Results 1  10
of
16,482
Accelerating CUDA graph algorithms at maximum warp
 In PPoPP
, 2011
"... Graphs are powerful data representations favored in many computational domains. Modern GPUs have recently shown promising results in accelerating computationally challenging graph problems but their performance suffers heavily when the graph structure is highly irregular, as most realworld graphs t ..."
Abstract

Cited by 49 (3 self)
 Add to MetaCart
tend to be. In this study, we first observe that the poor performance is caused by work imbalance and is an artifact of a discrepancy between the GPU programming model and the underlying GPU architecture. We then propose a novel virtual warpcentric programming method that exposes the traits
Nonlinear spatial normalization using basis functions
 Human Brain Mapping
, 1999
"... Abstract: We describe a comprehensive framework for performing rapid and automatic nonlabelbased nonlinear spatial normalizations. The approach adopted minimizes the residual squared difference between an image and a template of the same modality. In order to reduce the number of parameters to be f ..."
Abstract

Cited by 329 (19 self)
 Add to MetaCart
to be fitted, the nonlinear warps are described by a linear combination of low spatial frequency basis functions. The objective is to determine the optimum coefficients for each of the bases by minimizing the sum of squared differences between the image and template, while simultaneously maximizing
Maximum Intensity Projection at Warp Speed
, 1999
"... Maximum Intensity Projection (MIP) is a volume rendering technique which is used to extract highintensity structures from volumetric scalar data. At each pixel the highest data value encountered along the corresponding viewing ray is determined. MIP is commonly used to extract vascular structures f ..."
Abstract

Cited by 10 (3 self)
 Add to MetaCart
Maximum Intensity Projection (MIP) is a volume rendering technique which is used to extract highintensity structures from volumetric scalar data. At each pixel the highest data value encountered along the corresponding viewing ray is determined. MIP is commonly used to extract vascular structures
Restoration of a Single Superresolution Image from Several Blurred, Noisy, and Undersampled Measured Images
, 1997
"... The three main tools in the single image restoration theory are the maximum likelihood (ML) estimator, the maximum a posteriori probability (MAP) estimator, and the set theoretic approach using projection onto convex sets (POCS). This paper utilizes the above known tools to propose a unified methodo ..."
Abstract

Cited by 267 (22 self)
 Add to MetaCart
The three main tools in the single image restoration theory are the maximum likelihood (ML) estimator, the maximum a posteriori probability (MAP) estimator, and the set theoretic approach using projection onto convex sets (POCS). This paper utilizes the above known tools to propose a unified
Bayesian Warped Gaussian Processes
"... Warped Gaussian processes (WGP) [1] model output observations in regression tasks as a parametric nonlinear transformation of a Gaussian process (GP). The use of this nonlinear transformation, which is included as part of the probabilistic model, was shown to enhance performance by providing a bette ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
in which the maximum likelihood WGP failed: Low data regime, data with censored values, classification, etc. We demonstrate the superior performance of Bayesian warped GPs on several real data sets. 1
Fast Maximum Intensity Projection using Binary ShearWarp Factorization
 In Proceedings of WSCG’99
, 1999
"... This paper presents a fast maximum intensity projection technique based on binary shearwarp factorization. The proposed method divides the density domain into a small number of intervals, and to each interval a binary code representation is assigned. In a preprocessing step, an additional volume is ..."
Abstract

Cited by 9 (4 self)
 Add to MetaCart
This paper presents a fast maximum intensity projection technique based on binary shearwarp factorization. The proposed method divides the density domain into a small number of intervals, and to each interval a binary code representation is assigned. In a preprocessing step, an additional volume
Y.: Learning maximum margin temporal warping for action recognition
 In: ICCV. (2013
"... Temporal misalignment and duration variation in video actions largely influence the performance of action recognition, but it is very difficult to specify effective temporal alignment on action sequences. To address this challenge, this paper proposes a novel discriminative learningbased temporal ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
alignment method, called maximum margin temporal warping (MMTW), to align two action sequences and measure their matching score. Based on the latent structure SVM formulation, the proposed MMTW method is able to learn a phantom action template to represent an action class for maximum discrimination
Warped Universal Extra Dimensions
, 2011
"... We consider a 5D warped scenario with a KKparity symmetry, where the nontrivial warping arises from the dynamics that stabilizes the size of the extra dimension. Generically, the lightest KaluzaKlein (KK) particle is the first excitation of the radion field, while the nexttolightest KaluzaKlei ..."
Abstract
 Add to MetaCart
We consider a 5D warped scenario with a KKparity symmetry, where the nontrivial warping arises from the dynamics that stabilizes the size of the extra dimension. Generically, the lightest KaluzaKlein (KK) particle is the first excitation of the radion field, while the nexttolightest Kaluza
Results 1  10
of
16,482