Baback Moghaddam

Handbook for the GREAT08 Challenge: An image analysis competition for cosmological lensing (2008)

Abstract — We extend the l0-norm “subspectral ” algorithms developed for sparse-LDA [5] and sparse-PCA [6] to more general quadratic costs such as MSE in linear (or kernel) regression. The...

Bridle, Sarah, Shawe-Taylor, John, Amara, Adam, Applegate, Douglas, Balan, Sreekumar T., Berge, Joel, ...

The GRavitational lEnsing Accuracy Testing 2008 (GREAT08) Challenge focuses on a problem that is of crucial importance for future observations in cosmology. The shapes of distant galaxies can be used...

Abstract (2008)

Baback Moghaddam, Gregory Shakhnarovich

We introduce a novel learning algorithm for binary classification with hyperplane discriminants based on pairs of training points from opposite classes (dyadic hypercuts). This algorithm is further...

Abstract (2008)

Visualization, Estimation and User-Modeling for Interactive Browsing (2008)

Sparse PCA seeks approximate sparse “eigenvectors ” whose projections capture the maximal variance of data. As a cardinality-constrained and non-convex optimization problem, it is NP-hard and is...

Qi Tian, Baback Moghaddam, Thomas S. Huang

Abstract. We present a user-centric system for visualization and layout for content-based image retrieval and browsing. Image features (visual and/or semantic) are analyzed to display and group...

Abstract Visualization & Layout for Image Libraries (2008)

Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas S. Huang

can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to build a more intuitive browser for retrieval, navigation and story-telling,...

HIGHER-ORDER DEPENDENCIES IN LOCAL APPEARANCE MODELS £ (2008)

David Guillamet, Baback Moghaddam, Jordi Vitrià

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple...

Factorized Local Appearance Models (2008)

Baback Moghaddam, Xiang Zhou

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple...

Abstract (2008)

Baback Moghaddam, Gregory Shakhnarovich

We introduce a novel learning algorithm for binary classification with hyperplane discriminants based on pairs of training points from opposite classes (dyadic hypercuts). This algorithm is further...

Factorized Local Appearance Models (2007)

Baback Moghaddam, Baback Moghaddam, Xiang Zhou, Xiang Zhou

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple...

Local Apearance-Based Models using High-Order Statistics of Image Features (2007)

Jordi Vitria, Baback Moghaddam, Baback Moghaddam, David Guillamet, David Guillamet, Jordi Vitrià

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple...

Boosted Dyadic Kernel Discriminants (2007)

Baback Moghaddam, Gregory Shakhnarovich

We introduce a novel learning algorithm for binary classification with hyperplane discriminants based on pairs of training points from opposite classes (dyadic hypercuts). This algorithm is further...

Generalized Ma. tching for Recognition and Retrieval m an Image Database (2007)

Chahab Nastar, Baback Moghaddam, Alex Pentl

We describe a novel approach for image matching based on deformable intensity surfaces. In this approach, the intensity surface of the image is modeled as a deformable 3D mesh in the (x, y, I(x, y))...

Image Retrieval with Local and Spatial Queries (2007)

Baback Moghaddam, Henning Biermann, Dimitris Margaritis

To date most "content-based image retrieval" (CBIR) techniques rely on global attributes such as color or texture histograms which unfortunately ignore the spatial composition of...

Statistical Learning of Physically-Based Deformations (2007)

Chahab Nastar, Baback Moghaddam, Alex Pentl

We describe a novel approach for image matching based on deformable intensity surfaces. In this approach, the intensity surface of the image is modeled as a deformable 3D mesh in the (x; y; I(x;y))...

2 (2007)

Qi Tian, Baback Moghaddam, Thomas S. Huang

In this paper, we propose a technique to visualize a multitude of images on a 2-D screen based on their visual features (color, texture, structure, etc.). The resulting layout will automatically...

2 (2007)

Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas Huang

Abstract. In this paper, we present visualization and layout algorithms that can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to...

Fast Pixel/Part Selection with Sparse Eigenvectors (2007)

Spectral Bounds for Sparse PCA: Exact and Greedy Algorithms (2006)

We extend the ”Sparse LDA ” algorithm of [7] with new sparsity bounds on 2-class separability and efficient partitioned matrix inverse techniques leading to 1000-fold speed-ups. This mitigates...

Spectral Bounds for Sparse PCA: Exact and Greedy Algorithms (2006)

Sparse PCA seeks approximate sparse "eigenvectors" whose projections capture the maximal variance of data. As a cardinality-constrained and non-convex optimization problem, it is NP-hard...

Generalized spectral bounds for sparse LDA (2006)

Sparse PCA seeks approximate sparse "eigenvectors" whose projections capture the maximal variance of data. As a cardinality-constrained and non-convex optimization problem, it is NP-hard...

Mitsubishi Electric Research Laboratories (2005)

We present a discrete spectral framework for the sparse or cardinality-constrained solution of a generalized Rayleigh quotient. This NPhard combinatorial optimization problem is central to supervised...

Http Www Merl, Jinho Lee, Raghu Machiraju, Hanspeter Pfister, Baback Moghaddam

this paper we present a novel framework that acquires the 3D shape, texture, pose and illumination of a face from a single photograph. Additionally, we show how we can recreate a face under varying...

Mitsubishi Electric Research Laboratories (2005)

Http Www Merl, Kuang-chih Lee, Kuang-chih Lee, Baback Moghaddam, Baback Moghaddam

We propose a simplified and practical computational technique for estimating directional lighting in uncalibrated images of faces in frontal pose. We show that this inverse problem can be solved...

A Bilinear Illumination Model for Robust Face Recognition (2005)

Jinho Lee, Jinho Lee, Baback Moghaddam, Baback Moghaddam, Hanspeter Pfister, Hanspeter Pfister, ...

this paper belongs to this latter camp, yet has key differences and presents both computational and modeling advantages not shared by other techniques. For example, it easily surpasses the...

A practical face relighting method for directional lighting normalization (2005)

Kuang-chih Lee, Kuang-chih Lee, Baback Moghaddam, Baback Moghaddam

We propose a simplified and practical computational technique for estimating directional lighting in uncalibrated images of faces in frontal pose. We show that this inverse problem can be solved...

A bilinear illumination model for robust face recognition (2005)

Jinho Lee, Jinho Lee, Baback Moghaddam, Baback Moghaddam, Hanspeter Pfister, Hanspeter Pfister, ...

We present a technique to generate an illumination subspace for arbitrary 3D faces based on the statistics of measured illuminations under variable lighting conditions from many subjects. A bilinear...

A practical face relighting method for directional lighting normalization (2005)

Kuang-chih Lee, Baback Moghaddam

Abstract. We propose a simplified and practical computational technique for estimating directional lighting in uncalibrated images of faces in frontal pose. We show that this inverse problem can be...

Finding Optimal Views for 3D Face Shape Modeling (2004)

Jinho Lee, Baback Moghaddam, Hanspeter Pfister, Raghu Machiraju

A fundamental problem in multi-view 3D face modeling is the determination of the set of optimal views required for accurate 3D shape estimation for a generic face. There is no analytical solution to...

Appearance tracking using adaptive models in a particle filter (2004)

Shaohua Zhou, Shaohua Kevin Zhou, Baback Moghaddam, Baback Moghaddam

The particle filter is a popular tool for visual tracking. Usually, the appearance model is either fixed or rapidly changing and the motion model is simply a random walk with fixed noise variance....

Visual tracking and recognition using appearance-adaptive models in particle filters (2004)

Shaohua Zhou, Baback Moghaddam

We propose an approach that incorporates appearance-based models in a particle filter to realize robust visual tracking and recognition algorithms. In conventional tracking algorithms, the appearance...

Face Recognition in Subspaces (2004)

Gregory Shakhnarovich, Gregory Shakhnarovich, Baback Moghaddam, Baback Moghaddam

Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision research in general, has witnessed a...

Finding Optimal Views for 3D Face Shape Modeling (2004)

Jinho Lee, Jinho Lee, Baback Moghaddam, Baback Moghaddam, Hanspeter Pfister, Hanspeter Pfister, ...

A fundamental problem in multi-view 3D face modeling is the determination of the set of optimal views (poses) required for accurate 3D shape estimation of a generic face. There is no analytical...

Appearance Tracking Using Adaptive Models in a Particle Filter (2004)

Shaohua Kevin Zhou, Rama Chellappa, Baback Moghaddam

The particle filter is a popular tool for visual tracking. Usually, the appearance model is either fixed or rapidly changing, and the motion model is simply a random walk with fixed noise variance....

Mitsubishi Electric Research Laboratories (2004)

Http Www Merl, Shaohua Zhou, Baback Moghaddam, Shaohua Kevin Zhou

Intra-personal space modeling proposed by Moghaddam et al. has been successfully applied in face recognition. In their work the regular principal subspaces are derived from the intra-personal space...

Visual Tracking and Recognition Using Appearance-Adaptive Models in Particle Filters (2004)

Shaohua Zhou, Rama Chellappa, Baback Moghaddam

this paper, we overcome this by introducing an adaptive-velocity model. While contour is the visual cue used in many tracking algorithms [2], another class of tracking approaches [8], [9], [7]...

Visualization & User-Modeling for Browsing Personal Photo Libraries (2004)

Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas S. Huang

We present a user-centric system for visualization and layout for content-based image retrieval. Image features (visual and/or semantic) are used to display retrievals as thumbnails in a 2-D spatial...

Visual Tracking and Recognition Using Appearance-Adaptive Models in Particle Filters (2004)

Shaohua Kevin Zhou, Rama Chellappa, Baback Moghaddam

We present an approach that incorporates appearance-adaptive models in a particle filter to realize robust visual tracking and recognition algorithms. Tracking needs modeling inter-frame motion and...

Modelbased 3D face capture with shape-from-silhouettes (2003)

Baback Moghaddam, Jinho Lee, Hanspeter Pfister, Raghu Machiraju

We present a method for 3D face acquisition using a set or sequence of 2D binary silhouettes. Since silhouette images depend only on the shape and pose of an object, they are immune to lighting...

Local Appearance-Based Models using High-Order Statistics of Image Features (2003)

Baback Moghaddam, David Guillamet, Jordi Vitrià

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple...

Higher-Order Dependencies in Local Appearance Models (2003)

Jordi Vitria, David Guillamet, David Guillamet, Baback Moghaddam, Baback Moghaddam, Jordi Vitrià

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple...

Silhouette-Based 3D Face Shape Recovery (2003)

J. Lee, B. Moghaddam, H. Pfister, R. Machiraju, Jinho Lee, Baback Moghaddam, ...

In this paper we present a novel method to obtain the 3D shape of an arbitrary human face using a sequence of silhouette images as input. Our face model is a linear combination of eigenheads, which...

Adaptive Visual Tracking and Recognition using Particle Filters (2003)

Shaouha Zhou, Rama Chellappa, Shaohua Zhou, Baback Moghaddam, Baback Moghaddam

This paper presents an improved method for simultaneous tracking and recognition of human faces from video where a time series model is used to resolve the uncertainties in tracking and recognition....

Mitsubishi Electric Research Laboratories (2003)

Http Www Merl, David Guillament, Jordi Vitria, Baback Moghaddam, Baback Moghaddam, David Guillamet, ...

Visualization and layout for personal photo libraries (2003)

Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas Huang

Abstract. In this paper, we present visualization and layout algorithms that can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to...

Silhouette-based 3d face shape recovery (2003)

Jinho Lee, Baback Moghaddam, Hanspeter Pfister, Raghu Machiraju

The creation of realistic 3D face models is still a fundamental problem in computer graphics. In this paper we present a novel method to obtain the 3D shape of an arbitrary human face using a...

Higher-Order Dependencies in Local Appearance Models (2003)

David Guillamet, Baback Moghaddam, Jordi Vitrià

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple...

Silhouette-Based 3D Face Shape Recovery (2003)

Jinho Lee Baback, Jinho Lee, Baback Moghaddam, Hanspeter Pfister, Raghu Machiraju

The creation of realistic 3D face models is still a fundamental problem in computer graphics. In this paper we present a novel method to obtain the 3D shape of an arbitrary human face using a...

Mitsubishi Electric Research Laboratories (2003)

Http Www Merl, Baback Moghaddam, Baback Moghaddam, Jinho Lee, Jinho Lee, Hanspeter Pfister, ...

this paper, we present two systems that recover 3D shape of a human face (and consequently its 2D texture-map as well) from a sequence of silhouette images using an underlying model-based 3D face...

PDH: A human-Centric Interface for Image Libraries (2002)

Baback Moghaddam, Baback Moghaddam, Qi Tian, Qi Tian, Neal Lesh, Neal Lesh, ...

We present visualization and layout algorithms that can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to build a more intuitive...

A Unified Learning Framework for Real Time Face Detection and Classification (2002)

Gregory Shakhnarovich, Paul A. Viola, Baback Moghaddam

This paper presents progress toward an integrated, robust, real-time face detection and demographic analysis system. Faces are detected and extracted using the fast algorithm recently proposed by...

A Unified Learning Framework for Real Time Face Detection and Classification (2002)

Gregory Shakhnarovich, Paul A. Viola, Baback Moghaddam

This paper presents progress toward an integrated, robust, real-time face detection and demographic analysis system. Faces are detected and extracted using the fast algorithm recently proposed by...

Visualization, Estimation and User-Modeling for Interactive Browsing (2002)

Baback Moghaddam, Baback Moghaddam, Qi Tian, Qi Tian, Thomas S. Huang, Thomas S. Huang

We present a user-centric system for visualization and layout for content-based image retrieval and browsing. Image features (visual and/or semantic) are analyzed to display and group retrievals as...

A Unified Learning Framework for Real Time Face Detection and Classification (2002)

Paul Viola, Gregory Shakhnarovich, Gregory Shakhnarovich, Paul A. Viola, Baback Moghaddam, 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...

Visualization, Estimation and User-Modeling for (2002)

Interactive Browsing Of, Qi Tian T, Baback Moghaddam

We present a user-centric system for visualization and layout for content-based image retrieval and browsing. Image features (visual and/or semantic) are analyzed to display and group retrievals as...

Mitsubishi Electric Research Laboratories (2002)

Http Www Merl, Baback Moghaddam, Xiang Zhou

this paper, we will focus our attention on the modeling of images and objects through the use of joint histograms. Figure 1 provides an overview diagram of our histogram-based image and object model....

A Unified Learning Framework for Real Time Face Detection and Classification (2002)

Gregory Shakhnarovich, Paul A. Viola, Baback Moghaddam

This paper presents progress toward an integrated, robust, real-time face detection and demographic analysis system. Faces are detected and extracted using the fast algorithm recently proposed by...

Principal manifolds and probabilistic subspaces for visual recognition (2002)

Learning gender with support faces (2002)

We investigate the use of linear and nonlinear principal manifolds for learning low-dimensional representations for visual recognition. Several leading techniques: Principal Component Analysis (PCA),...

Baback Moghaddam, Ming-hsuan Yang

appearance-based gender classification with low-resolution ªthumbnailº faces processed from 1,755 images from the FERET face database. The performance of SVMs �3.4 percent error) is shown to be...

PDH: A human-Centric Interface for Image Libraries (2002)

Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas S. Huang

can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to build a more intuitive browser for retrieval, navigation and story-telling,...

Personal Digital Historian: User interface design (2001)

Ryan Scott Bardsley, Chia Shen, Chia Shen, Neal Lesh, Neal Lesh, Baback Moghaddam, ...

Desktop computers are not designed for multi-person face-to-face conversation in a social setting. We describe the design of a novel user interface for multi-user interactive informal storytelling....

ICA-based Probabilistic Local Appearance Models (2001)

Xiang Zhou, Thomas Huang, Xiang Sean Zhou, Baback Moghaddam, Baback Moghaddam, Thomas S. Huang

This paper proposes a novel image modeling scheme for object detection and localization. Object appearance is modeled by the joint distribution of k-tuple salient point feature vectors which are...

Personal Digital Historian: User interface design (2001)

Chia Shen, Neal Lesh, Baback Moghaddam, Paul Beardsley

Desktop computers are not designed for multi-person faceto-face conversation in a social setting. We describe the design of a novel user interface for multi-user interactive informal storytelling....

Spatial visualization for content-based image retrieval (2001)

Baback Moghaddam, Qi Tian, Thomas S. Huang

In traditional content-based image retrieval (CBIR), the retrieved images are displayed in order of decreasing similarities from the query and can be considered as a 1-D display. In this paper, a...

Spatial Visualization for Content-Based Image Retrieval (2001)

Thomas S. Huang, Baback Moghaddam, Baback Moghaddam, Qi Tian, Qi Tian, Thomas S. Huang

In traditional content-based image retrieval (CBIR), the retrieved images are displayed in order of decreasing similarities from the query and can be considered as a 1-D display. In this paper, a...

ICA-based Probabilistic Local Appearance Models (2001)

Xiang Zhou, Thomas Huang, Xiang Sean Zhou, Baback Moghaddam, Baback Moghaddam, Thomas S. Huang

This paper proposes a novel image modeling scheme for object detection and localization. Object appearance is modeled by the joint distribution of k-tuple salient point feature vectors which are...

Personal Digital Historian: User interface design (2001)

Ryan Scott Bardsley, Chia Shen, Chia Shen, Neal Lesh, Neal Lesh, Baback Moghaddam, ...

Desktop computers are not designed for multi-person face-to-face conversation in a social setting. We describe the design of a novel user interface for multi-user interactive informal storytelling....

Personal Digital Historian: User interface design (2001)

Chia Shen, Neal Lesh, Baback Moghaddam, Paul Beardsley

Desktop computers are not designed for multi-person faceto-face conversation in a social setting. We describe the design of a novel user interface for multi-user interactive informal storytelling....

ICA-based Probabilistic Local Appearance Models (2001)

Xiang Sean Zhou, Baback Moghaddam, Thomas S. Huang

This paper proposes a novel image modeling scheme for object detection and localization. Object appearance is modeled by the joint distribution of k-tuple salient point feature vectors which are...

Spatial visualization for content-based image retrieval (2001)

Baback Moghaddam, Qi Tian, Thomas S. Huang

In traditional content-based image retrieval (CBIR), the retrieved images are displayed in order of decreasing similarities from the query and can be considered as a 1-D display. In this paper ∗ ,...

Display Optimization for Image Browsing (2001)

Qi Tian, Baback Moghaddam, Thomas S. Huang

Abstract. ∗ In this paper, we propose a technique to visualize a multitude of images on a 2-D screen based on their visual features (color, texture, structure, etc.). The resulting layout will...

Sex with Support Vector Machines (2000)

Baback Moghaddam, Ming-hsuan Yang

Nonlinear Support Vector Machines (SVMs) are investigated for visual sex classification with low resolution "thumbnail " faces (21by-12 pixels) processed from 1,755 images from the...

Gender Classification with Support Vector Machines (2000)

Baback Moghaddam, Ming-Hsuan Yang

Support Vector Machines (SVMs) are investigated for visual gender classification with low-resolution "thumbnail " faces (21-by-12 pixels) processed from 1,755 images from the FERET face...

Gender Classication with Support Vector Machine (2000)

Ming-hsuan Yang, Baback Moghaddam, Baback Moghaddam

Support Vector Machines (SVMs) are investigated for visual gender classification with low resolution "thumbnail" faces (21-by-12 pixels) processed from 1755 images from the FERET face...

Gender Classi cation with Support Vector Machines (2000)

Baback Moghaddam, Ming-hsuan Yang, Baback Moghaddam, Ming-hsuan Yang

Support Vector Machines (SVMs) are investigated for visual gender classification with low resolution ¨thumbnail¨faces (21-by-12 pixels) processed from 1,755 images from the FERET face database. The...

Gender classification with support vector machines (2000)

Principal manifolds and Bayesian subspaces for visual recognition (1999)

Support Vector Machines (SVMs) are investigated for visual gender classification with low resolution “thumbnail” faces (21-by-12 pixels) processed from 1,755 images from the FERET face database....

Baback Moghaddam, Baback Moghaddam

We investigate the use of linear and nonlinear principal manifolds for learning lowdimensional representations for visual recognition. Three techniques: Principal Component Analysis (PCA),...

Regionsof-interest and spatial layout in content based image retrieval (1999)

Baback Moghaddam, Baback Moghaddam, Henning Biermann, Henning Biermann, Dimitris Margaritis, Dimitris Margaritis

To date most "content-based image retrieval " (CBIR) techniques rely on global attributes such as color or texture histograms which tend to ignore the spatial composition of the...

Defining image content with multiple regions-of-interest (1999)

Baback Moghaddam, Henning Biermann, Dimitris Margaritis

With the proliferation of multimedia, the web and digital imaging, there now exists a high demand for intelligent tools for image management, most importantly indexing, search and retrieval, commonly...

Defining Image Content with Multiple Regions-of-Interest (1999)

Baback Moghaddam, Henning Biermann, Dimitris Margaritis

With the proliferation of multimedia, the web and digital imaging, there now exists a high demand for intelligent tools for image management, most importantly indexing, search and retrieval, commonly...

Principal Manifolds and Bayesian Subspaces for Visual Recognition (1999)

De ning Image Content with (1999)

Weinvestigate the use of linear and nonlinear principal manifolds for learning lowdimensional representations for visual recognition. Three techniques: Principal Component Analysis #PCA#, Independent...

Baback Moghaddam, Henning Biermann, Dimitris Margaritis, Baback Moghaddam, Henning Biermann, Dimitris Margaritis

With the proliferation of multimedia, the web and digital imaging, there now exists a high demand for intelligent tools for image management, most importantly indexing, search and retrieval, commonly...

Bayesian modeling of facial similarity (1998)

Baback Moghaddam, Tony Jebara, Alex Pentl

In previous work [6, 9, 10], we advanced a new technique for direct visual matching of images for the purposes of face recognition and image retrieval, using a probabilistic measure of similarity...

Beyond Euclidean Eigenspaces: Bayesian Matching for Visual Recognition (1998)

Bayesian Modeling of Facial Similarity (1998)

We propose a novel technique for direct visual matching of images for the purposes of face recognition and database search. Speci#cally,we argue in favor of a probabilistic measure of similarity, in...

Baback Moghaddam, Tony Jebara, Alex Pentland

In previous work [6, 9, 10], we advanced a new technique for direct visual matching of images for the purposes of face recognition and image retrieval, using a probabilistic measure of similarity...

Beyond Eigenfaces: Probabilistic Matching for Face Recognition (1998)

Baback Moghaddam, Wasiuddin Wahid, Alex Pentland

We propose a novel technique for direct visual matching of images for the purposes of face recognition and database search. Specifically, we argue in favor of a probabilistic measure of similarity,...

Beyond Euclidean Eigenspaces: Bayesian Matching for Visual Recognition (1998)

Bayesian modeling of facial similarity (1998)

We propose a novel technique for direct visual matching of images for the purposes of face recognition and database search. Specifically, we argue in favor of a probabilistic measure of similarity,...

Baback Moghaddam, Tony Jebara, Alex Pentl

In previous work [6, 9,10],weadvanced a new technique for direct visual matching of images for the purposes of face recognition and image retrieval, using a probabilistic measure of similarity based...

Beyond Euclidean Eigenspaces: Bayesian Matching for Visual Recognition”, Face Recognition: From Theories to Applications (1998)

Baback Moghaddam, Alex Pentl

We propose a novel technique for direct visual matching of images for the purposes of face recognition and database search. Specifically, we argue in favor of a probabilistic measure of similarity,...

Probabilistic visual learning for object detection (1997)

Moghaddam, Baback

Bayesian face recognition using deformable intensity surfaces (1996)

Baback Moghaddam, Chahab Nastar, Alex Pentl

We describe a novel technique for face recognition based on deformable intensity surfaces which incorporates both the shape and texture components of the 2D image. The intensity surface of the facial...

Baback Moghaddam, Chahab Nastar, Alex Pentl

We propose a probabilistic similarity measure for direct image matching based on a Bayesian analysis of image deformations. We model two classes of variation in object appearance: intra-object and...

Probabilistic Visual Learning for Object Representation (1996)

Bayesian Face Recognition using Deformable Intensity Surfaces (1996)

We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived...

Baback Moghaddam, Chahab Nastar, Alex Pentland

We describe a novel technique for face recognition based on deformable intensity surfaces which incorporates both the shape and texture components of the 2D image. The intensity surface of the facial...

Generalized Matching for Recognition and Retrieval in an Image Database (1996)

Chahab Nastar, Baback Moghaddam, Alex Pentland

We describe a novel approach for image matching based on deformable intensity surfaces. In this approach, the intensity surface of the image is modeled as a deformable 3D mesh in the (x; y; I(x; y))...

Active Face Tracking and Pose Estimation in an Interactive Room (1996)

Trevor Darrell, Baback Moghaddam, Alex P. Pentland

We demonstrate real-time face tracking and pose estimation in an unconstrained office environment with an active foveated camera. Using vision routines previously implemented for an interactive...

Probabilistic Visual Learning for Object Representation (1996)

Bayesian face recognition using deformable intensity surfaces (1996)

We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived...

Baback Moghaddam, Chahab Nastar, Alex Pentl

We describe a novel technique for face recognition based on deformable intensity surfaces which incorporates both the shape and texture components of the 2D image. The intensity surface of the facial...

A Subspace Method for Maximum Likelihood Target Detection (1995)

Probabilistic Visual Learning for Object Detection (1995)

We present an unsupervised technique for visual target modeling which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. A computationally efficient and...

An Automatic System for Model-Based Coding of Faces (1995)

We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived...

An automatic system for model-based coding of faces (1995)

We present a fully automatic system for 2D model-based image coding of human faces for potential applications such as video telephony, database image compression, and face recognition. The system...

Baback Moghaddam, Alex Pentl

We present a fully automatic system for 2D model-based image coding of human faces for potential applications such as video telephony, database image compression, and face recognition. The system...

View-Based and Modular Eigenspaces for Face Recognition (1994)

Alex Pentland, Baback Moghaddam, Thad Starner

In this work we describe experiments with eigenfaces for recognition and interactive search in a large-scale face database. Accurate visual recognition is demonstrated using a database of

Face Recognition using View-Based and Modular Eigenspaces (1994)