Results 1 - 10 of 944

MOORE, WARRELL AND PRINCE: HIERARCHIAL BOUNDARY PRIORS 1 Vistas: Hierarchial boundary priors using multiscale conditional random fields.

by Alastair P. Moore, Jonathan Warrell, Simon J. D. Prince
"... Boundary detection is a fundamental problem in computer vision. However, bound-ary detection is difficult as it involves integrating multiple cues (intensity, color, texture) as well as trying to incorporate object class or scene level descriptions to mitigate the am-biguity of the local signal. In ..."
Abstract - Add to MetaCart
boundary detection algorithms do not generalize well to these complex scenes. We show that our algorithm successfully learns these boundary distributions and can exploit this knowledge to improve state-of-the-art bound-ary detectors. 1

Vistas: Hierarchial boundary priors using multiscale conditional random fields.

by Jonathan Warrell, Alastair P. Moore, Simon J. D. Prince
"... Boundary detection is a fundamental problem in computer vision. However, bound-ary detection is difficult as it involves integrating multiple cues (intensity, color, texture) as well as trying to incorporate object class or scene level descriptions to mitigate the am-biguity of the local signal. In ..."
Abstract - Add to MetaCart
boundary detection algorithms do not generalize well to these complex scenes. We show that our algorithm successfully learns these boundary distributions and can exploit this knowledge to improve state-of-the-art bound-ary detectors. 1

Local features and kernels for classification of texture and object categories: a comprehensive study

by J. Zhang, S. Lazebnik, C. Schmid - International Journal of Computer Vision , 2007
"... Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations an ..."
Abstract - Cited by 653 (34 self) - Add to MetaCart
and classifiers. We then conduct a comparative evaluation with several state-of-the-art recognition methods on four texture and five object databases. On most of these databases, our implementation exceeds the best reported results and achieves comparable performance on the rest. Finally, we investigate

Contour Detection and Hierarchical Image Segmentation

by Pablo Arbeláez, Michael Maire, Charless Fowlkes, Jitendra Malik - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2010
"... This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentati ..."
Abstract - Cited by 389 (24 self) - Add to MetaCart
This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our

Multiple Kernels for Object Detection

by Andrea Vedaldi, Varun Gulshan, Manik Varma, Andrew Zisserman
"... Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image subwindows. We use multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential χ 2 kernels, ..."
Abstract - Cited by 275 (10 self) - Add to MetaCart
Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image subwindows. We use multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential χ 2 kernels

Neutrinos: Summarizing the State-of-the-Art

by J. W. F. Valle , 2002
"... Abstract. I review oscillation solutions to the neutrino anomalies and discuss how to account for the required pattern of neutrino masses and mixings from first principles. Unification and low-energy bottom-up approaches are discussed, the latter open up the possibility of testing neutrino mixing at ..."
Abstract - Add to MetaCart
at high energy colliders, such as the LHC. Large νe mixing is consistent with Supernova (SN) astrophysics and may serve to probe galactic SN parameters at Cherenkov detectors. I discuss the robustness of the atmospheric neutrino oscillation hypothesis against the presence of Flavor Changing (FC) Non

State-of-the-Art: Transformation Invariant Descriptors

by Asha S, Sreeraj M
"... Abstract — As the popularity of digital videos increases, a large number illegal videos are being generated and getting published. Video copies are generated by performing various sorts of transformations on the original video data. For effectively identifying such illegal videos, the image features ..."
Abstract - Add to MetaCart
of local features is due to its efficient discriminative power in extracting image contents. In this paper, we focus on various recently proposed local detectors and descriptors that are invariant to a number of image transformations. This paper also compares the performance of various local feature

Inferring Global Perceptual Contours from Local Features

by Gideon Guy, Gérard Medioni , 1996
"... Introduction Computer vision can greatly benefit from perceptual grouping. Perceptual Grouping can be classified as a mid-level process directed toward closing the gap between what is produced by state-of-the-art low-level algorithms (such as edge detectors) and what is desired as input to high lev ..."
Abstract - Cited by 210 (10 self) - Add to MetaCart
Introduction Computer vision can greatly benefit from perceptual grouping. Perceptual Grouping can be classified as a mid-level process directed toward closing the gap between what is produced by state-of-the-art low-level algorithms (such as edge detectors) and what is desired as input to high

Building high-level features using large scale unsupervised learning

by Quoc V. Le, Rajat Monga, Matthieu Devin, Kai Chen, Greg S. Corrado, Jeff Dean, Andrew Y. Ng - In International Conference on Machine Learning, 2012. 103
"... We consider the problem of building highlevel, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder withpoolingandlocalcontrastnormalizati ..."
Abstract - Cited by 180 (9 self) - Add to MetaCart
the previous state-of-the-art.

Groups of Adjacent Contour Segments for Object Detection

by V. Ferrari, L. Fevrier, F. Jurie, C. Schmid , 2007
"... We present a family of scale-invariant local shape features formed by chains of k connected, roughly straight contour segments (kAS), and their use for object class detection. kAS are able to cleanly encode pure fragments of an object boundary, without including nearby clutter. Moreover, they offer ..."
Abstract - Cited by 188 (7 self) - Add to MetaCart
object classes and more than 1400 images, we 1) study the evolution of performance as the degree of feature complexity k varies and determine the best degree; 2) show that kAS substantially outperform interest points for detecting shape-based classes; 3) compare our object detector to the recent, state-of-the-art
Results 1 - 10 of 944