Sciweavers

ICCV
2009
IEEE
1849views Computer Vision» more  ICCV 2009»
14 years 9 months ago
Simultaneous Color Consistency and Depth Map Estimation for Radiometrically Varying Stereo Images
In this paper, we propose a new method that infers accurate depth maps and color-consistent images between radiometrically varying stereo images, simultaneously. In general, stereo...
Yong Seok Heo (Seoul National University), Kyoung ...
ICCV
2009
IEEE
1821views Computer Vision» more  ICCV 2009»
14 years 9 months ago
Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering
We present an efficient method for feature correspondence and object-based image matching, which exploits both photometric similarity and pairwise geometric consistency from local ...
Minsu Cho (Seoul National University), Jungmin Lee...
ICCV
2009
IEEE
14 years 9 months ago
What is the Best Multi-Stage Architecture for Object Recognition?
In many recent object recognition systems, feature extraction stages are generally composed of a filter bank, a non-linear transformation, and some sort of feature pooling layer...
Kevin Jarrett, Koray Kavukcuoglu, Marc’Aurelio R...
ICCV
2009
IEEE
14 years 9 months ago
Estimating Contact Dynamics
Motion and interaction with the environment are fundamentally intertwined. Few people-tracking algorithms exploit such interactions, and those that do assume that surface geomet...
Marcus A. Brubaker Leonid Sigal David J. Fleet
ICCV
2009
IEEE
1022views Computer Vision» more  ICCV 2009»
14 years 9 months ago
Kernelized Locality-Sensitive Hashing for Scalable Image Search
Fast retrieval methods are critical for large-scale and data-driven vision applications. Recent work has explored ways to embed high-dimensional features or complex distance fun...
Brian Kulis, Kristen Grauman
ICCV
2009
IEEE
1035views Computer Vision» more  ICCV 2009»
14 years 9 months ago
Efficient High-Quality Image Contour Detection
Image contour detection is fundamental to many image analysis applications, including image segmentation, object recognition and classification. However, highly accurate image c...
Bryan Catanzaro, Bor-Yiing Su, Narayanan Sundaram,...
ICCV
2009
IEEE
14 years 9 months ago
Video Scene Understanding Using Multi-scale Analysis
We propose a novel method for automatically discover-ing key motion patterns happening in a scene by observing the scene for an extended period. Our method does not rely on object ...
Yang Yang, Jingen Liu, Mubarak Shah
ICCV
2009
IEEE
14 years 9 months ago
Tensor completion for estimating missing values in visual data
In this paper we propose an algorithm to estimate missing values in tensors of visual data. The values can be missing due to problems in the acquisition process, or because the ...
Ji Liu, Przemyslaw Musialski, Peter Wonka, Jieping...
ICCV
2009
IEEE
14 years 9 months ago
Structure- and Motion-adaptive Regularization for High Accuracy Optic Flow
The accurate estimation of motion in image sequences is of central importance to numerous computer vision applications. Most competitive algorithms compute flow fields by minimi...
Andreas Wedel, Daniel Cremers, Thomas Pock, Horst ...
ICCV
2009
IEEE
14 years 9 months ago
Using machine learning to predict where people look
For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene. Where eye tracking devices are not a viable o...
Tilke Judd, Krista Ehinger, Fr´edo Durand, Antoni...