Search For:

Displaying 1-26 out of 26 total
Registration Invariant Representations for Expression Detection
Found in: Digital Image Computing: Techniques and Applications
By Patrick Lucey, Simon Lucey, Jeffrey F. Cohn
Issue Date:December 2010
pp. 255-261
Active appearance model (AAM) representations have been used to great effect recently in the accurate detection of expression events (e.g., action units, pain, broad expressions, etc.). The motivation for their use, and rationale for their success, lies in...
 
Using a Free-Parts Representation for Visual Speech Recognition
Found in: Digital Image Computing: Techniques and Applications
By Patrick Lucey, Simon Lucey, Sridha Sridharan
Issue Date:December 2005
pp. 55
Motivated by the success of free-parts based representations in face recognition, we have attempted to address some of the problems associated with applying such a philosophy to the task of speaker-independent visual speech recognition. A major problem wit...
 
Rank Minimization across Appearance and Shape for AAM Ensemble Fitting
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Xin Cheng,Sridha Sridharan,Jason Saragih,Simon Lucey
Issue Date:December 2013
pp. 577-584
Active Appearance Models (AAMs) employ a paradigm of inverting a synthesis model of how an object can vary in terms of shape and appearance. As a result, the ability of AAMs to register an unseen object image is intrinsically linked to two factors. First, ...
 
Multi-channel Correlation Filters
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Hamed Kiani Galoogahi,Terence Sim,Simon Lucey
Issue Date:December 2013
pp. 3072-3079
Modern descriptors like HOG and SIFT are now commonly used in vision for pattern detection within image and video. From a signal processing perspective, this detection process can be efficiently posed as a correlation/ convolution between a multi-channel i...
 
Fourier Lucas-Kanade Algorithm
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Simon Lucey,Rajitha Navarathna,Ahmed Bilal Ashraf,Sridha Sridharan
Issue Date:June 2013
pp. 1383-1396
In this paper, we propose a framework for both gradient descent image and object alignment in the Fourier domain. Our method centers upon the classical Lucas & Kanade (LK) algorithm where we represent the source and template/model in the complex...
 
Collecting Large, Richly Annotated Facial-Expression Databases from Movies
Found in: IEEE MultiMedia
By Abhinav Dhall,Roland Goecke,Simon Lucey,Tom Gedeon
Issue Date:July 2012
pp. 34-41
Two large facial-expression databases depicting challenging real-world conditions were constructed using a semi-automatic approach via a recommender system based on subtitles.
 
Graph Rigidity for Near-Coplanar Structure from Motion
Found in: Digital Image Computing: Techniques and Applications
By Jack Valmadre,Ben Upcroft,Sridha Sridharan,Simon Lucey
Issue Date:December 2011
pp. 480-486
Recent algorithms for monocular motion capture (MoCap) estimate weak-perspective camera matrices between images using a small subset of approximately-rigid points on the human body (i.e.\ the torso and hip). A problem with this approach, however, is that t...
 
Fourier Active Appearance Models
Found in: Computer Vision, IEEE International Conference on
By Rajitha Navarathna,Sridha Sridharan,Simon Lucey
Issue Date:November 2011
pp. 1919-1926
Gaining invariance to camera and illumination variations has been a well investigated topic in Active Appearance Model (AAM) fitting literature. The major problem lies in the inability of the appearance parameters of the AAM to generalize to unseen conditi...
 
Non-rigid Face Tracking Using Short Track-Life Features
Found in: Digital Image Computing: Techniques and Applications
By Simon Lucey, Jun-Su Jang
Issue Date:December 2010
pp. 241-248
We define a “generic” non-rigid face tracker as any system that exhibits robustness to changes in illumination, expression and viewpoint during the tracking of facial land-marks in a video sequence. A popular approach to the problem is to detect/track an e...
 
Are Correlation Filters Useful for Human Action Recognition?
Found in: Pattern Recognition, International Conference on
By Saad Ali, Simon Lucey
Issue Date:August 2010
pp. 2608-2611
It has been argued in recent work that correlation filters are attractive for human action recognition from videos. Motivation for their employment in this classification task lies in their ability to: (i) specify where the filter should peak in contrast t...
 
Fast image alignment in the Fourier domain
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ahmed Bilal Ashraf, Simon Lucey, Tsuhan Chen
Issue Date:June 2010
pp. 2480-2487
In this paper we propose a framework for gradient descent image alignment in the Fourier domain. Specifically, we propose an extension to the classical Lucas & Kanade (LK) algorithm where we represent the source and template image's intensity pixels in...
 
Reinterpreting the Application of Gabor Filters as a Manipulation of the Margin in Linear Support Vector Machines
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ahmed Bilal Ashraf, Simon Lucey, Tsuhan Chen
Issue Date:July 2010
pp. 1335-1341
Linear filters are ubiquitously used as a preprocessing step for many classification tasks in computer vision. In particular, applying Gabor filters followed by a classification stage, such as a support vector machine (SVM), is now common practice in compu...
 
Least squares congealing for unsupervised alignment of images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mark Cox, Sridha Sridharan, Simon Lucey, Jeffrey Cohn
Issue Date:June 2008
pp. 1-8
In this paper, we present an approach we refer to as “least squares congealing” which provides a solution to the problem of aligning an ensemble of images in an unsupervised manner. Our approach circumvents many of the limitations existing in the canonical...
 
Learning patch correspondences for improved viewpoint invariant face recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ahmed Bilal Ashraf, Simon Lucey, Tsuhan Chen
Issue Date:June 2008
pp. 1-8
Variation due to viewpoint is one of the key challenges that stand in the way of a complete solution to the face recognition problem. It is easy to note that local regions of the face change differently in appearance as the viewpoint varies. Recently, patc...
 
Enforcing convexity for improved alignment with constrained local models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yang Wang, Simon Lucey, Jeffrey F. Cohn
Issue Date:June 2008
pp. 1-8
Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/ tracking in comparison to leading holistic approaches (e.g., AAMs). A major problem hindering the development of CLMs further, for non-rigid object a...
 
Enforcing non-positive weights for stable support vector tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Simon Lucey
Issue Date:June 2008
pp. 1-8
In this paper we demonstrate that the support vector tracking (SVT) framework first proposed by Avidan is equivalent to the canonical Lucas-Kanade (LK) algorithm with a weighted Euclidean norm. From this equivalence we empirically demonstrate that in many ...
 
Non-Rigid Object Alignment with a Mismatch Template Based on Exhaustive Local Search
Found in: Computer Vision, IEEE International Conference on
By Yang Wang, Simon Lucey, Jeffrey Cohn
Issue Date:October 2007
pp. 1-8
Non-rigid object alignment is especially challenging when only a single appearance template is available and target and template images fail to match. Two sources of discrepancy between target and template are changes in illumination and non-rigid motion. ...
 
Learning Patch Dependencies for Improved Pose Mismatched Face Verification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Simon Lucey, Tsuhan Chen
Issue Date:June 2006
pp. 909-915
Most pose robust face verification algorithms, which employ 2D appearance, rely heavily on statistics gathered from offline databases containing ample facial appearance variation across many views. Due to the high dimensionality of the face images being em...
 
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...
 
A GMM Parts Based Face Representation for Improved Verification through Relevance Adaptation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Simon Lucey, Tsuhan Chen
Issue Date:July 2004
pp. 855-861
Motivated by the success of parts based representations in face detection we have attempted to address some of the problems associated with applying such a philosophy to the task of face verification. Hitherto, a major problem with this approach in face ve...
 
The Symbiotic Relationship of Parts and Monolithic Face Representations in Verification
Found in: Computer Vision and Pattern Recognition Workshop
By Simon Lucey
Issue Date:July 2004
pp. 89
Techniques that treat the face holistically as a vector of pixel values, which we refer to as a monolithic representation, are still widely considered state of the art for the task of face verification in literature. Recently good performance has be attain...
 
Initialized Eigenlip Estimator for Fast Lip Tracking Using Linear Regression
Found in: Pattern Recognition, International Conference on
By Simon Lucey, Sridha Sridharan, Vinod Chandran
Issue Date:September 2000
pp. 3182
Multimodal speech processing in which visual facial features are jointly processed with audio features is a rapidly advancing field. Lip movements and configurations provide useful information to improve speech and speaker recognition. However, the use of ...
 
Convolutional Sparse Coding for Trajectory Reconstruction
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yingying Zhu,Simon Lucey
Issue Date:December 2013
pp. 1
Trajectory basis Non-Rigid Structure from Motion (NRSfM) refers to the process of reconstructing the 3D trajectory of each point of a non-rigid object from just their 2D projected trajectories. Reconstruction relies on two factors: (i) the condition of the...
 
Fast Convolutional Sparse Coding
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Hilton Bristow,Anders Eriksson,Simon Lucey
Issue Date:June 2013
pp. 391-398
Sparse coding has become an increasingly popular method in learning and vision for a variety of classification, reconstruction and coding tasks. The canonical approach intrinsically assumes independence between observations during learning. For many natura...
 
Deformable face ensemble alignment with robust grouped-L1 anchors
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Xin Cheng,Clinton Fookes,Sridha Sridharan,Jason Saragih,Simon Lucey
Issue Date:April 2013
pp. 1-7
Many methods exist at the moment for deformable face fitting. A drawback to nearly all these approaches is that they are (i) noisy in terms of landmark positions, and (ii) the noise is biased across frames (i.e. the misalignment is toward common directions...
   
Temporal coordination of head motion in couples with history of interpersonal violence
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Zakia Hammal,Teresa E. Bailie,Jeffrey F. Cohn,David T. George,Jason Saraghi,Jesus Nuevo Chiquero,Simon Lucey
Issue Date:April 2013
pp. 1-8
Previous research in automated expression analysis has focused on discrete actions with little attention to their timing either within or between persons. We investigated the interpersonal coordination of rigid head motion in 11 intimate couples with a his...
   
 1