate Saenko, Trevor Darrell
ICCV
2009
IEEE
1824views Computer Vision» more  ICCV 2009»
16 years 4 months ago
Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel
Common visual codebook generation methods used in a Bag of Visual words model, e.g. k-means or Gaussian Mixture Model, use the Euclidean distance to cluster features into visual...
Jianxin Wu, James M. Rehg
CVPR
2011
IEEE
14 years 7 months ago
What Makes a Chair a Chair?
Many object classes are primarily defined by their functions. However, this fact has been left largely unexploited by visual object categorization or detection systems. We propos...
Helmut Grabner, Juergen Gall, Luc VanGool
ICPR
2006
IEEE
16 years 24 days ago
Online Learning of Discriminative Patterns from Unlimited Sequences of Candidates
Recent research in object recognition has demonstrated the advantages of representing objects and scenes through localized patterns such as small image templates. In this paper we...
Ilkka Autio, Jussi T. Lindgren
93
Voted
BMVC
1998
15 years 1 months ago
Learning Enhanced 3D Models for Vehicle Tracking
This paper presents an enhanced hypothesis verification strategy for 3D object recognition. A new learning methodology is presented which integrates the traditional dichotomic obj...
James M. Ferryman, Anthony D. Worrall, Stephen J. ...