Merl -- A Mitsubishi Electric Research Laboratory (2004)
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...
Interactive Information Extraction (2004)
Trausti Kristjansson, Aron Culotta, Paul Viola, Andrew Mccallum
Information Extraction methods can be used to automatically "fill-in" database forms from unstructured data such as Web documents or email. State-of-the-art methods have achieved low error rates but...
Restructuring Sparse High Dimensional Data for (2004)
Charles Lee Isbell, Paul Viola
The task in text retrieval is to find the subset of a collection of documents relevant to a user's information request, usually expressed as a set of words. Classically, documents and queries are...
Rapid Object Detection using a Boosted Cascade of Simple Features (2004)
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...
Accepted Conference On Computer Vision And Pattern Recognition 2001 (2004)
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...
Boosting Image Retrieval (2003)
We present an approach for image retrieval using a very large number of highly selective features and efficient online learning. Our approach is predicated on the assumption that each image is...
Fast Pose Estimation with Parameter-Sensitive Hashing (2003)
Gregory Shakhnarovich, Paul Viola, Trevor Darrell
Example-based methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and high-dimensional problems such as...
Mitsubishi Electric Research Laboratories (2003)
This paper extends the face detection framework proposed by Viola and Jones 2001 to handle profile views and rotated faces. As in the work of Rowley et al 1998. and Schneiderman et al. 2000, we build...
Mitsubishi Electric Research Laboratories (2003)
Paul Viola, Michael Jones, Daniel Snow
This paper describes a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive...
Fast Pose Estimation with Parameter-Sensitive Hashing (2003)
Gregory Shakhnarovich, Paul Viola, Trevor Darrell
Example-based methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and high-dimensional problems such as...
Unsupervised Improvement of Visual Detectors using Co-Training (2003)
Anat Levin, Paul Viola, Yoav Freund
One significant challenge in the construction of visual detection systems is the acquisition of sufficient labeled data. This paper describes a new technique for training visual detectors which...
A Unified Learning Framework for Real Time Face Detection & Classification (2003)
Gregory Shakhnarovich, Paul Viola, Baback Moghaddam
This paper presents progress toward an integrated face detection and demographic analysis system that is robust and works in real-time. Faces are detected and extracted using the very fast algorithm...
Mitsubishi Electric Research Laboratories (2003)
This paper presents a new method for face recognition which learns a face similarity measure from example image pairs. A set of computationally efficient "rectangle" features are described which act...
Fast Pose Estimation with Parameter Sensitive Hashing (2003)
Gregory Shakhnarovich, Paul Viola
Example-based methods' are effective for parameter estimation problems when the underlying system is' simple or the dimensionality of the input is' low. For complex and high-dimensional problems such...
Fast Pose Estimation with Parameter Sensitive Hashing (2003)
Shakhnarovich, Gregory, Viola, Paul, Darrell, Trevor
Example-based methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and high-dimensional problems such as...
Fast Pose Estimation with Parameter Sensitive Hashing (2003)
Shakhnarovich, Gregory, Viola, Paul, Darrell, Trevor
Example-based methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and high-dimensional problems such as...
Restructuring Sparse High Dimensional Data for Effective Retrieval (2002)
Charles Lee Isbell, Paul Viola
The task in text retrieval is to find the subset of a collection of documents relevant to a user's information request, usually expressed as a set of words. Classically, documents and queries are...
We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is...
Second International Workshop On Statistical And Computational Theories Of (2002)
This paper describes a visual object detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is...
Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade (2002)
This paper develops a new approach for extremely fast detection in domains where the distribution of positive and negative examples is highly skewed (e.g. face detection or database retrieval). In...
Robust Real-time Object Detection (2001)
This paper describes a visual object detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is...
Rapid Object Detection using a Boosted Cascade of Simple Features (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...
Cooperative Control of a Semi-Autonomous Mobile Robot (2001)
Consider the differences between riding a horse and driving an automobile. A horse will not run into a telephone pole at high speed. If you fall asleep in the saddle, a horse will continue to follow...
We present an approach for image retrieval using a very large number of highly selective features and efficient online learning. Our approach is' predicated on the assumption that each image is'...
Learning Joint Statistical Models for Audio-Visual Fusion and Segregation (2001)
John W. Fisher Iii, Trevor Darrell, William T. Freeman, Paul Viola
People can understand complex auditory and visual information, often using one to disambiguate the other. Automated analysis, even at a lowlevel, faces severe challenges, including the lack of...
Multi-Modal Volume Registration by Maximization of Mutual Information (2000)
William M. Wells Iii, Paul Viola, Hideki Atsumi, Ron Kikinis
A new information-theoretic approach is presented for finding the registration of volumetric medical images of di#ering modalities. Registration is achieved by adjustment of the relative position and...
Face Detection and Recognition in Office Environments (2000)
Paul Viola, Arthur C. Smith, Jeffrey S. Norris
The Gatekeeper is a vision-based door security system developed at the MIT Artificial Intelligence Laboratory. Faces are detected in a real-time video stream using an efficient algorithmic approach,...
Boosting Image Retrieval (2000)
We present an approach for image retrieval using a very large number of highly selective features and efficient online learning. Our approach is predicated on the assumption that each image is...
Exact Voxel Occupancy with Graph Cuts (470) (2000)
Dan Snow, Paul Viola, Ramin Zabih
Voxel occupancy is one approach for reconstructing the 3-dimensional shape of an object from multiple views. In voxel occupancy, the task is to produce a binary labeling of a set of voxels, that...
Boosting Image Database Retrieval (1999)
We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is...
Boosting Image Database Retrieval (1999)
We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is...
Boosting Image Database Retrieval (1999)
We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is...
Boosting Image Database Retrieval (1999)
We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is...
Boosting Image Database Retrieval (1999)
We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is...
A Cluster-Based Statistical Model for Object Detection (1999)
Thomas D. Rikert, Michael J. Jones, Paul Viola
This paper presents an approach to object detection which is based on recent work in statistical models for texture synthesis and recognition [7, 4, 23, 17]. Our method follows the texture...
A Cluster-Based Statistical Model for Object Detection (1999)
Thomas D. Rikert, Michael J. Jones, Paul Viola
This paper presents an approach to object detection which is based on recent work in statistical models for texture synthesis and recognition [7, 4, 23, 17]. Our method follows the texture...
Nonparametric Estimation of Aspect Dependence for ATR (1999)
Andrew Kim, John Fisher, Alan Willsky, Paul Viola
In conventional SAR image formation, idealizations are made about the underlying scattering phenomena in the target field. In particular, the reflected signal is modeled as a pure delay and scaling...
Empirical Entropy Manipulation for Real-World Problems (1999)
Paul Viola, Nicol N. Schraudolph, Terrence J. Sejnowski
No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is...
Empirical Entropy Manipulation for Real-World Problems (1999)
Paul Viola, Nicol N. Schraudolph, Terrence J. Sejnowski
No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is...
Restructuring Sparse High Dimensional Data for Effective Retrieval (1998)
The task in text retrieval is to find the subset of a collection of documents relevant to a user's information request, usually expressed as a set of words. Classically, documents and queries are...
Restructuring Sparse High Dimensional Data for Effective Retrieval (1998)
The task in text retrieval is to find the subset of a collection of documents relevant to a user's information request, usually expressed as a set of words. Classically, documents and queries are...
Flexible Histograms: A Multiresolution Target Discrimination Model (1998)
Jeremy S. De Bonet, Paul Viola, John Fisher
In previous work we have developed a methodology for texture recognition and synthesis that estimates and exploits the dependencies across scale that occur within images. 1,2 In this paper we discuss...
Multi-Modal Volume Registration by Maximization of Mutual Information (1998)
William M. Wells Iii, Paul Viola, Hideki Atsumi, Shin Nakajima, Ron Kikinis
A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative position...
Multi-Modal Volume Registration by Maximization of Mutual Information (1998)
William M. Wells Iii, Paul Viola, Hideki Atsumi, Shin Nakajima, Ron Kikinis
A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative position...
Empirical Entropy Manipulation for Real-World Problems (1998)
Paul Viola, Nicol N. Schraudolph, Terrence J. Sejnowski
No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is...
MIMIC: Finding Optima by Estimating Probability Densities (1997)
Jeremy S. De Bonet, Charles L. Isbell, Paul Viola
In many optimization problems, the structure of solutions reflects complex relationships between the different input parameters. For example, experience may tell us that certain parameters are...
MIMIC: Finding Optima by Estimating Probability Densities (1997)
Jeremy S. De Bonet, Charles L. Isbell, Paul Viola
In many optimization problems, the structure of solutions reflects complex relationships between the different input parameters. For example, experience may tell us that certain parameters are...
Alignment by Maximization of Mutual Information (1997)
Paul Viola, William M. Wells Iii, Harvard Medical School
A new approach is presented for finding the pose of an object model in an image. The technique does not require information about the surface properties of the object, besides its shape, and is...
MIMIC: Finding Optima by Estimating Probability Densities (1997)
Jeremy S. De Bonet, Charles L. Isbell, Paul Viola
In many optimization problems, the structure of solutions reflects complex relationships between the different input parameters. For example, experience may tell us that certain parameters are...
Alignment by Maximization of Mutual Information (1997)
Paul Viola, William M. Wells Iii, Harvard Medical School
A new approach is presented for finding the pose of an object model in an image.
MIMIC: Finding Optima by Estimating Probability Densities (1997)
Jeremy S. De Bonet, Charles L. Isbell, Paul Viola
In many optimization problems, the structure of solutions reflects complex relationships between the different input parameters. For example, experience may tell us that certain parameters are...
Image Guided Microscopic Surgery System Using Mutual-Information Based Registration (1996)
Nobuhiko Hata, William M. Wells Iii, Michael Halle, Paul Viola, Ron Kikinis, Ferenc A. Jolesz
. We have developed an image guided microscopic surgery system for the navigation of surgical procedures that can overlay renderings of anatomical structures that are otherwise invisible. A new...
Image Guided Microscopic Surgery System Using Mutual-Information Based Registration (1996)
Nobuhiko Hata, William M. Wells Iii, Michael Halle, Paul Viola, Ron Kikinis, Ferenc A. Jolesz
. We have developed an image guided microscopic surgery system for the navigation of surgical procedures that can overlay renderings of anatomical structures that are otherwise invisible. A new...
Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects (1996)
We have developed a new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features. This framework can be...
Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects (1996)
We have developed a new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features. This framework can be...
Empirical Entropy Manipulation for Real-World Problems (1996)
Paul Viola, Nicol N. Schraudolph, Terrence J. Sejnowski
No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is...
Multi-Modal Volume Registration by Maximization of Mutual Information (1996)
William M. Wells Iii, Paul Viola, Hideki Atsumi, Shin Nakajima, Ron Kikinis
A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative position...
Multi-Modal Volume Registration by Maximization of Mutual Information (1996)
William M. Wells Iii, Paul Viola, Ron Kikinis
A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative pose until...
Multi-Modal Volume Registration by Maximization of Mutual Information (1996)
William M. Wells Iii, Paul Viola, Hideki Atsumi, Shin Nakajima, Ron Kikinis
A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative position...
Multi-Modal Volume Registration by Maximization of Mutual Information (1996)
William M. Wells Iii, Paul Viola, Hideki Atsumi, Shin Nakajima, Ron Kikinis
A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative position...
Empirical Entropy Manipulation for Real-World Problems (1996)
Paul Viola, Nicol N. Schraudolph, Terrence J. Sejnowski
No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is...
Empirical Entropy Manipulation for Real-World Problems (1995)
Paul Viola, Nicol N. Schraudolph, Terrence J. Sejnowski
No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is...