Search For:

Displaying 1-42 out of 42 total
MRF Energy Minimization and Beyond via Dual Decomposition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Nikos Komodakis, Nikos Paragios, Georgios Tziritas
Issue Date:March 2011
pp. 531-552
This paper introduces a new rigorous theoretical framework to address discrete MRF-based optimization in computer vision. Such a framework exploits the powerful technique of Dual Decomposition. It is based on a projected subgradient scheme that attempts to...
 
Optical flow estimation with uncertainties through dynamic MRFs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ben Glocker, Nikos Paragios, Nikos Komodakis, Georgios Tziritas, Nassir Navab
Issue Date:June 2008
pp. 1-8
In this paper, we propose a novel dynamic discrete framework to address image morphing with application to optical flow estimation. We reformulate the problem using a number of discrete displacements, and therefore the estimation of the morphing parameters...
 
MRF Optimization via Dual Decomposition: Message-Passing Revisited
Found in: Computer Vision, IEEE International Conference on
By Nikos Komodakis, Nikos Paragios, Georgios Tziritas
Issue Date:October 2007
pp. 1-8
A new message-passing schenme for MRF optimization is proposed in this paper. This scheme inherits better theoretical properties than all other state-of-the-art message passing methods and in practice performs equally well/outperforms them. It is based on ...
 
Fast, Approximately Optimal Solutions for Single and Dynamic MRFs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nikos Komodakis, Georgios Tziritas, Nikos Paragios
Issue Date:June 2007
pp. 1-8
A new efficient MRF optimization algorithm, called Fast-PD, is proposed, which generalizes ?-expansion. One of its main advantages is that it offers a substantial speedup over that method, e.g. it can be at least 3-9 times faster than ?-expansion. Its effi...
 
Background Modeling and Subtraction of Dynamic Scenes
Found in: Computer Vision, IEEE International Conference on
By Antoine Monnet, Anurag Mittal, Nikos Paragios, Visvanathan Ramesh
Issue Date:October 2003
pp. 1305
Background modeling and subtraction is a core component in motion analysis. The central idea behind such module is to create a probabilistic representation of the static scene that is compared with the current input to perform subtraction. Such approach is...
 
Knowledge-based Registration & Segmentation of the Left Ventricle: A Level Set Approach
Found in: Applications of Computer Vision, IEEE Workshop on
By Nikos Paragios, Mikael Rousson, Visvanathan Ramesh
Issue Date:December 2002
pp. 37
In this paper, we propose a level set formulation to deal with the segmentation and registration of the left ventricle in Magnetic Resonance (MR) images. Our approach is based on the integration of visual information, anatomical constraints and a flexible ...
 
A MRF-Based Approach for Real-Time Subway Monitoring
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nikos Paragios, Visvanathan Ramesh
Issue Date:December 2001
pp. 1034
There has been an increase in the use of video surveillance and monitoring in public areas to improve safety and security. Change detection and crowding/congestion density estimation are two sub-tasks in a subway monitoring system. We propose a method that...
 
A Variational Approach for the Segmentation of the Left Ventricle in MR Cardiac Images
Found in: Variational and Level Set Methods in Computer Vision, IEEE Workshop on
By Nikos Paragios
Issue Date:July 2001
pp. 153
This paper proposes a new front propagation method to segment MR cardiac images. This framework is based on the Geodesic Active Region Model, refers to a coupled propagation of two curves (inner and outer cardiac contours) and integrates boundary and regio...
 
Gradient Vector Flow Fast Geodesic Active Contours
Found in: Computer Vision, IEEE International Conference on
By Nikos Paragios, Olivier Mellina-Gottardo, Visvanathan Ramesh
Issue Date:July 2001
pp. 67
This paper proposes a new front propagation flow for boundary extraction. The proposed framework is inspired by the geodesic active contour model and leads to a paradigm that is relatively free from the initial curve position. Towards this end, it makes us...
 
Corrections to 'Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects'
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Nikos Paragios, Rachid Deriche
Issue Date:April 2000
pp. 415
No summary available.
 
A Generic Deformation Model for Dense Non-rigid Surface Registration: A Higher-Order MRF-Based Approach
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yun Zeng,Chaohui Wang,Xianfeng Gu,Dimitris Samaras,Nikos Paragios
Issue Date:December 2013
pp. 3360-3367
We propose a novel approach for dense non-rigid 3D surface registration, which brings together Riemannian geometry and graphical models. To this end, we first introduce a generic deformation model, called Canonical Distortion Coefficients (CDCs), by charac...
 
Uncertainty-Driven Efficiently-Sampled Sparse Graphical Models for Concurrent Tumor Segmentation and Atlas Registration
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Sarah Parisot,William Wells,Stephane Chemouny,Hugues Duffau,Nikos Paragios
Issue Date:December 2013
pp. 641-648
Graph-based methods have become popular in recent years and have successfully addressed tasks like segmentation and deformable registration. Their main strength is optimality of the obtained solution while their main limitation is the lack of precision due...
 
High-Level Bottom-Up Cues for Top-Down Parsing of Facade Images
Found in: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)
By David Ok,Mateusz Kozinski,Renaud Marlet,Nikos Paragios
Issue Date:October 2012
pp. 128-135
We address the problem of parsing images of building facades. The goal is to segment images, assigning to the resulting regions semantic labels that correspond to the basic architectural elements. We assume a top-down parsing framework based on a 2D shape ...
 
Efficient parallel message computation for MAP inference
Found in: Computer Vision, IEEE International Conference on
By Stavros Alchatzidis,Aristeidis Sotiras,Nikos Paragios
Issue Date:November 2011
pp. 1379-1386
First order Markov Random Fields (MRFs) have become a predominant tool in Computer Vision over the past decade. Such a success was mostly due to the development of efficient optimization algorithms both in terms of speed as well as in terms of optimality p...
 
Markov Random Field-based fitting of a subdivision-based geometric atlas
Found in: Computer Vision, IEEE International Conference on
By Uday Kurkure,Yen H. Le,Nikos Paragios,Tao Ju,James P. Carson,Ioannis A. Kakadiaris
Issue Date:November 2011
pp. 2540-2547
An accurate labeling of a multi-part, complex anatomical structure (e.g., brain) is required in order to compare data across images for spatial analysis. It can be achieved by fitting an object-specific geometric atlas that is constructed using a partition...
 
Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors
Found in: Computer Vision, IEEE International Conference on
By Chaohui Wang, Yun Zeng,Loic Simon,Ioannis Kakadiaris,Dimitris Samaras,Nikos Paragios
Issue Date:November 2011
pp. 319-326
In this paper, we propose a novel one-shot optimization approach to simultaneously determine both the optimal 3D landmark model and the corresponding 2D projections without explicit estimation of the camera viewpoint, which is also able to deal with misdet...
 
Model-Based 3D Hand Pose Estimation from Monocular Video
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Martin de La Gorce, David J. Fleet, Nikos Paragios
Issue Date:September 2011
pp. 1793-1805
A novel model-based approach to 3D hand tracking from monocular video is presented. The 3D hand pose, the hand texture, and the illuminant are dynamically estimated through minimization of an objective function. Derived from an inverse problem formulation,...
 
Data fusion through cross-modality metric learning using similarity-sensitive hashing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michael M. Bronstein, Alexander M. Bronstein, Fabrice Michel, Nikos Paragios
Issue Date:June 2010
pp. 3594-3601
Visual understanding is often based on measuring similarity between observations. Learning similarities specific to a certain perception task from a set of examples has been shown advantageous in various computer vision and pattern recognition problems. In...
 
Dense non-rigid surface registration using high-order graph matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yun Zeng, Chaohui Wang, Yang Wang, Xianfeng Gu, Dimitris Samaras, Nikos Paragios
Issue Date:June 2010
pp. 382-389
In this paper, we propose a high-order graph matching formulation to address non-rigid surface matching. The singleton terms capture the geometric and appearance similarities (e.g., curvature and texture) while the high-order terms model the intrinsic embe...
 
Sparsity, redundancy and optimal image support towards knowledge-based segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Salma Essafi, Georg Langs, Nikos Paragios
Issue Date:June 2008
pp. 1-7
In this paper, we propose a novel approach to model shape variations. It encodes sparsity, exploits geometric redundancy, and accounts for the different degrees of local variation and image support. In this context we consider a control-point based shape r...
 
Model-based hand tracking with texture, shading and self-occlusions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Martin de La Gorce, Nikos Paragios, David J. Fleet
Issue Date:June 2008
pp. 1-8
A novel model-based approach to 3D hand tracking from monocular video is presented. The 3D hand pose, the hand texture and the illuminant are dynamically estimated through minimization of an objective function. Derived from an inverse problem formulation, ...
 
Graph commute times for image representation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Regis Behmo, Nikos Paragios, Veronique Prinet
Issue Date:June 2008
pp. 1-8
We introduce a new image representation that encompasses both the general layout of groups of quantized local invariant descriptors as well as their relative frequency. A graph of interest points clusters is constructed and we use the matrix of commute tim...
 
Modeling the structure of multivariate manifolds: Shape maps
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Georg Langs, Nikos Paragios
Issue Date:June 2008
pp. 1-8
We propose a shape population metric that reflects the interdependencies between points observed in a set of examples. It provides a notion of topology for shape and appearance models that represents the behavior of individual observations in a metric spac...
 
Registration with Uncertainties and Statistical Modeling of Shapes with Variable Metric Kernels
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Maxime Taron, Nikos Paragios, Marie-Pierre Jolly
Issue Date:January 2009
pp. 99-113
Registration and modeling of shapes are two important problems in computer vision and pattern recognition. Despite enormous progress made over the past decade, these problems are still open. In this paper, we advance the state of the art in both directions...
 
Motion Analysis of Endovascular Stent-Grafts by MDL Based Registration
Found in: Computer Vision, IEEE International Conference on
By Georg Langs, Nikos Paragios, Rene Donner, Pascal Desgranges, Alain Rahmouni, Hicham Kobeiter
Issue Date:October 2007
pp. 1-8
The endovascular repair of a traumatic rupture of the thoracic aorta - that would otherwise lead to the death of the patient - is performed by delivering a stent-graft into the vessel at the rupture location. The age range of the affected patients is large...
 
From Uncertainties to Statistical Model Building and Segmentation of the Left Ventricle
Found in: Computer Vision, IEEE International Conference on
By Maxime Taron, Nikos Paragios, Marie-Pierre Jolly
Issue Date:October 2007
pp. 1-8
Reliable segmentation of the left ventricle is a long sought objective in medical imaging for automatic retrieval of anatomical and pathological measurements and detection of malfunctions. In this paper, we propose a novel model-constrained approach to add...
 
Variable Bandwidth Image Denoising Using Image-based Noise Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Noura Azzabou, Nikos Paragios, Frederic Guichard, Frederic Cao
Issue Date:June 2007
pp. 1-7
This paper introduces a variational formulation for image denoising based on a quadratic function over kernels of variable bandwidth. These kernels are scale adaptive and reflect spatial and photometric similarities between pixels. The bandwidth of the ker...
 
Joint Object Segmentation and Behavior Classification in Image Sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Laura Gui, Jean-Philippe Thiran, Nikos Paragios
Issue Date:June 2007
pp. 1-8
In this paper, we propose a general framework for fusing bottom-up segmentation with top-down object behavior classification over an image sequence. This approach is beneficial for both tasks, since it enables them to cooperate so that knowledge relevant t...
 
Radon space and Adaboost for Pose Estimation
Found in: Pattern Recognition, International Conference on
By Patrick Etyngier, Nikos Paragios, Renaud Keriven, Yakup Genc, Jean-Yves Audibert
Issue Date:August 2006
pp. 421-424
In this paper, we present a new approach to camera pose estimation from single shot images in known environment. Such a method comprises two stages, a learning step and an inference stage where given a new image we recover the exact camera position. Lines ...
 
Image Renaissance Using Discrete Optimization
Found in: Pattern Recognition, International Conference on
By Cedric Allene, Nikos Paragios
Issue Date:August 2006
pp. 631-634
In this paper we propose a novel technique to image completion that addresses image renaissance through a graph-based matching process. To this end, a number of candidate seeds with content similar to the one of the area to be inpainted are considered. The...
 
Fast Dichotomic Multiple Search Algorithm for Shortest Cirular Path
Found in: Pattern Recognition, International Conference on
By Martin de La Gorce, Nikos Paragios
Issue Date:August 2006
pp. 403-406
Circular shortest path algorithms for polar objects segmentation have been proposed in [1, 11, 10] to address discrete case and extended in [2] to the continuous domain for closed global optimal geodesic calculation. The best method up to date relies on a ...
 
Modelling Shapes with Uncertainties: Higher Order Polynomials, Variable Bandwidth Kernels and Non Parametric Density Estimation
Found in: Computer Vision, IEEE International Conference on
By Maxime Taron, Nikos Paragios, Marie-Pierre Jolly
Issue Date:October 2005
pp. 1659-1666
In this paper, we introduce a new technique for shape modelling in the space of implicit polynomials. Registration consists of recovering an optimal one-to-one transformation of a higher order polynomial along with uncertainties measures that are determine...
 
Fast Illumination-Invariant Background Subtraction Using Two Views: Error Analysis, Sensor Placement and Applications
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ser-Nam Lim, Anurag Mittal, Larry S. Davis, Nikos Paragios
Issue Date:June 2005
pp. 1071-1078
Background modeling and subtraction to detect new or moving objects in a scene is an important component of many intelligent video applications. Compared to a single camera, the use of multiple cameras leads to better handling of shadows, specularities and...
 
Motion-Based Background Subtraction Using Adaptive Kernel Density Estimation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Anurag Mittal, Nikos Paragios
Issue Date:July 2004
pp. 302-309
Background modeling is an important component of many vision systems. Existing work in the area has mostly addressed scenes that consist of static or quasi-static structures. When the scene exhibits a persistent dynamic behavior in time, such an assumption...
 
Gradient Vector Flow Fast Geometric Active Contours
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Nikos Paragios, Olivier Mellina-Gottardo, Visvanathan Ramesh
Issue Date:March 2004
pp. 402-407
<p><b>Abstract</b>—In this paper, we propose an edge-driven bidirectional geometric flow for boundary extraction. To this end, we combine the geodesic active contour flow [CHECK END OF SENTENCE] and the gradient vector flow external force...
 
Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Nikos Paragios, Rachid Deriche
Issue Date:March 2000
pp. 266-280
<p><b>Abstract</b>—This paper presents a new variational framework for detecting and tracking multiple moving objects in image sequences. Motion detection is performed using a statistical framework for which the observed interframe differ...
 
Geodesic Active Regions for Supervised Texture Segmentation
Found in: Computer Vision, IEEE International Conference on
By Nikos Paragios, Rachid Deriche
Issue Date:September 1999
pp. 688
This paper presents a novel variational method for supervised texture segmentation. The textured feature space is generated by filtering the given textured images using isotropic and anisotropic filters, and analyzing their responses as multi-component con...
 
Geodesic Active Regions for Supervised Texture Segmentation
Found in: Computer Vision, IEEE International Conference on
By Nikos Paragios, Rachid Deriche
Issue Date:September 1999
pp. 926
This paper presents a novel variational method for supervised texture segmentation. The textured feature space is generated by filtering the given textured images using isotropic and anisotropic filters, and analyzing their responses as multi-component con...
 
Unifying Boundary and Region-Based Information for Geodesic Active Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nikos Paragios, Rachid Deriche
Issue Date:June 1999
pp. 2300
This paper addresses the problem of tracking several non-rigid objects over a sequence of frames acquired from a static observer using boundary and region-based information under a coupled geodesic active contour framework. Given the current frame, a stati...
 
Geodesic Active Contours for Supervised Texture Segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nikos Paragios, Rachid Deriche
Issue Date:June 1999
pp. 2422
This paper presents a variational method for supervised texture segmentation, which is based on ideas coming from the curve propagation theory. We assume that a preferable texture pattern is known (e.g. the pattern that we want to distinguish from the rest...
 
Segmentation of building facades using procedural shape priors
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Olivier Teboul, Loic Simon, Panagiotis Koutsourakis, Nikos Paragios
Issue Date:June 2010
pp. 3105-3112
In this paper we propose a novel approach to the perceptual interpretation of building facades that combines shape grammars, supervised classification and random walks. Procedural modeling is used to model the geometric and the photometric variation of bui...
 
Uncertainties-driven Surface Morphing: The case of Photo-realistic Transitions between Facial Expressions
Found in: Pattern Recognition, International Conference on
By Maxime TARON, Charlotte Ghys, Nikos PARAGIOS
Issue Date:August 2006
pp. 889-892
Reproduction of facial animation play a fundamental role in applications requiring human-computer interactions The objective of this paper is to introduce a geometric mechanism that exploits a fix number of states and is able to execute a subsequent number...
 
 1