Results 1 - 10 of 1,585

Policy gradient methods for reinforcement learning with function approximation.

by Richard S Sutton , David Mcallester , Satinder Singh , Yishay Mansour - In NIPS, , 1999
"... Abstract Function approximation is essential to reinforcement learning, but the standard approach of approximating a value function and determining a policy from it has so far proven theoretically intractable. In this paper we explore an alternative approach in which the policy is explicitly repres ..."
Abstract - Cited by 439 (20 self) - Add to MetaCart
and in the state-visitation distribution. In this paper we prove that an unbiased estimate of the gradient (1) can be obtained from experience using an approximate value function satisfying certain properties. Our result also suggests a way of proving the convergence of a wide variety of algorithms based on "

PCA-SIFT: A more distinctive representation for local image descriptors

by Yan Ke, Rahul Sukthankar , 2004
"... Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid [14] recently evaluated a variety of approaches and identified the SIFT [11] algorithm as being the most resistant to common image deforma ..."
Abstract - Cited by 591 (6 self) - Add to MetaCart
Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid [14] recently evaluated a variety of approaches and identified the SIFT [11] algorithm as being the most resistant to common image

Fronts propagating with curvature dependent speed: algorithms based on Hamilton–Jacobi formulations

by Stanley Osher, James A. Sethian , 1988
"... We devise new numerical algorithms, called PSC algorithms, for following fronts propagating with curvature-dependent speed. The speed may be an arbitrary function of curvature, and the front also can be passively advected by an underlying flow. These algorithms approximate the equations of motion, w ..."
Abstract - Cited by 1183 (60 self) - Add to MetaCart
, which resemble Hamilton-Jacobi equations with parabolic right-hand sides, by using techniques from hyperbolic conservation laws. Nonoscillatory schemes of various orders of accuracy are used to solve the equations, providing methods that accurately capture the formation of sharp gradients and cusps

An iterative image registration technique with an application to stereo vision

by Bruce D. Lucas, Takeo Kanade - In IJCAI81 , 1981
"... Image registration finds a variety of applications in computer vision. Unfortunately, traditional image registration techniques tend to be costly. We present a new image registration technique that makes use of the spatial intensity gradient of the images to find a good match using a type of Newton- ..."
Abstract - Cited by 2897 (30 self) - Add to MetaCart
Image registration finds a variety of applications in computer vision. Unfortunately, traditional image registration techniques tend to be costly. We present a new image registration technique that makes use of the spatial intensity gradient of the images to find a good match using a type of Newton

Shape modeling with front propagation: A level set approach

by Ravikanth Malladi, James A. Sethian, Baba C. Vemuri - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 1995
"... Shape modeling is an important constituent of computer vision as well as computer graphics research. Shape models aid the tasks of object representation and recognition. This paper presents a new approach to shape modeling which retains some of the attractive features of existing methods and over- ..."
Abstract - Cited by 808 (20 self) - Add to MetaCart
along its gradient field with constant speed or a speed that depends on the curvature. It is moved by solving a “Hamilton-Jacob? ’ type equation written for a function in which the interface is a particular level set. A speed term synthesizpd from the image is used to stop the interface in the vicinity

Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources

by Te-won Lee, Mark Girolami, Terrence J. Sejnowski , 1999
"... An extension of the infomax algorithm of Bell and Sejnowski (1995) is presented that is able blindly to separate mixed signals with sub- and supergaussian source distributions. This was achieved by using a simple type of learning rule first derived by Girolami (1997) by choosing negentropy as a proj ..."
Abstract - Cited by 314 (22 self) - Add to MetaCart
projection pursuit index. Parameterized probability distributions that have sub- and supergaussian regimes were used to derive a general learning rule that preserves the simple architecture proposed by Bell and Sejnowski (1995), is optimized using the natural gradient by Amari (1998), and uses the stability

Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation

by Nikos Paragios, Rachid Deriche - INTERNATIONAL JOURNAL OF COMPUTER VISION , 2002
"... This paper presents a novel variational framework to deal with frame partition problems in Computer Vision. This framework exploits boundary and region-based segmentation modules under a curve-based optimization objective function. The task of supervised texture segmentation is considered to demonst ..."
Abstract - Cited by 312 (9 self) - Add to MetaCart
by unifying region and boundary-based information as an improved Geodesic Active Contour Model. The defined objective function is minimized using a gradient-descent method where a level set approach is used to implement the obtained PDE. According to this PDE, the curve propagation towards the final solution

Interactive Digital Photomontage

by Aseem Agarwala, Mira Dontcheva, Maneesh Agrawala, Steven Drucker, Alex Colburn, Brian Curless, David Salesin, Michael Cohen - ACM TRANS. GRAPH , 2004
"... We describe an interactive, computer-assisted framework for combining parts of a set of photographs into a single composite picture, a process we call "digital photomontage." Our framework makes use of two techniques primarily: graph-cut optimization, to choose good seams within the consti ..."
Abstract - Cited by 304 (17 self) - Add to MetaCart
the constituent images so that they can be combined as seamlessly as possible; and gradient-domain fusion, a process based on Poisson equations, to further reduce any remaining visible artifacts in the composite. Also central to the framework is a suite of interactive tools that allow the user to specify a

A Comparison of Algorithms for Maximum Entropy Parameter Estimation

by Robert Malouf
"... A comparison of algorithms for maximum entropy parameter estimation Conditional maximum entropy (ME) models provide a general purpose machine learning technique which has been successfully applied to fields as diverse as computer vision and econometrics, and which is used for a wide variety of class ..."
Abstract - Cited by 290 (2 self) - Add to MetaCart
A comparison of algorithms for maximum entropy parameter estimation Conditional maximum entropy (ME) models provide a general purpose machine learning technique which has been successfully applied to fields as diverse as computer vision and econometrics, and which is used for a wide variety

Irradiance Gradients

by Gregory J. Ward, Paul S. Heckbert , 1992
"... A new method for improving the accuracy of a diffuse interreflection calculation is introduced in a ray tracing context. The information from a hemispherical sampling of the luminous environment is interpreted in a new way to predict the change in irradiance as a function of position and surface ori ..."
Abstract - Cited by 142 (2 self) - Add to MetaCart
orientation. The additional computation involved is modest and the benefit is substantial. An improved interpolation of irradiance resulting from the gradient calculation produces smoother, more accurate renderings. This result is achieved through better utilization of ray samples rather than additional
Results 1 - 10 of 1,585