Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 11 - 20
of
146
Learning with Spectral Kernels and Heavy-Tailed Data
, 906
"... Heavy-tailed data, e.g., graphs in which the degree sequence decays according to a power law, are ubiquitous in applications. In many of those applications, spectral kernels, e.g., Laplacian Eigenmaps and Diffusion Maps, are commonly-used analytic tools. We establish learnability results applicable ..."
Abstract
- Add to MetaCart
in both settings. Our first result is an exact learning bound for learning a classification hyperplane when the components of the feature vector decay according to a power law. Thus, although the distribution of data is infinite dimensional and unbounded, a nearly optimal linear classification hyperplane
An Analysis of Active Learning With Uniform Feature Noise
"... In active learning, the user sequentially chooses values for feature X and an oracle returns the corresponding label Y. In this paper, we consider the effect of feature noise in active learning, which could arise either because X itself is being measured, or it is corrupted in transmission to the or ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
to the oracle, or the oracle returns the label of a noisy ver-sion of the query point. In statistics, feature noise is known as “errors in variables ” and has been studied extensively in non-active settings. However, the effect of feature noise in active learning has not been studied be-fore. We consider
Facial Feature Localization Using Graph Matching with Higher Order Statistical Shape Priors and Global Optimization
"... Abstract — This paper presents a graphical model for deformable face matching and landmark localization under an unknown non-rigid warp. The proposed model learns and combines statistics of both appearance and shape variations of facial images (learnt purely from a set of frontal training images) in ..."
Abstract
- Add to MetaCart
Abstract — This paper presents a graphical model for deformable face matching and landmark localization under an unknown non-rigid warp. The proposed model learns and combines statistics of both appearance and shape variations of facial images (learnt purely from a set of frontal training images
Laplace-Beltrami Eigenvalues and Topological Features of Eigenfunctions for Statistical Shape Analysis
, 2009
"... This paper proposes the use of the surface-based Laplace-Beltrami and the volumetric Laplace eigenvalues and eigenfunctions as shape descriptors for the comparison and analysis of shapes. These spectral measures are isometry invariant and therefore allow for shape comparisons with minimal shape pre- ..."
Abstract
-
Cited by 22 (3 self)
- Add to MetaCart
topological features such as critical points, level sets and integral lines of the gradient field across subjects. The use of these topological features of the Laplace-Beltrami eigenfunctions in 2D and 3D for statistical shape analysis is novel.
Convolutional networks for real-time 6-DOF camera relocalization
"... Figure 1: Convolutional neural network monocular camera relocalization. Relocalization results for an input image (top), the predicted camera pose of a visual reconstruction (middle), shown again overlaid in red on the original image (bottom). Our system relocalizes to within approximately 2m and 3 ..."
Abstract
- Add to MetaCart
-strating that convnets can be used to solve complicated out of image plane regression problems. This was made possi-ble by leveraging transfer learning from large scale classi-fication data. We show the convnet localizes from high level features and is robust to difficult lighting, motion blur and different camera
Learning Edge-Specific Kernel Functions For Pairwise Graph Matching
, 2011
"... In this paper we consider the pairwise graph matching problem of finding correspon-dences between two point sets using unary and pairwise potentials, which analyze local descriptor similarity and geometric compatibility. Recently, it was shown that it is possi-ble to learn optimal parameters for the ..."
Abstract
- Add to MetaCart
In this paper we consider the pairwise graph matching problem of finding correspon-dences between two point sets using unary and pairwise potentials, which analyze local descriptor similarity and geometric compatibility. Recently, it was shown that it is possi-ble to learn optimal parameters
SPECTRAL REGRESSION DISCRIMINANT ANALYSIS FOR HYPERSPECTRAL IMAGE CLASSIFICATION
"... Dimensionality reduction algorithms, which aim to select a small set of efficient and discriminant features, have attracted great attention for Hyperspectral Image Classification. The manifold learning methods are popular for dimensionality reduction, such as Locally Linear Embedding, Isomap, and La ..."
Abstract
- Add to MetaCart
Dimensionality reduction algorithms, which aim to select a small set of efficient and discriminant features, have attracted great attention for Hyperspectral Image Classification. The manifold learning methods are popular for dimensionality reduction, such as Locally Linear Embedding, Isomap
Slovenian Pattern Recognition Society, Ljubljana, Slovenia Learned local descriptors fo
"... Abstract In the past local features have become popular for a wide variety of applications such as object recogni-tion, object tracking, structure from motion or stereo vision. Many different interest point detectors as well as local de-scriptors capturing the information of the local surrounding pa ..."
Abstract
- Add to MetaCart
Abstract In the past local features have become popular for a wide variety of applications such as object recogni-tion, object tracking, structure from motion or stereo vision. Many different interest point detectors as well as local de-scriptors capturing the information of the local surrounding
MATCHING OF INTEREST POINT GROUPS WITH PAIRWISE SPATIAL CONSTRAINTS
"... We present an algorithm for finding robust matches between images by considering the spatial constraints between pairs of interest points. By considering these constraints, we account for the layout and structure of features during matching, which produces more robust matches compared to the common ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
approach of using local feature appearance for matching alone. We calculate the similarity between interest point pairs based on a set of spatial constraints. Matches are then found by searching for pairs which satisfy these constraints in a similarity space. Our results show that the algorithm produces
Discussion of “Spectral Dimensionality Reduction via Maximum Entropy”
"... of non-linear dimensionality reduction techniques (manifold learners) have been proposed. Many of these non-linear techniques can be viewed as instantiations of Kernel PCA; they employ a cleverly designed kernel matrix 1 that preserves local data structure in the “feature space ” (Bengio et al., 200 ..."
Abstract
- Add to MetaCart
of non-linear dimensionality reduction techniques (manifold learners) have been proposed. Many of these non-linear techniques can be viewed as instantiations of Kernel PCA; they employ a cleverly designed kernel matrix 1 that preserves local data structure in the “feature space ” (Bengio et al
Results 11 - 20
of
146
