90%
kr
5Seoul National University15 Jun 11
cn
2Huazhong University of Science and Technology09 Jun 11
ch
2University of Berne10 Jun 11
jp
1Shibaura Institute of Technology25 May 11
tw
1Yuan ZHI College15 Jun 11
nz
1Victoria University of Wellington10 Oct 14
il
1the Hebrew University of Jerusalem03 Jun 11
ca
1University of Alberta20 May 11
us
1University of Missouri Columbia08 Jun 11
us
1Ohio State University03 Jun 11
jp
1Osaka University12 Jun 11
tw
1National Dong HWA University07 Jun 11
il
1BEN Gurion University Network31 May 11
gb
1University of Sussex09 Jun 11
us
1University of Pennsylvania13 Jun 11
kr
1Seoul National University of Technology15 Jun 11
us
1Siemens Corp Research27 May 11
us
619United States
un
114
cn
68China
tr
13Turkey
de
13Germany
ru
11Russian Federation
kr
10Korea, Republic of
fr
5France
ua
4Ukraine
nl
4Netherlands
jp
3Japan
gb
3United Kingdom
vn
3Vietnam
se
3Sweden
ch
2Switzerland
ng
2Nigeria
il
2Israel
tw
2Taiwan
pl
2Poland
it
1Italy
ca
1Canada
nz
1New Zealand
ir
1Iran, Islamic Republic of
Visual tracking on the affine group via geometric particle filtering using optimal importance function
Visual tracking on the affine group via geometric particle filtering using optimal importance function
cv.snu.ac.kr
We propose a geometric method for visual tracking, in which the 2-D affine motion of a given object template is estimated in a video sequence by means of coordi...
2305 views   117 votes
IEEE Junghyun Kwon (Seoul National University), Kyoung Mu Lee (Seoul National University), Frank Park (Seoul National University)
Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space
Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space
cv.snu.ac.kr
Radiometric variations between input images can seriously degrade the performance of stereo matching algorithms. In this situation, mutual information is a ve...
1930 views   110 votes
IEEE Yong Seok Heo (Seoul National University), Kyoung Mu Lee (Seoul National University), Sang Uk Lee (Seoul National University)
Simultaneous Color Consistency and Depth Map Estimation for Radiometrically Varying Stereo Images
Simultaneous Color Consistency and Depth Map Estimation for Radiometrically Varying Stereo Images
cv.snu.ac.kr
In this paper, we propose a new method that infers accurate depth maps and color-consistent images between radiometrically varying stereo images, simultaneously...
1849 views   98 votes
IEEE Yong Seok Heo (Seoul National University), Kyoung Mu Lee (Seoul National University), and Sang Uk Lee (Seoul National University)
Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering
Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering
cv.snu.ac.kr
We present an efficient method for feature correspondence and object-based image matching, which exploits both photometric similarity and pairwise geometric con...
1821 views   95 votes
IEEE Minsu Cho (Seoul National University), Jungmin Lee (Seoul National University), Kyoung Mu Lee (Seoul National University)
Unsupervised Detection and Segmentation of Identical Objects
Unsupervised Detection and Segmentation of Identical Objects
cv.snu.ac.kr
We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or model...
1341 views   74 votes
IEEE Minsu Cho (Seoul National University), Young Min Shin (Seoul National University), Kyoung Mu Lee (Seoul National University)
Visual Tracking Decomposition
Visual Tracking Decomposition
cv.snu.ac.kr
We propose a novel tracking algorithm that can work robustly in a challenging scenario such that several kinds of appearance and motion changes of an object occ...
1208 views   70 votes
IEEE Junseok Kwon (Seoul National University), Kyoung Mu Lee (Seoul National University)
Reweighted Random Walks for Graph Matching
Reweighted Random Walks for Graph Matching
cv.snu.ac.kr
Graph matching is an essential problem in computer vision and machine learning. In this paper, we introduce a random walk view on the problem and propose a robu...
991 views   92 votes
Springer Minsu Cho (Seoul National University), Jungmin Lee (Seoul National University), Kyoung Mu Lee (Seoul National University)
Learning Full Pairwise Affinities for Spectral Segmentation
Learning Full Pairwise Affinities for Spectral Segmentation
cv.snu.ac.kr
This paper studies the problem of learning a full range of pairwise affinities gained by integrating local grouping cues for spectral segmentation. The overall ...
927 views   65 votes
IEEE Tae Hoon Kim (Seoul National University), Kyoung Mu Lee (Seoul National University), Sang Uk Lee (Seoul National University)
Generative Image Segmentation Using Random Walks with Restart
Generative Image Segmentation Using Random Walks with Restart
cv.snu.ac.kr
We consider the problem of multi-label, supervised image segmentation when an initial labeling of some pixels is given. In this paper, we propose a new generati...
805 views   66 votes
Springer Tae Hoon Kim (Seoul National University), Kyoung Mu Lee (Seoul National University), Sang Uk Lee (Seoul National University)
Authority-Shift Clustering: Hierarchical Clustering by Authority Seeking on Graphs
Authority-Shift Clustering: Hierarchical Clustering by Authority Seeking on Graphs
cv.snu.ac.kr
In this paper, a novel hierarchical clustering method using link analysis techniques is introduced. The algorithm is formulated as an authority seeking procedur...
796 views   62 votes
IEEE Minsu Cho (Seoul National University), Kyoung Mu Lee (Seoul National University)
Hyper-graph Matching via Reweighted Random Walks
Hyper-graph Matching via Reweighted Random Walks
cv.snu.ac.kr
Establishing correspondences between two feature sets is a fundamental issue in computer vision, pattern recognition, and machine learning. This problem can be ...
760 views   103 votes
IEEE Jungmin Lee (Seoul National University), Minsu Cho (Seoul National University), Kyoung Mu Lee (Seoul National University)
Monocular SLAM with Locally Planar Landmarks via Geometric Rao-Blackwellized Particle Filtering on Lie groups
Monocular SLAM with Locally Planar Landmarks via Geometric Rao-Blackwellized Particle Filtering on Lie groups
cv.snu.ac.kr
We propose a novel geometric Rao-Blackwellized particle filtering framework for monocular SLAM with locally planar landmarks. We represent the states for the ca...
687 views   70 votes
IEEE Junghyun Kwon (Seoul National University) and Kyoung Mu Lee (Seoul National University)
Tracking of a Non-Rigid Object via Patch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling
Tracking of a Non-Rigid Object via Patch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling
cv.snu.ac.kr
We propose a novel tracking algorithm for the target of which geometric appearance changes drastically over time. To track it, we present a local patch-based ap...
634 views   70 votes
IEEE Junseok Kwon (Seoul National University), Kyoung Mu Lee (Seoul National University)
Illumination and Camera Invariant Stereo Matching
Illumination and Camera Invariant Stereo Matching
cv.snu.ac.kr
Color information can be used as a basic and crucial cue for finding correspondence in a stereo matching algorithm. In a real scene, however, image colors are a...
588 views   55 votes
IEEE Yong Seok Heo (Seoul National University), Kyoung Mu Lee (Seoul National University), and Sang Uk Lee (Seoul National University)
Nonparametric Higher-Order Learning for Interactive Segmentation
Nonparametric Higher-Order Learning for Interactive Segmentation
cv.snu.ac.kr
In this paper, we deal with a generative model for multi-label, interactive segmentation. To estimate the pixel likelihoods for each label, we propose a new hig...
572 views   56 votes
IEEE Tae Hoon Kim (Seoul National University), Kyoung Mu Lee (Seoul National University), Sang Uk Lee (Seoul National University)
A Graph Matching Algorithm using Data-Driven Markov Chain Monte Carlo Sampling
A Graph Matching Algorithm using Data-Driven Markov Chain Monte Carlo Sampling
cv.snu.ac.kr
We propose a novel stochastic graph matching algorithm based on data-driven Markov Chain Monte Carlo (DDMCMC) sampling technique. The algorithm explores the sol...
530 views   83 votes
IEEE Jungmin Lee, Minsu Cho, Kyoung Mu Lee
Markov Chain Monte Carlo Combined with Deterministic Methods for Markov Random Field Optimization
Markov Chain Monte Carlo Combined with Deterministic Methods for Markov Random Field Optimization
cv.snu.ac.kr
Many vision problems have been formulated as en- ergy minimization problems and there have been signif- icant advances in energy minimization algorithms. The mo...
427 views   67 votes
IEEE Wonsik Kim (Seoul National University), Kyoung Mu Lee (Seoul National University)
Edge-preserving Colorization using Data-Driven Random Walks with Restart
Edge-preserving Colorization using Data-Driven Random Walks with Restart
cv.snu.ac.kr
In this paper, we consider the colorization problem of grayscale images in which some color scribbles are initially given. Our proposed method is based on the w...
398 views   67 votes
IEEE Tae Hoon Kim (Seoul National University), Kyoung Mu Lee (Seoul National University), and Sang Uk Lee (Seoul National University)
CV-SLAM: A new ceiling vision-based SLAM technique
CV-SLAM: A new ceiling vision-based SLAM technique
cv.snu.ac.kr
We propose a fast and robust CV-SLAM (Ceiling Vision –based Simultaneous Localization and Mapping) technique using a single ceiling vision sensor. The propose...
364 views   84 votes
IEEE Woo Yeon Jeong (Seoul National University), Kyoung Mu Lee (Seoul National University)
Toward Global Minimum through Combined Local Minima
Toward Global Minimum through Combined Local Minima
cv.snu.ac.kr
There are many local and greedy algorithms for energy minimization over Markov Random Field (MRF) such as iterated condition mode (ICM) and various gradient des...
356 views   58 votes
Springer Ho Yub Jung, Kyoung Mu Lee, Sang Uk Lee
Shape from Shading with Perspective Projection
Shape from Shading with Perspective Projection
cv.snu.ac.kr
Most conventional SFS (shape from shading) algorithms have been developed under the assumption of orthographic projection. However, the assumption is not valid ...
353 views   57 votes
Kyoung Mu Lee (Seoul National University), C.-C. J. Kuo
Tracking of Abrupt Motion using Wang-Landau Monte Carlo Estimation
 Tracking of Abrupt Motion using Wang-Landau Monte Carlo Estimation
cv.snu.ac.kr
We propose a novel tracking algorithm based on the Wang-Landau Monte Carlo sampling method which efficiently deals with the abrupt motions. Abrupt motions could...
345 views   62 votes
Springer Junseok Kwon (Seoul National University), Kyoung Mu Lee (Seoul National University)
Continuous Markov Random Field Optimization using Fusion Move Driven Markov Chain Monte Carlo Technique
Continuous Markov Random Field Optimization using Fusion Move Driven Markov Chain Monte Carlo Technique
cv.snu.ac.kr
Many vision applications have been formulated as Markov Random Field (MRF) problems. Although many of them are discrete labeling problems, continuous formulatio...
342 views   62 votes
IEEE Wonsik Kim (Seoul National University), Kyoung Mu Lee (Seoul National University)
Shape from Shading with a Generalized Reflectance Map Model
Shape from Shading with a Generalized Reflectance Map Model
cv.snu.ac.kr
Most conventional SFS (shape from shading) algorithms have been developed under three basic assumptions on surface properties and imaging geometry to simplify t...
338 views   70 votes
Kyoung Mu Lee (Seoul National University), C.-C. J. Kuo
Ghost-free High Dynamic Range Imaging
Ghost-free High Dynamic Range Imaging
cv.snu.ac.kr
Most high dynamic range image (HDRI) algorithms assume stationary scene for registering multiple images which are taken under different exposure settings. In pr...
331 views   88 votes
Springer Yong Seok Heo (Seoul National University), Kyoung Mu Lee (Seoul National University), Sang Uk Lee (Seoul National University), Youngsu Moon(SAMSUNG), and Joonhyuk Cha(SAMSUNG)
Shape from shading with a linear triangular element surface model
Shape from shading with a linear triangular element surface model
cv.snu.ac.kr
We propose to combine a triangular element surface model with a linearized reflectance map to formulate the shape-from-shading problem. The main idea is to appr...
323 views   43 votes
Kyoung Mu Lee (Seoul National University), C.-C. J. Kuo
Partially Occluded Object-Specific Segmentation in View-Based Recognition
Partially Occluded Object-Specific Segmentation in View-Based Recognition
cv.snu.ac.kr
We present a novel object-specific segmentation method which can be used in view-based object recognition systems. Previous object segmentation approaches gener...
323 views   55 votes
IEEE Minsu Cho (Seoul National University), Kyoung Mu Lee (Seoul National University)
Co-Recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration
Co-Recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration
cv.snu.ac.kr
We introduce a new concept of co-recognition for object-level image matching between an arbitrary image pair. Our method augments putative local regionmatches...
314 views   62 votes
Springer Minsu Cho (Seoul National University), Young Min Shin (Seoul National University), and Kyoung Mu Lee (Seoul National University)
Co-recognition of Actions in Video Pairs
Co-recognition of Actions in Video Pairs
cv.snu.ac.kr
In this paper, we present a method that recognizes single or multiple common actions between a pair of video sequences. We establish an energy function that eva...
289 views   60 votes
IEEE Young Min Shin (Seoul National University), Minsu Cho (Seoul National University), Kyoung Mu Lee (Seoul National University)
Bilateral Symmetry Detection and Segmentation via Symmetry-Growing
Bilateral Symmetry Detection and Segmentation via Symmetry-Growing
cv.snu.ac.kr
We present a novel and robust method for localizing and segmenting bilaterally symmetric patterns from real-world images. On the basis of symmetrically matched ...
285 views   62 votes
Minsu Cho (Seoul National University), Kyoung Mu Lee (Seoul National University)
Stereo Matching Using Population-Based MCMC
Stereo Matching Using Population-Based MCMC
cv.snu.ac.kr
In this paper, we propose a new stereo matching method using the population-based Markov Chain Monte Carlo (Pop-MCMC), which belongs to the sampling-based metho...
282 views   55 votes
Wonsik Kim (Seoul National University), Joonyoung Park (Seoul National University), Kyoung Mu Lee (Seoul National University)
Simultaneous Depth Reconstruction and Restoration of Noisy Stereo Images Using Non-local Pixel Distribution
Simultaneous Depth Reconstruction and Restoration of Noisy Stereo Images Using Non-local Pixel Distribution
cv.snu.ac.kr
In this paper, we propose a new algorithm that solves both the stereo matching and the image denoising problem simultaneously for a pair of noisy stereo images....
234 views   71 votes
IEEE Yong Seok Heo (Seoul National University), Kyoung Mu Lee (Seoul National University), and Sang Uk Lee (Seoul National University)
A Unified Probabilistic Approach to Feature Matching and Object Segmentation
A Unified Probabilistic Approach to Feature Matching and Object Segmentation
cv.snu.ac.kr
This paper deals with feature matching and segmentation of common objects in a pair of images, simultaneously. For the feature matching problem, the matching li...
220 views   72 votes
IEEE Tae Hoon Kim (Seoul National University), Kyoung Mu Lee (Seoul National University), Sang Uk Lee (Seoul National University)
Window Annealing over Square Lattice Markov Random Field
Window Annealing over Square Lattice Markov Random Field
cv.snu.ac.kr
Monte Carlo methods and their subsequent simulated annealing are able to minimize general energy functions. However, the slow convergence of simulated annealing...
215 views   55 votes
Springer Ho Yub Jung, Kyoung Mu Lee, Sang Uk Lee
Incorporating Higher-Order Cues in Image Colorization
Incorporating Higher-Order Cues in Image Colorization
cv.snu.ac.kr
We consider the colorization problem of grayscale images when some pixels, called scribbles, with initial colors are given. In this paper, we propose a new mult...
207 views   50 votes
Tae Hoon Kim (Seoul National University), Kyoung Mu Lee (Seoul National University), and Sang Uk Lee (Seoul National University)
about kyoungmu
Powered by
sciweavers