CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
We present a novel approach to learn distance metric for information retrieval. Learning distance metric from a number of queries with side information, i.e., relevance judgements...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
In this paper, we propose a novel robust retrieval and classification system for video and motion events based on null space representation. In order to analyze the robustness of ...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
In this work we aim to capitalize on the availability of Internet image search engines to automatically create image training sets from user provided queries. This problem is part...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
This paper presents a new photometric stereo method aiming to efficiently estimate BRDF and reconstruct glossy surfaces. Rough specular surfaces exhibit wide specular lobes under ...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
Region based features are getting popular due to their higher descriptive power relative to other features. However, real world images exhibit changes in image segments capturing ...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
In this paper, we present an approach we refer to as "least squares congealing" which provides a solution to the problem of aligning an ensemble of images in an unsuperv...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
This paper presents a new method to enforce inverse consistency in nonrigid image registration and matching. Conventional approaches assume diffeomorphic transformation, implicitl...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
In this paper we demonstrate that the support vector tracking (SVT) framework first proposed by Avidan is equivalent to the canonical Lucas-Kanade (LK) algorithm with a weighted E...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
We introduce a distributed algorithm for solving large scale Support Vector Machines (SVM) problems. The algorithm divides the training set into a number of processing nodes each ...