Results 1  10
of
208
Statistical shape influence in geodesic active contours
 In Proc. 2000 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Hilton Head, SC
, 2000
"... A novel method of incorporating shape information into the image segmentation process is presented. We introduce a representation for deformable shapes and define a probability distribution over the variances of a set of training shapes. The segmentation process embeds an initial curve as the zero l ..."
Abstract

Cited by 396 (4 self)
 Add to MetaCart
shape information and the image information. We then evolve the surface globally, towards the MAP estimate, and locally, based on image gradients and curvature. Results are demonstrated on synthetic data and medical imagery, in 2D and 3D. 1
Stochastic Gradient Descent Training for L1regularized Loglinear Models with Cumulative Penalty
"... Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework is attractive because it often requires much less training time in practice than batch training algorithms. However, L1re ..."
Abstract

Cited by 42 (0 self)
 Add to MetaCart
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework is attractive because it often requires much less training time in practice than batch training algorithms. However, L1
Geodesic Active Regions for Motion Estimation and Tracking
, 1999
"... This paper proposes a new front propagation method to deal accurately with the challenging problem of tracking nonrigid moving objects. This is obtained by employing a Geodesic Active Region model where the designed objective function is composed of boundary and regionbased terms and optimizes the ..."
Abstract

Cited by 71 (5 self)
 Add to MetaCart
position and the corresponding motion model. The designed objective function is minimized using a gradient descent method; the curve is propagated towards the object boundaries under the influence of boundary, intensity and motionbased forces, while given the curve position an analytical solution
Hierarchical Datadriven Descent for Efficient Optimal Deformation Estimation
"... Realworld surfaces such as clothing, water and human body deform in complex ways. The image distortions observed are highdimensional and nonlinear, making it hard to estimate these deformations accurately. The recent datadriven descent approach [17] applies Nearest Neighbor estimators iterativ ..."
Abstract
 Add to MetaCart
Realworld surfaces such as clothing, water and human body deform in complex ways. The image distortions observed are highdimensional and nonlinear, making it hard to estimate these deformations accurately. The recent datadriven descent approach [17] applies Nearest Neighbor estimators
Fast gradient descent for drifting least squares regression, with application to bandits
"... Online learning algorithms require to often recompute least squares regression estimates of parameters. We study improving the computational complexity of such algorithms by using stochastic gradient descent (SGD) type schemes in place of classic regression solvers. We show that SGD schemes efficien ..."
Abstract
 Add to MetaCart
Online learning algorithms require to often recompute least squares regression estimates of parameters. We study improving the computational complexity of such algorithms by using stochastic gradient descent (SGD) type schemes in place of classic regression solvers. We show that SGD schemes
Gradient Feature Selection for Online Boosting
"... Boosting has been widely applied in computer vision, especially after Viola and Jones’s seminal work [23]. The marriage of rectangular features and integralimageenabled fast computation makes boosting attractive for many vision applications. However, this popular way of applying boosting normally e ..."
Abstract

Cited by 21 (3 self)
 Add to MetaCart
characteristic, but yet impractical due to the huge hypothesis pool. This paper proposes a gradientbased feature selection approach. Assuming a generally trained feature set and labeled samples are given, our approach iteratively updates each feature using the gradient descent, by minimizing the weighted least
ProximalGradient Algorithms for Tracking Cascades Over Social Networks
"... Abstract—Many realworld processes evolve in cascades over complex networks, whose topologies are often unobservable and change over time. However, the sotermed adoption times when blogs mention popular news items, individuals in a community catch an infectious disease, or consumers adopt a trendy ..."
Abstract
 Add to MetaCart
promoting proximal gradient iterations, the improved convergence rate of accelerated variants, or reduced computational complexity of stochastic gradient descent. Numerical tests with both synthetic and real data demonstrate the effectiveness of the novel algorithms in unveiling sparse dynami
Exponential Convergence of a Gradient Descent Algorithm for a Class of Recurrent Neural Networks
 In Proceedings of the 38th Midwest Symposium on Circuits and Systems
, 1995
"... We investigate the convergence properties of a gradient descent learning algorithm for a class of recurrent neural networks. The networks compute an affine combination of nonlinear (sigmoidal) functions of the outputs of biased linear dynamical systems. The learning algorithm performs approximate gr ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
gradient descent to minimize the squared error on a training sequence of inputoutput data. We consider the convergence of the parameter estimates produced by this algorithm when the data sequence is generated by a network in this class. We assume that the sigmoid is analytic and bounded everywhere
Learning Probabilistic NonLinear Latent Variable Models for Tracking Complex Activities
"... A common approach for handling the complexity and inherent ambiguities of 3D human pose estimation is to use pose priors learned from training data. Existing approaches however, are either too simplistic (linear), too complex to learn, or can only learn latent spaces from “simple data”, i.e., single ..."
Abstract

Cited by 21 (2 self)
 Add to MetaCart
A common approach for handling the complexity and inherent ambiguities of 3D human pose estimation is to use pose priors learned from training data. Existing approaches however, are either too simplistic (linear), too complex to learn, or can only learn latent spaces from “simple data”, i
Geodesic Active Regions: A new framework to deal with frame partition problems in Computer Vision
, 2002
"... This paper presents a novel variational framework for dealing with frame partition problems in Computer Vision by the propagation of curves. This framework integrates boundary and regionbased frame partition modules under a curvebased energy framework, which aims at finding a set of minimal le ..."
Abstract

Cited by 85 (10 self)
 Add to MetaCart
information). The defined objective function is minimized using a gradient descent method. According to the obtained motion equations, the set of initial curves is propagated towards the best partition under the influence of boundary and regionbased forces, and being constrained by a regularity force
Results 1  10
of
208