Publikační činnost - 13133
Zobrazují se záznamy 21-40 z 110
-
Line Filtering for Surgical Tool Localization in 3D Ultrasound Images
(Elsevier, 2013)We present a method for automatic surgical tool localization in 3D ultrasound images based on line ltering, voxel classi cation and model tting. A possible application is to provide assistance for biopsy needle or ... -
Fast Detection of Multiple Textureless 3-D Objects
(Springer, 2013)We propose a fast edge-based approach for detection and approximate pose estimation of multiple textureless objects in a single image. The objects are trained from a set of edge maps, each showing one object in one pose. ... -
What Is Decreased by the Max-sum Arc Consistency Algorithm?
(ACM, 2007)Inference tasks in Markov random fields (MRFs) are closely related to the constraint satisfaction problem (CSP) and its soft generalizations. In particular, MAP inference in MRF is equivalent to the weighted (maxsum) CSP. ... -
A Linear Programming Approach to Max-sum Problem: A Review
(Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, 2005-12)The max-sum labeling problem, de ned as maximizing a sum of functions of pairs of discrete variables, is a general optimization problem with numerous applications, e.g., computing MAP assignments of a Markov random eld. ... -
Revisiting the Decomposition Approach to Inference in Exponential Families and Graphical Models
(Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, 2009-05) -
Fixed Points of Loopy Belief Propagation as Zero Gradients of a Function of Reparameterizations
(Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, 2010-02)The existing view on loopy belief propagation sees it as an algorithm to nd a common zero of a system of non-linear functions, not explicitly related to each other. We show that these functions are in fact related { they ... -
Joint Orientation of Epipoles
(British Machine Vision Association, 2003-09)It is known that epipolar constraint can be augmented with orientation by formulating it in the oriented projective geometry. This oriented epipolar constraint requires knowing the orientations (signs of overall scales) ... -
Model Selection for Automated Architectural Reconstruction from Multiple Views
(British Machine Vision Conference (BMVC), 2002-09)We describe progress in automatically fitting a plane plus modelled perturbation surface model to represent architectural scenes. There are two areas of novelty. The first is a method of fitting parametrized models in which ... -
Marginal Consistency: Unifying Constraint Propagation on Commutative Semirings
(Institute National de la Recherche Agronomique, 2008-09)We generalise the linear programming relaxation approach to Weighted CSP by Schlesinger and the max-sum diffusion algorithm by Koval and Kovalevsky twice: from Weighted CSP to Semiring CSP, and from binary networks to ... -
Primal View on Belief Propagation
(AUAI Press, 2010-07)It is known that xed points of loopy belief propagation (BP) correspond to stationary points of the Bethe variational problem, where we minimize the Bethe free energy subject to normalization and marginalization constraints. ... -
Unified Framework for Semiring-Based Arc Consistency and Relaxation Labeling
(Verlag der Technischen Universität Graz, 2007-02)Constraint Satisfaction Problem (CSP), including its soft modifications, is ubiquitous in artificial intelligence and related fields. In computer vision and pattern recognition, the crisp CSP is more known as the consistent ... -
Revisiting the Linear Programming Relaxation Approach to Gibbs Energy Minimization and Weighted Constraint Satisfaction
(IEEE, 2010)We present a number of contributions to the LP relaxation approach to weighted constraint satisfaction (= Gibbs energy minimization). We link this approach to many works from constraint programming, which relation has so ... -
Zero-Temperature Limit of a Convergent Algorithm to Minimize the Bethe Free Energy
(Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, 2011-12)After the discovery that xed points of loopy belief propagation coincide with stationary points of the Bethe free energy, several researchers proposed provably convergent algorithms to directly minimize the Bethe free ... -
Number of arrhythmia beats determination in Holter electrocardiogram: How many clusters?
(IEEE, 2003-09)Holter signals correspond to long-term electrocardiograph (ECG) registers. Manual inspection of such signals is difficult because of the enormous quantity of beats involved. Throughout the literature several methods of ... -
Multimethod machine learning approach for medical diagnosing
(IEEE, 2003-04)In this paper we present a multimethod approach for induction of a specific class of classifiers, which can assist physicians in medical diagnosing in the case of mitral valve prolapse. Mitral valve prolapse is one of the ... -
Large-Scale Discovery of Spatially Related Images
(IEEE, 2010-02)We propose a randomized data mining method that finds clusters of spatially overlapping images. The core of the method relies on the min-Hash algorithm for fast detection of pairs of images with spatial overlap, the so-called ... -
Unsupervised Discovery of Co-occurrence in Sparse High Dimensional Data
(IEEE, 2010-06)An efficient min-Hash based algorithm for discovery of dependencies in sparse high-dimensional data is presented. The dependencies are represented by sets of features co-occurring with high probability and are called ... -
Efficient Sequential Correspondence Selection by Cosegmentation
(IEEE, 2008-06)In many retrieval, object recognition and wide baseline stereo methods, correspondences of interest points are established possibly sublinearly by matching a compact descriptor such as SIFT. We show that a subsequent ... -
Geometric min-Hashing: Finding a (Thick) Needle in a Haystack
(IEEE, 2009-06)We propose a novel hashing scheme for image retrieval, clustering and automatic object discovery. Unlike commonly used bag-of-words approaches, the spatial extent of image features is exploited in our method. The geometric ...