Search For:

Displaying 1-17 out of 17 total
Sieving Regression Forest Votes for Facial Feature Detection in the Wild
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Heng Yang,Ioannis Patras
Issue Date:December 2013
pp. 1936-1943
In this paper we propose a method for the localization of multiple facial features on challenging face images. In the regression forests (RF) framework, observations (patches) that are extracted at several image locations cast votes for the localization of...
 
Coupled Gaussian processes for pose-invariant facial expression recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ognjen Rudovic,Maja Pantic,Ioannis Patras
Issue Date:June 2013
pp. 1357-1369
We propose a method for head-pose invariant facial expression recognition that is based on a set of characteristic facial points. To achieve head-pose invariance, we propose the Coupled Scaled Gaussian Process Regression (CSGPR) model for head-pose normali...
 
Pyramidal Model for Image Semantic Segmentation
Found in: Pattern Recognition, International Conference on
By Giuseppe Passino, Ioannis Patras, Ebroul Izquierdo
Issue Date:August 2010
pp. 1554-1557
We present a new hierarchical model applied to the problem of image semantic segmentation, that is, the association to each pixel in an image with a category label (e.g. tree, cow, building, .). This problem is usually addressed with a combination of an ap...
 
Regression-Based Multi-view Facial Expression Recognition
Found in: Pattern Recognition, International Conference on
By Ognjen Rudovic, Ioannis Patras, Maja Pantic
Issue Date:August 2010
pp. 4121-4124
We present a regression-based scheme for multi-view facial expression recognition based on 2D geometric features. We address the problem by mapping facial points (e.g. mouth corners) from non-frontal to frontal view where further recognition of the express...
 
Multiplicative Update Rules for Multilinear Support Tensor Machines
Found in: Pattern Recognition, International Conference on
By Irene Kotsia, Ioannis Patras
Issue Date:August 2010
pp. 33-36
In this paper, we formulate the Multilinear Support Tensor Machines (MSTMs) problem in a similar to the Non-negative Matrix Factorization (NMF) algorithm way. A novel set of simple and robust multiplicative update rules are proposed in order to find the mu...
 
Coupled Prediction Classification for Robust Visual Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ioannis Patras, Edwin R. Hancock
Issue Date:September 2010
pp. 1553-1567
This paper addresses the problem of robust template tracking in image sequences. Our work falls within the discriminative framework in which the observations at each frame yield direct probabilistic predictions of the state of the target. Our primary contr...
 
The fast-3D spatio-temporal interest region detector
Found in: Image Analysis for Multimedia Interactive Services, International Workshop on
By Sander Koelstra, Ioannis Patras
Issue Date:May 2009
pp. 242-245
Spatio-temporal interest region detectors can be used in the analysis of video to determine sparse, informative regions as candidates for feature extraction. In this paper we compare existing detectors and introduce the new FAST-3D detector, loosely based ...
 
Context awareness in graph-based image semantic segmentation via visual word distributions
Found in: Image Analysis for Multimedia Interactive Services, International Workshop on
By Giuseppe Passino, Ioannis Patras, Ebroul Izquierdo
Issue Date:May 2009
pp. 33-36
This paper addresses the problem of image semantic segmentation (or semantic labelling), that is the association of one of a predefined set of semantic categories (e.g. cow, car, face) to each image pixel. We adopt a patch-based approach, in which super-pi...
 
Regression tracking with data relevance determination
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ioannis Patras, Edwin R. Hancock
Issue Date:June 2007
pp. 1-8
This paper1 addresses the problem of efficient visual 2D template tracking in image sequences. We adopt a discriminative approach in which the observations at each frame yield direct predictions of a parametrisation of the state (e.g. position/scale/rotati...
 
Regression-Based Template Tracking in Presence of Occlusions
Found in: Image Analysis for Multimedia Interactive Services, International Workshop on
By Ioannis Patras, Edwin Hancock
Issue Date:June 2007
pp. 15
This paper addresses the problem of efficient visual 2D template tracking in the presence of large motions and partial occlusions. We adopt a learning approach, in our case using a Bayesian Mixture of Experts (BME), in which observations at each frame yiel...
 
Gaze Tracking by Using Factorized Likelihoods Particle Filtering and Stereo Vision
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Erik Pogalin, Andre Redert, Ioannis Patras, Emile A. Hendriks
Issue Date:June 2006
pp. 57-64
This paper describes a non-intrusive method to estimate the gaze direction of a person by using stereo cameras. First, facial features are tracked with an adapted particle filtering algorithm using factorized likelihoods to estimate the 3D head pose. Next ...
 
Video Segmentation by MAP Labeling of Watershed Segments
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ioannis Patras, E.a. Hendriks, R.l. Lagendijk
Issue Date:March 2001
pp. 326-332
<p><b>Abstract</b>—This paper addresses the problem of spatio-temporal segmentation of video sequences. An initial intensity segmentation method (watershed segmentation) provides a number of initial segments which are subsequently labeled...
 
Supervised dictionary learning for action localization
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By B G Vijay Kumar,Ioannis Patras
Issue Date:April 2013
pp. 1-8
Most of the existing methods that adopt the Implicit Shape Model (ISM) for action localization learn the dictionary (codebook) in an unsupervised manner. In contrast to this, we present a supervised approach to learn a dictionary for action localization. W...
   
Privileged information-based conditional regression forest for facial feature detection
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Heng Yang,Ioannis Patras
Issue Date:April 2013
pp. 1-6
In this paper we propose a method that utilises privileged information, that is information that is available only at the training phase, in order to train Regression Forests for facial feature detection. Our method chooses the split functions at some rand...
   
Optimizing visual search with implicit user feedback in interactive video retrieval
Found in: Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR '10)
By Ioannis Kompatsiaris, Ioannis Patras, Stefanos Vrochidis
Issue Date:July 2010
pp. 274-281
This paper describes an approach to optimize query by visual example results, by combining visual features and implicit user feedback in interactive video retrieval. To this end, we propose a framework, in which video processing is performed by employing w...
     
Discriminative space-time voting for joint recognition and localization of actions.
Found in: Proceedings of the 2nd international workshop on Social signal processing (SSPW '10)
By Antonios Oikonomopoulos, Ioannis Patras, Maja Pantic
Issue Date:October 2010
pp. 11-16
In this paper we address the problem of activity detection in unsegmented image sequences. Our main contribution is the use of an implicit representation of the spatiotemporal shape of the activity which relies on the spatiotemporal localization of charact...
     
Relative Margin Support Tensor Machines for gait and action recognition
Found in: Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR '10)
By Ioannis Patras, Irene Kotsia
Issue Date:July 2010
pp. 446-453
In this paper, we formulate the Relative Margin Support Tensor Machines (RMSTMs) problem as an extension of the Relative Margin Machines (RMMs). While the typical Support Tensor Machines (STMs) find a solution that is greatly influenced by the data spread,...
     
 1