Search For:

Displaying 1-27 out of 27 total
Similarity-based cross-layered hierarchical representation for object categorization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sanja Fidler, Marko Boben, Ales Leonardis
Issue Date:June 2008
pp. 1-8
This paper proposes a new concept in hierarchical representations that exploits features of different granularity and specificity coming from all layers of the hierarchy. The concept is realized within a cross-layered compositional representation learned f...
 
Superquadrics for Segmenting and Modeling Range Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ales Leonardis, Ales Jaklic, Franc Solina
Issue Date:November 1997
pp. 1289-1295
<p><b>Abstract</b>—We present a novel approach to reliable and efficient recovery of part-descriptions in terms of superquadric models from range data. We show that superquadrics can <it>directly</it> be recovered from unsegme...
 
The Visual Object Tracking VOT2013 Challenge Results
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Matej Kristan,Roman Pflugfelder,Ale Leonardis,Jiri Matas,Fatih Porikli,Luka Cehovin,Georg Nebehay,Gustavo Fernandez,Toma Vojir,Adam Gatt,Ahmad Khajenezhad,Ahmed Salahledin,Ali Soltani-Farani,Ali Zarezade,Alfredo Petrosino,Anthony Milton,Behzad Bozorgtabar,Bo Li,Chee Seng Chan,Cherkeng Heng,Dale Ward,David Kearney,Dorothy Monekosso,Hakki Can Karaimer,Hamid R. Rabiee,Jianke Zhu,Jin Gao,Jingjing Xiao,Junge Zhang,Junliang Xing,Kaiqi Huang,Karel Lebeda,Lijun Cao,Mario Edoardo Maresca,Mei Kuan Lim,Mohamed El Helw,Michael Felsberg,Paolo Remagnino,Richard Bowden,Roland Goecke,Rustam Stolkin,Samantha Yueying Lim,Sara Maher,Sebastien Poullot,Sebastien Wong,Shin'Ichi Satoh,Weihua Chen,Weiming Hu,Xiaoqin Zhang,Yang Li,Zhiheng Niu
Issue Date:December 2013
pp. 98-111
Visual tracking has attracted a significant attention in the last few decades. The recent surge in the number of publications on tracking-related problems have made it almost impossible to follow the developments in the field. One of the reasons is that th...
 
An Enhanced Adaptive Coupled-Layer LGTracker++
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Jingjing Xiao,Rustam Stolkin,Ale Leonardis
Issue Date:December 2013
pp. 137-144
This paper addresses the problems of tracking targets which undergo rapid and significant appearance changes. Our starting point is a successful, state-of-the-art tracker based on an adaptive coupled-layer visual model [10]. In this paper, we identify four...
 
An adaptive coupled-layer visual model for robust visual tracking
Found in: Computer Vision, IEEE International Conference on
By Luka Cehovin,Matej Kristan,Ales Leonardis
Issue Date:November 2011
pp. 1363-1370
This paper addresses the problem of tracking objects which undergo rapid and significant appearance changes. We propose a novel coupled-layer visual model that combines the target's global and local appearance. The local layer in this model is a set of loc...
 
Illumination Insensitive Eigenspaces
Found in: Computer Vision, IEEE International Conference on
By Horst Bischof, Horst Wildenauer, Ales Leonardis
Issue Date:July 2001
pp. 233
Variations in illumination can have a dramatic effect on the appearance of an object in an image. In this paper we propose how to deal with illumination variations in eigenspace methods. We demonstrate that the eigenimages obtained by a training set under ...
 
Selection of Reference Views for Image-Based Representation
Found in: Pattern Recognition, International Conference on
By Tomas Werner, Vaclav Hlavac, Ales Leonardis, Tomas Pajdla
Issue Date:August 1996
pp. 73
No summary available.
 
Dealing with occlusions in the eigenspace approach
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ales Leonardis, Horst Bischof
Issue Date:June 1996
pp. 453
The basic limitations of the current appearance-based matching methods using eigenimages are non-robust estimation of coefficients and inability to cope with problems related to occlusions and segmentation. In this paper we present a new approach which suc...
 
Online Discriminative Kernel Density Estimation
Found in: Pattern Recognition, International Conference on
By Matej Kristan, Aleš Leonardis
Issue Date:August 2010
pp. 581-584
We propose a new method for online estimation of probabilistic discriminative models. The method is based on the recently proposed online Kernel Density Estimation (oKDE) framework which produces Gaussian mixture models and allows adaptation using only a s...
 
Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sanja Fidler, Ales Leonardis
Issue Date:June 2007
pp. 1-8
This paper proposes a novel approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object categories. Inspired by the principles of efficient indexing (bottom-up), robust ma...
 
Combining Reconstructive and Discriminative Subspace Methods for Robust Classification and Regression by Subsampling
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Sanja Fidler, Danijel Skocaj, Aleš Leonardis
Issue Date:March 2006
pp. 337-350
Linear subspace methods that provide sufficient reconstruction of the data, such as PCA, offer an efficient way of dealing with missing pixels, outliers, and occlusions that often appear in the visual data. Discriminative methods, such as LDA, which, on th...
 
Weighted and Robust Incremental Method for Subspace Learning
Found in: Computer Vision, IEEE International Conference on
By Danijel Skocaj, Ales Leonardis
Issue Date:October 2003
pp. 1494
Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper we present a method for subspace learning, which takes these considerations into account. We present an incremental method, w...
 
Fuzzy C-Means in an MDL-Framework
Found in: Pattern Recognition, International Conference on
By Alexander Selb, Horst Bischof, Aleš Leonardis
Issue Date:September 2000
pp. 2740
In this paper, we present a Minimum Description Length (MDL) framework for fuzzy clustering algorithms. This framework enables us to find an optimal number of cluster centers. We applied our approach to the fuzzy c-means algorithm for which we designed a c...
 
Robust Localization Using Panoramic View-Based Recognition
Found in: Pattern Recognition, International Conference on
By Matjaž Jogan, Aleš Leonardis
Issue Date:September 2000
pp. 4136
The results of recent studies on the possibility of spatial localization from panoramic images have shown good prospects for view-based methods. The major advantages of these methods are a wide field-of-view, capability of modeling cluttered environments, ...
 
Is my new tracker really better than yours?
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Luka Cehovin,Matej Kristan,Ales Leonardis
Issue Date:March 2014
pp. 540-547
The problem of visual tracking evaluation is sporting an abundance of performance measures, which are used by various authors, and largely suffers from lack of consensus about which measures should be preferred. This is hampering the cross-paper tracker co...
   
Catadioptric Image-based Rendering for Mobile Robot Localization
Found in: Computer Vision, IEEE International Conference on
By Hynek Bakstein, Ales Leonardis
Issue Date:October 2007
pp. 1-6
We present an approach to view-based mobile robot localization using a X-slits image based rendering (IBR) method for creating novel views from a set of input images. The input images are acquired by a non-central catadioptric sensor mounted on a robot mov...
 
High-Dimensional Feature Matching: Employing the Concept of Meaningful Nearest Neighbors
Found in: Computer Vision, IEEE International Conference on
By Dusan Omercevic, Ondrej Drbohlav, Ales Leonardis
Issue Date:October 2007
pp. 1-8
Matching of high-dimensional features using nearest neighbors search is an important part of image matching methods which are based on local invariant features. In this work we highlight effects pertinent to high-dimensional spaces that are significant for...
 
Hierarchical Statistical Learning of Generic Parts of Object Structure
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sanja Fidler, Gregor Berginc, Ales Leonardis
Issue Date:June 2006
pp. 182-189
With the growing interest in object categorization various methods have emerged that perform well in this challenging task, yet are inherently limited to only a moderate number of object classes. In pursuit of a more general categorization system this pape...
 
Visual Learning and Recognition of a Probabilistic Spatio-Temporal Model of Cyclic Human Locomotion
Found in: Pattern Recognition, International Conference on
By Miha Peternel, Ales Leonardis
Issue Date:August 2004
pp. 146-149
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of continuous, phase aligned spatio-temporal curves from trajectories of random...
 
Workshop on Generic Object Recognition and Categorization
Found in: Computer Vision and Pattern Recognition Workshop
By Sven Dickinson, Ales Leonardis, Bernt Schiele
Issue Date:July 2004
pp. 26
We discuss the issues and challenges of generic object recognition. We argue that high-level, volumetric part-based descriptions are essential in the process of recognizing objects that might never have been observed before, and for which no exact geometri...
 
Robust LDA Classification by Subsampling
Found in: Computer Vision and Pattern Recognition Workshop
By Sanja Fidler, Ales Leonardis
Issue Date:June 2003
pp. 97
In this paper we present a new method which enables a robust calculation of the LDA classification rule, thus making the recognition of objects under non-ideal conditions possible, i.e., in situations when objects are occluded or they appear on a varying b...
 
Incremental PCA or On-Line Visual Learning and Recognition
Found in: Pattern Recognition, International Conference on
By Matej Artač, Matjaž Jogan, Aleš Leonardis
Issue Date:August 2002
pp. 30781
The methods for visual learning that compute a space of eigenvectors by Principal Component Analysis (PCA) traditionally require a batch computation step. Since this leads to potential problems when dealing with large sets of images, several incremental me...
 
Range Image Acquisition of Objects with Non-Uniform Albedo Using Structured Light Range Sensor
Found in: Pattern Recognition, International Conference on
By Danijel Skocaj, Ales Leonardis
Issue Date:September 2000
pp. 1778
We present a novel approach to acquisition of range images of objects with non-uniform albedo using a structured light sensor. The main idea is to systematically vary the intensity of the light projector and to form high dynamic scale radiance maps. The ra...
 
Multiple Eigenspaces by MDL
Found in: Pattern Recognition, International Conference on
By Ales Leonardis, Horst Bischof
Issue Date:September 2000
pp. 1233
In this paper, we propose a novel approach to constructing multiple eigenspaces from a set of training images based on the MDL principle. The main idea is to systematically build a redundant set of eigenspaces, which are treated as hypotheses that are then...
 
Robust Localization Using Eigenspace of Spinning-Images
Found in: Omnidirectional Vision, Workshop on
By Matjaz Jogan, Ales Leonardis
Issue Date:June 2000
pp. 37
No summary available.
 
A Robust Subspace Classifier
Found in: Pattern Recognition, International Conference on
By Horst Bischof, Ales Leonardis, Florian Pezzei
Issue Date:August 1998
pp. 114
No summary available.
 
MDL-Based of Vector Quantizers
Found in: Pattern Recognition, International Conference on
By Horst Bischof, Ales Leonardis
Issue Date:August 1998
pp. 891
No summary available.
 
 1