Sciweavers

CVPR
2007
IEEE
15 years 5 days ago
Multi-label image segmentation via max-sum solver
We formulate single-image multi-label segmentation into regions coherent in texture and color as a MAX-SUM problem for which efficient linear programming based solvers have recent...
Branislav Micusík, Tomás Pajdla
CVPR
2007
IEEE
15 years 5 days ago
Face Recognition using Discriminatively Trained Orthogonal Rank One Tensor Projections
We propose a method for face recognition based on a discriminative linear projection. In this formulation images are treated as tensors, rather than the more conventional vector o...
Gang Hua, Paul A. Viola, Steven M. Drucker
CVPR
2007
IEEE
15 years 5 days ago
Tree-based Classifiers for Bilayer Video Segmentation
This paper presents an algorithm for the automatic segmentation of monocular videos into foreground and background layers. Correct segmentations are produced even in the presence ...
Pei Yin, Antonio Criminisi, John M. Winn, Irfan A....
CVPR
2007
IEEE
15 years 5 days ago
Compositional Boosting for Computing Hierarchical Image Structures
In this paper, we present a compositional boosting algorithm for detecting and recognizing 17 common image structures in low-middle level vision tasks. These structures, called &q...
Tianfu Wu, Gui-Song Xia, Song Chun Zhu
CVPR
2007
IEEE
15 years 5 days ago
Kernel-based Tracking from a Probabilistic Viewpoint
In this paper, we present a probabilistic formulation of kernel-based tracking methods based upon maximum likelihood estimation. To this end, we view the coordinates for the pixel...
Quang Anh Nguyen, Antonio Robles-Kelly, Chunhua Sh...
CVPR
2007
IEEE
15 years 5 days ago
Stereo Matching via Disparity Estimation and Surface Modeling
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a dispar...
Jong Dae Oh, Siwei Ma, C. C. Jay Kuo
CVPR
2007
IEEE
15 years 5 days ago
Light Fall-off Stereo
We present light fall-off stereo?LFS?a new method for computing depth from scenes beyond lambertian reflectance and texture. LFS takes a number of images from a stationary camera ...
Miao Liao, Liang Wang, Ruigang Yang, Minglun Gong
CVPR
2007
IEEE
15 years 5 days ago
Multiphase Segmentation of Deformation using Logarithmic Priors
In [8], the authors proposed the large deformation logunbiased diffeomorphic nonlinear image registration model which has been successfully used to obtain theoretically and intuit...
Igor Yanovsky, Paul M. Thompson, Stanley Osher, Lu...
CVPR
2007
IEEE
15 years 5 days ago
Learning Features for Tracking
We treat tracking as a matching problem of detected keypoints between successive frames. The novelty of this paper is to learn classifier-based keypoint descriptions allowing to i...
Michael Grabner, Helmut Grabner, Horst Bischof
CVPR
2007
IEEE
15 years 5 days ago
Segmenting Motions of Different Types by Unsupervised Manifold Clustering
We propose a novel algorithm for segmenting multiple motions of different types from point correspondences in multiple affine or perspective views. Since point trajectories associ...
Alvina Goh, René Vidal