Results 1 - 10 of 8,191

Rapid object detection using a boosted cascade of simple features

by Paul Viola, Michael Jones - ACCEPTED CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION 2001 , 2001
"... This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the " ..."
Abstract - Cited by 3283 (9 self) - Add to MetaCart
This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called

Face recognition: features versus templates

by Roberto Brunelli, Tomaso Poggio - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 1993
"... Over the last 20 years, several different techniques have been proposed for computer recognition of human faces. The purpose of this paper is to compare two simple but general strategies on a common database (frontal images of faces of 47 people: 26 males and 21 females, four images per person). We ..."
Abstract - Cited by 749 (25 self) - Add to MetaCart
). We have developed and implemented two new algorithms; the first one is based on the computation of a set of geometrical features, such as nose width and length, mouth position, and chin shape, and the second one is based on almost-grey-level template matching. The results obtained on the testing sets

An extended set of Haar-like features for rapid objection detection

by Rainer Lienhart, Jochen Maydt - IEEE ICIP
"... Recently Viola et al. [5] have introduced a rapid object detection scheme based on a boosted cascade of simple feature classifiers. In this paper we introduce a novel set of rotated haar-like features. These novel features significantly enrich the simple features of [5] and can also be calculated ef ..."
Abstract - Cited by 577 (4 self) - Add to MetaCart
Recently Viola et al. [5] have introduced a rapid object detection scheme based on a boosted cascade of simple feature classifiers. In this paper we introduce a novel set of rotated haar-like features. These novel features significantly enrich the simple features of [5] and can also be calculated

Valuing American options by simulation: A simple least-squares approach

by Francis A. Longstaff, Eduardo S. Schwartz - Review of Financial Studies , 2001
"... This article presents a simple yet powerful new approach for approximating the value of America11 options by simulation. The kcy to this approach is the use of least squares to estimate the conditional expected payoff to the optionholder from continuation. This makes this approach readily applicable ..."
Abstract - Cited by 517 (9 self) - Add to MetaCart
This article presents a simple yet powerful new approach for approximating the value of America11 options by simulation. The kcy to this approach is the use of least squares to estimate the conditional expected payoff to the optionholder from continuation. This makes this approach readily

Maximum Likelihood Linear Transformations for HMM-Based Speech Recognition

by M.J.F. Gales - COMPUTER SPEECH AND LANGUAGE , 1998
"... This paper examines the application of linear transformations for speaker and environmental adaptation in an HMM-based speech recognition system. In particular, transformations that are trained in a maximum likelihood sense on adaptation data are investigated. Other than in the form of a simple bias ..."
Abstract - Cited by 570 (68 self) - Add to MetaCart
) constrained, which requires the variance transform to have the same form as the mean transform (sometimes referred to as feature-space transforms). Re-estimation formulae for all appropriate cases of transform are given. This includes a new and efficient "full" variance transform and the extension

Keying hash functions for message authentication

by Mihir Bellare, Ran Canetti, Hugo Krawczyk , 1996
"... The use of cryptographic hash functions like MD5 or SHA for message authentication has become a standard approach inmanyInternet applications and protocols. Though very easy to implement, these mechanisms are usually based on ad hoc techniques that lack a sound security analysis. We present new cons ..."
Abstract - Cited by 611 (39 self) - Add to MetaCart
The use of cryptographic hash functions like MD5 or SHA for message authentication has become a standard approach inmanyInternet applications and protocols. Though very easy to implement, these mechanisms are usually based on ad hoc techniques that lack a sound security analysis. We present new

Decentralized Trust Management

by Matt Blaze, Joan Feigenbaum, Jack Lacy - In Proceedings of the 1996 IEEE Symposium on Security and Privacy , 1996
"... We identify the trust management problem as a distinct and important component of security in network services. Aspects of the trust management problem include formulating security policies and security credentials, determining whether particular sets of credentials satisfy the relevant policies, an ..."
Abstract - Cited by 1025 (24 self) - Add to MetaCart
approach to trust management, based on a simple language for specifying trusted actions and trust relationships. It also describes a prototype implementation of a new trust management system, called PolicyMaker, that will facilitate the development of security features in a wide range of network services

Light Field Rendering

by Marc Levoy , Pat Hanrahan , 1996
"... A number of techniques have been proposed for flying through scenes by redisplaying previously rendered or digitized views. Techniques have also been proposed for interpolating between views by warping input images, using depth information or correspondences between multiple images. In this paper, w ..."
Abstract - Cited by 1337 (22 self) - Add to MetaCart
, we describe a simple and robust method for generating new views from arbitrary camera positions without depth information or feature matching, simply by combining and resampling the available images. The key to this technique lies in interpreting the input images as 2D slices of a 4D function

The "Independent Components" of Natural Scenes are Edge Filters

by Anthony J. Bell, Terrence J. Sejnowski , 1997
"... It has previously been suggested that neurons with line and edge selectivities found in primary visual cortex of cats and monkeys form a sparse, distributed representation of natural scenes, and it has been reasoned that such responses should emerge from an unsupervised learning algorithm that attem ..."
Abstract - Cited by 617 (29 self) - Add to MetaCart
that attempts to find a factorial code of independent visual features. We show here that a new unsupervised learning algorithm based on information maximization, a nonlinear "infomax" network, when applied to an ensemble of natural scenes produces sets of visual filters that are localized and oriented

Online Learning with Kernels

by Jyrki Kivinen, Alexander J. Smola, Robert C. Williamson , 2003
"... Kernel based algorithms such as support vector machines have achieved considerable success in various problems in the batch setting where all of the training data is available in advance. Support vector machines combine the so-called kernel trick with the large margin idea. There has been little u ..."
Abstract - Cited by 2831 (123 self) - Add to MetaCart
use of these methods in an online setting suitable for real-time applications. In this paper we consider online learning in a Reproducing Kernel Hilbert Space. By considering classical stochastic gradient descent within a feature space, and the use of some straightforward tricks, we develop simple
Results 1 - 10 of 8,191