Search For:

Displaying 1-35 out of 35 total
Source constrained clustering
Found in: Computer Vision, IEEE International Conference on
By Ekaterina Taralova,Fernando De la Torre,Martial Hebert
Issue Date:November 2011
pp. 1927-1934
We consider the problem of quantizing data generated from disparate sources, e.g. subjects performing actions with different styles, movies with particular genre bias, various conditions in which images of objects are taken, etc. These are scenarios where ...
 
Semi-supervised learning of multi-factor models for face de-identification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ralph Gross, Latanya Sweeney, Fernando de la Torre, Simon Baker
Issue Date:June 2008
pp. 1-8
With the emergence of new applications centered around the sharing of image data, questions concerning the protection of the privacy of people visible in the scene arise. Recently, formal methods for the de-identification of images have been proposed which...
 
Model-Based Face De-Identification
Found in: Computer Vision and Pattern Recognition Workshop
By Ralph Gross, Latanya Sweeney, Fernando de la Torre, Simon Baker
Issue Date:June 2006
pp. 161
Advances in camera and computing equipment hardware in recent years have made it increasingly simple to capture and store extensive amounts of video data. This, among other things, creates ample opportunities for the sharing of video sequences. In order to...
 
Facial Action Unit Event Detection by Cascade of Tasks
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Xiaoyu Ding,Wen-Sheng Chu,Fernando De La Torre,Jeffery F. Cohn,Qiao Wang
Issue Date:December 2013
pp. 2400-2407
Automatic facial Action Unit (AU) detection from video is a long-standing problem in facial expression analysis. AU detection is typically posed as a classification problem between frames or segments of positive examples and negative ones, where existing w...
 
Eigenfiltering for Flexible Eigentracking (EFE)
Found in: Pattern Recognition, International Conference on
By Fernando de la Torre, Javier Melenchon, Jordi Vitria, Petia Radeva
Issue Date:September 2000
pp. 7118
Traditional techniques for tracking non-rigid objects such as optical flow, correlation, active contours or color, can not deal with situations where image changes are not due to motion but appearance (e.g. tracking the lips when the teeth appear). Two mai...
 
Temporal Segmentation of Facial Behavior
Found in: Computer Vision, IEEE International Conference on
By Fernando De la Torre, Joan Campoy, Zara Ambadar, Jeffrey F. Cohn
Issue Date:October 2007
pp. 1-8
Temporal segmentation of facial gestures in spontaneous facial behavior recorded in real-world settings is an important, unsolved, and relatively unexplored problem in facial image analysis. Several issues contribute to the challenge of this task. These in...
 
A Probabilistic Framework for Rigid and Non-Rigid Appearance Based Tracking and Recognition
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Fernando de la Torre, Yaser Yacoob, Larry Davis
Issue Date:March 2000
pp. 491
This paper describes an unified probabilistic framework for appearance based tracking of rigid and non-rigid objects. A spatio-temporal dependent shape/texture Eigenspace and mixture of diagonal gaussians are learned in a Hidden Markov Model(HMM) like stru...
 
Robust Principal Component Analysis for Computer Vision
Found in: Computer Vision, IEEE International Conference on
By Fernando De la Torre, Michael J. Black
Issue Date:July 2001
pp. 362
Principal Component Analysis (PCA) has been widely used for the representation of shape, appearance, and motion. One drawback of typical PCA methods is that they are least squares estimation techniques and hence fail to account for
 
Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-Rank Matrix Decomposition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Ricardo Cabral,Fernando De La Torre,Joao P. Costeira,Alexandre Bernardino
Issue Date:December 2013
pp. 2488-2495
Low rank models have been widely used for the representation of shape, appearance or motion in computer vision problems. Traditional approaches to fit low rank models make use of an explicit bilinear factorization. These approaches benefit from fast numeri...
 
Unsupervised discovery of facial events
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Feng Zhou, Fernando De la Torre, Jeffrey F. Cohn
Issue Date:June 2010
pp. 2574-2581
Automatic facial image analysis has been a long standing research problem in computer vision. A key component in facial image analysis, largely conditioning the success of subsequent algorithms (e.g. facial expression recognition), is to define a vocabular...
 
Local minima free Parameterized Appearance Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Minh Hoai Nguyen, Fernando De la Torre
Issue Date:June 2008
pp. 1-8
Parameterized Appearance Models (PAMs) (e.g. Eigen-tracking, Active Appearance Models, Morphable Models) are commonly used to model the appearance and shape variation of objects in images. While PAMs have numerous advantages relative to alternate approache...
 
Bilinear Active Appearance Models
Found in: Computer Vision, IEEE International Conference on
By Jose Gonzalez-Mora, Fernando De la Torre, Rajesh Murthi, Nicolas Guil, Emilio L. Zapata
Issue Date:October 2007
pp. 1-8
Appearance Models have been applied to model the space of human faces over the last two decades. In particular, Active Appearance Models (AAMs) have been successfully used for face tracking, synthesis and recognition, and they are one of the state-of-the-a...
 
A Framework for Modeling the Appearance of 3D Articulated Figures
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Hedvig Sidenbladh, Fernando de la Torre, Michael J. Black
Issue Date:March 2000
pp. 368
This paper describes a framework for constructing a linear subspace model of image appearance for complex articulated 3D figures such as humans and other animals. A commercial motion capture system provides 3D data that is aligned with images of subjects p...
 
Robust Matrix Factorization with Unknown Noise
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Deyu Meng,Fernando De La Torre
Issue Date:December 2013
pp. 1337-1344
Many problems in computer vision can be posed as recovering a low-dimensional subspace from high-dimensional visual data. Factorization approaches to low-rank subspace estimation minimize a loss function between the observed measurement matrix and a biline...
 
Facing Imbalanced Data--Recommendations for the Use of Performance Metrics
Found in: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII)
By Laszlo A. Jeni,Jeffrey F. Cohn,Fernando De La Torre
Issue Date:September 2013
pp. 245-251
Recognizing facial action units (AUs) is important for situation analysis and automated video annotation. Previous work has emphasized face tracking and registration and the choice of features classifiers. Relatively neglected is the effect of imbalanced d...
 
Action unit detection with segment-based SVMs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tomas Simon, Minh Hoai Nguyen, Fernando De La Torre, Jeffrey F. Cohn
Issue Date:June 2010
pp. 2737-2744
Automatic facial action unit (AU) detection from video is a long-standing problem in computer vision. Two main approaches have been pursued: (1) static modeling — typically posed as a discriminative classification problem in which each video frame is evalu...
 
Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fernando De la Torre, Minh Hoai Nguyen
Issue Date:June 2008
pp. 1-8
Parameterized Appearance Models (PAMs) (e.g. eigen-tracking, active appearance models, morphable models) use Principal Component Analysis (PCA) to model the shape and appearance of objects in images. Given a new image with an unknown appearance/shape confi...
 
Filtered Component Analysis to Increase Robustness to Local Minima in Appearance Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fernando De la Torre, Alvaro Collet, Manuel Quero, Jeffrey F. Cohn, Takeo Kanade
Issue Date:June 2007
pp. 1-8
Appearance Models (AM) are commonly used to model appearance and shape variation of objects in images. In particular, they have proven useful to detection, tracking, and synthesis of people's faces from video. While AM have numerous advantages relative to ...
 
Learning Kernel Expansions for Image Classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fernando De la Torre, Oriol Vinyals
Issue Date:June 2007
pp. 1-7
Kernel machines (e.g. SVM, KLDA) have shown state-of-the-art performance in several visual classification tasks. The classification performance of kernel machines greatly depends on the choice of kernels and its parameters. In this paper, we propose a meth...
 
Representational Oriented Component Analysis (ROCA) for Face Recognition with One Sample Image per Training Class
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fernando De la Torre, Ralph Gross, Simon Baker, B. V. K. Vijaya Kumar
Issue Date:June 2005
pp. 266-273
<p>Subspace methods such as PCA, LDA, ICA have become a standard tool to perform visual learning and recognition. In this paper we propose Representational Oriented Component Analysis (ROCA), an extension of OCA, to perform face recognition when just...
 
Learning 3D Appearance Models from Video
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Fernando De la Torre, Jordi Casoliva, Jeffrey F. Cohn
Issue Date:May 2004
pp. 645
Within the past few years, there has been a great interest in face modeling for analysis (e.g. facial expression recognition) and synthesis (e.g. virtual avatars). Two primary approaches are appearance models (AM) and structure from motion (SFM). While ext...
 
Pareto discriminant analysis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Karim T. Abou-Moustafa, Fernando de la Torre, Frank P. Ferrie
Issue Date:June 2010
pp. 3602-3609
Linear Discriminant Analysis (LDA) is a popular tool for multiclass discriminative dimensionality reduction. However, LDA suffers from two major problems: (1) It only optimizes the Bayes error for the case of unimodal Gaussian classes with equal covariance...
 
Deformable Graph Matching
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Feng Zhou,Fernando De la Torre
Issue Date:June 2013
pp. 2922-2929
Graph matching (GM) is a fundamental problem in computer science, and it has been successfully applied to many problems in computer vision. Although widely used, existing GM algorithms cannot incorporate global consistence among nodes, which is a natural c...
 
Selective Transfer Machine for Personalized Facial Action Unit Detection
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Wen-Sheng Chu,Fernando De La Torre,Jeffery F. Cohn
Issue Date:June 2013
pp. 3515-3522
Automatic facial action unit (AFA) detection from video is a long-standing problem in facial expression analysis. Most approaches emphasize choices of features and classifiers. They neglect individual differences in target persons. People vary markedly in ...
 
Supervised Descent Method and Its Applications to Face Alignment
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Xuehan Xiong,Fernando De la Torre
Issue Date:June 2013
pp. 532-539
Many computer vision problems (e.g., camera calibration, image alignment, structure from motion) are solved through a nonlinear optimization method. It is generally accepted that 2nd order descent methods are the most robust, fast and reliable approaches f...
 
Continuous AU intensity estimation using localized, sparse facial feature space
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Laszlo A. Jeni,Jeffrey M. Girard,Jeffrey F. Cohn,Fernando De La Torre
Issue Date:April 2013
pp. 1-7
Most work in automatic facial expression analysis seeks to detect discrete facial actions. Yet, the meaning and function of facial actions often depends in part on their intensity. We propose a part-based, sparse representation for automated measurement of...
   
Interactive region-based linear 3D face models
Found in: ACM SIGGRAPH 2011 papers (SIGGRAPH '11)
By Fernando De la Torre, Iain Matthews, J. Rafael Tena
Issue Date:August 2011
pp. 287-294
Linear models, particularly those based on principal component analysis (PCA), have been used successfully on a broad range of human face-related applications. Although PCA models achieve high compression, they have not been widely used for animation in a ...
     
Interactive region-based linear 3D face models
Found in: ACM Transactions on Graphics (TOG)
By Fernando De la Torre, Iain Matthews, J. Rafael Tena
Issue Date:July 2011
pp. 1-33
Linear models, particularly those based on principal component analysis (PCA), have been used successfully on a broad range of human face-related applications. Although PCA models achieve high compression, they have not been widely used for animation in a ...
     
Unsupervised summarization of rushes videos
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Feng Zhou, Fernando De la Torre, Wei Liu, Yan Liu, Yang Liu
Issue Date:October 2010
pp. 751-754
This paper proposes a new framework to formulate summarization of rushes video as an unsupervised learning problem. We pose the problem of video summarization as one of time-series clustering, and proposed Constrained Aligned Cluster Analysis (CACA). CACA ...
     
Discriminative cluster analysis
Found in: Proceedings of the 23rd international conference on Machine learning (ICML '06)
By Fernando De la Torre, Takeo Kanade
Issue Date:June 2006
pp. 241-248
Clustering is one of the most widely used statistical tools for data analysis. Among all existing clustering techniques, k-means is a very popular method because of its ease of programming and because it accomplishes a good trade-off between achieved perfo...
     
Multimodal oriented discriminant analysis
Found in: Proceedings of the 22nd international conference on Machine learning (ICML '05)
By Fernando De la Torre, Takeo Kanade
Issue Date:August 2005
pp. 177-184
Linear discriminant analysis (LDA) has been an active topic of research during the last century. However, the existing algorithms have several limitations when applied to visual data. LDA is only optimal for Gaussian distributed classes with equal covarian...
     
AAM Derived Face Representations for Robust Facial Action Recognition
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Simon Lucey, Iain Matthews, Changbo Hu, Zara Ambadar, Fernando de la Torre, Jeffrey Cohn
Issue Date:April 2006
pp. 155-162
In this paper, we present results on experiments employing Active Appearance Model (AAM) derived facial representations, for the task of facial action recognition. Experimental results demonstrate the benefit of AAM-derived representations on a spontaneous...
 
Matrix Completion for Weakly-supervised Multi-label Image Classification
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ricardo Cabral,Fernando de la Torre,Joao Paulo Costeira,Alexandre Bernardino
Issue Date:August 2014
pp. 1
In the last few years, image classification has become an incredibly active research topic, with widespread applications. Most methods for visual recognition are fully supervised in nature, as they make use of bounding boxes or pixelwise segmentations to l...
 
Automatic Learning of Appearance Face Models
Found in: Recognition, Analysis, & Tracking of Faces & Gestures in Real -Time Systems, IEEE ICCV Workshop on
By Fernando de la Torre
Issue Date:August 2001
pp. 0032
Abstract: Since Principal Component Analysis (PCA) technique has been applied by Sirovich and Kirby to parameterize the face, many computer vision researches have used eigen-whatever techniques to construct linear models of optical flow, shape, graylevel, ...
 
Segmentation and classification of meetings using multiple information streams
Found in: Proceedings of the 6th international conference on Multimodal interfaces (ICMI '04)
By Alexander I. Rudnicky, Carlos Vallespi, Fernando de la Torre, Manuela Veloso, Paul E. Rybski, Satanjeev Banerjee
Issue Date:October 2004
pp. 335-336
We present a meeting recorder infrastructure used to record and annotate events that occur in meetings. Multiple data streams are recorded and analyzed in order to infer a higher-level state of the group's activities. We describe the hardware and software ...
     
 1