Search For:

Displaying 1-15 out of 15 total
Learning equivariant structured output SVM regressors
Found in: Computer Vision, IEEE International Conference on
By Andrea Vedaldi,Matthew Blaschko,Andrew Zisserman
Issue Date:November 2011
pp. 959-966
Equivariance and invariance are often desired properties of a computer vision system. However, currently available strategies generally rely on virtual sampling, leaving open the question of how many samples are necessary, on the use of invariant feature r...
 
Efficient Additive Kernels via Explicit Feature Maps
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Andrea Vedaldi,Andrew Zisserman
Issue Date:March 2012
pp. 480-492
Large scale nonlinear support vector machines (SVMs) can be approximated by linear ones using a suitable feature map. The linear SVMs are in general much faster to learn and evaluate (test) than the original nonlinear SVMs. This work introduces explicit fe...
 
Efficient additive kernels via explicit feature maps
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrea Vedaldi, Andrew Zisserman
Issue Date:June 2010
pp. 3539-3546
Maji and Berg [13] have recently introduced an explicit feature map approximating the intersection kernel. This enables efficient learning methods for linear kernels to be applied to the non-linear intersection kernel, expanding the applicability of this m...
 
Relaxed matching kernels for robust image comparison
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrea Vedaldi, Stefano Soatto
Issue Date:June 2008
pp. 1-8
The popular bag-of-features representation for object recognition collects signatures of local image patches and discards spatial information. Some have recently attempted to at least partially overcome this limitation, for instance by “spatial pyramids” a...
 
Joint data alignment up to (lossy) transformations
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrea Vedaldi, Gregorio Guidi, Stefano Soatto
Issue Date:June 2008
pp. 1-8
Joint data alignment is often regarded as a data simplification process. This idea is powerful and general, but raises two delicate issues. First, one must make sure that the use ful information about the data is preserved by the alignment process. This is...
 
Boosting Invariance and Efficiency in Supervised Learning
Found in: Computer Vision, IEEE International Conference on
By Andrea Vedaldi, Paolo Favaro, Enrico Grisan
Issue Date:October 2007
pp. 1-8
In this paper we present a novel boosting algorithm for supervised learning that incorporates invariance to data transformations and has high generalization capabilities. While one can incorporate invariance by adding virtual samples to the data (e.g., by ...
 
Objects in Context
Found in: Computer Vision, IEEE International Conference on
By Andrew Rabinovich, Andrea Vedaldi, Carolina Galleguillos, Eric Wiewiora, Serge Belongie
Issue Date:October 2007
pp. 1-8
In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to incorporate semantic object context as a post-processing step into any off-the-sh...
 
Moving Forward in Structure From Motion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrea Vedaldi, Gregorio Guidi, Stefano Soatto
Issue Date:June 2007
pp. 1-7
It is well-known that forward motion induces a large number of local minima in the instantaneous least-squares reprojection error. This is caused in part by singularities in the error landscape around the forward direction, and presents a challenge in usin...
 
Local Features, All Grown Up
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrea Vedaldi, Stefano Soatto
Issue Date:June 2006
pp. 1753-1760
We present a technique to adapt the domain of local features through the matching process to augment their discriminative power. We start with local affine features selected and normalized independently in training and test images, and jointly expand their...
 
Features for Recognition: Viewpoint Invariance for Non-Planar Scenes
Found in: Computer Vision, IEEE International Conference on
By Andrea Vedaldi, Stefano Soatto
Issue Date:October 2005
pp. 1474-1481
Most current local feature detectors/descriptors implicitly assume that the scene is (locally) planar, an assumption that is violated at surface discontinuities. We show that this restriction is, at least in theory, unnecessary, as one can construct local ...
 
KALMANSAC: Robust Filtering by Consensus
Found in: Computer Vision, IEEE International Conference on
By Andrea Vedaldi, Hailin Jin, Paolo Favaro, Stefano Soatto
Issue Date:October 2005
pp. 633-640
We propose an algorithm to perform causal inference of the state of a dynamical model when the measurements are corrupted by outliers. While the optimal (maximum-likelihood) solution has doubly exponential complexity due to the combinatorial explosion of p...
 
Learning Local Feature Descriptors Using Convex Optimisation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Karen Simonyan,Andrea Vedaldi,Andrew Zisserman
Issue Date:August 2014
pp. 1573-1585
The objective of this work is to learn descriptors suitable for the sparse feature detectors used in viewpoint invariant matching. We make a number of novel contributions towards this goal. First, it is shown that learning the pooling regions for the descr...
 
Blocks That Shout: Distinctive Parts for Scene Classification
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Mayank Juneja,Andrea Vedaldi,C.V. Jawahar,Andrew Zisserman
Issue Date:June 2013
pp. 923-930
The automatic discovery of distinctive parts for an object or scene class is challenging since it requires simultaneously to learn the part appearance and also to identify the part occurrences in images. In this paper, we propose a simple, efficient, and e...
 
The truth about cats and dogs
Found in: Computer Vision, IEEE International Conference on
By Omkar M Parkhi,Andrea Vedaldi,C. V. Jawahar,Andrew Zisserman
Issue Date:November 2011
pp. 1427-1434
Template-based object detectors such as the deformable parts model of Felzenszwalb et al. [11] achieve state-of-the-art performance for a variety of object categories, but are still outperformed by simpler bag-of-words models for highly flexible objects su...
 
Vlfeat: an open and portable library of computer vision algorithms
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Andrea Vedaldi, Brian Fulkerson
Issue Date:October 2010
pp. 1469-1472
VLFeat is an open and portable library of computer vision algorithms. It aims at facilitating fast prototyping and reproducible research for computer vision scientists and students. It includes rigorous implementations of common building blocks such as fea...
     
 1