Sciweavers

CVPR
2007
IEEE
15 years 1 months ago
Spatial-Depth Super Resolution for Range Images
We present a new post-processing step to enhance the resolution of range images. Using one or two registered and potentially high-resolution color images as reference, we iterativ...
Qingxiong Yang, Ruigang Yang, James Davis, David N...
CVPR
2007
IEEE
15 years 1 months ago
Element Rearrangement for Tensor-Based Subspace Learning
The success of tensor-based subspace learning depends heavily on reducing correlations along the column vectors of the mode-k flattened matrix. In this work, we study the problem ...
Shuicheng Yan, Dong Xu, Stephen Lin, Thomas S. Hua...
CVPR
2007
IEEE
15 years 1 months ago
Improved Video Registration using Non-Distinctive Local Image Features
The task of registering video frames with a static model is a common problem in many computer vision domains. The standard approach to registration involves finding point correspo...
Robin Hess, Alan Fern
CVPR
2007
IEEE
15 years 1 months ago
Feature Extraction by Maximizing the Average Neighborhood Margin
A novel algorithm called Average Neighborhood Margin Maximization (ANMM) is proposed for supervised linear feature extraction. For each data point, ANMM aims at pulling the neighb...
Fei Wang, Changshui Zhang
CVPR
2007
IEEE
15 years 1 months ago
Robust Occlusion Handling in Object Tracking
In object tracking, occlusions significantly undermine the performance of tracking algorithms. Unlike the existing methods that solely depend on the observed target appearance to ...
Jiyan Pan, Bo Hu
CVPR
2007
IEEE
15 years 1 months ago
Trace Ratio vs. Ratio Trace for Dimensionality Reduction
A large family of algorithms for dimensionality reduction end with solving a Trace Ratio problem in the form of arg maxW Tr(WT SpW)/Tr(WT SlW)1 , which is generally transformed in...
Huan Wang, Shuicheng Yan, Dong Xu, Xiaoou Tang, Th...
CVPR
2007
IEEE
15 years 1 months ago
Composite Models of Objects and Scenes for Category Recognition
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
David J. Crandall, Daniel P. Huttenlocher
CVPR
2007
IEEE
15 years 1 months ago
Scene Segmentation and Categorization Using NCuts
For video summarization and retrieval, one of the important modules is to group temporal-spatial coherent shots into high-level semantic video clips namely scene segmentation. In ...
Yanjun Zhao, Tao Wang, Peng Wang, Wei Hu, Yangzhou...
CVPR
2007
IEEE
15 years 1 months ago
Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions
David Gallup, Jan-Michael Frahm, Philippos Mordoha...
CVPR
2007
IEEE
15 years 1 months ago
Discontinuity Preserving Filtering over Analytic Manifolds
Discontinuity preserving filtering of images is an important low-level vision task. With the development of new imaging techniques like diffusion tensor imaging (DTI), where the d...
Raghav Subbarao, Peter Meer