Sciweavers

CVPR
2005
IEEE
14 years 11 months ago
Radon-Based Structure from Motion without Correspondences
We present a novel approach for the estimation of 3Dmotion directly from two images using the Radon transform. We assume a similarity function defined on the crossproduct of two i...
Ameesh Makadia, Christopher Geyer, Shankar Sastry,...
CVPR
2005
IEEE
14 years 11 months ago
Contrast Enhancement of Multi-Displays Using Human Contrast Sensitivity
Study of contrast sensitivity of the human eye shows that we are more sensitive to brightness differences at low intensity levels than at high intensity levels. We apply this fact...
Aditi Majumder
CVPR
2005
IEEE
14 years 11 months ago
Detecting Doctored Images Using Camera Response Normality and Consistency
The advance in image/video editing techniques has facilitated people in synthesizing realistic images/videos that may hard to be distinguished from real ones by visual examination...
Zhouchen Lin, Rongrong Wang, Xiaoou Tang, Heung-Ye...
CVPR
2005
IEEE
14 years 11 months ago
Determining the Radiometric Response Function from a Single Grayscale Image
A method is presented for computing the radiometric response function of a camera from a single grayscale image. While most previous techniques require a set of registered images ...
Stephen Lin, Lei Zhang
CVPR
2005
IEEE
14 years 11 months ago
Using the Inner-Distance for Classification of Articulated Shapes
We propose using the inner-distance between landmark points to build shape descriptors. The inner-distance is defined as the length of the shortest path between landmark points wi...
Haibin Ling, David W. Jacobs
CVPR
2005
IEEE
14 years 11 months ago
Mercer Kernels for Object Recognition with Local Features
A new class of kernels for object recognition based on local image feature representations are introduced in this paper. These kernels satisfy the Mercer condition and incorporate...
Siwei Lyu
CVPR
2005
IEEE
14 years 11 months ago
Infomax Boosting
In this paper, we described an efficient feature pursuit scheme for boosting. The proposed method is based on the infomax principle, which seeks optimal feature that achieves maxi...
Siwei Lyu
CVPR
2005
IEEE
14 years 11 months ago
A Direct Method for Modeling Non-Rigid Motion with Thin Plate Spline
Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspond...
Jongwoo Lim, Ming-Hsuan Yang
CVPR
2005
IEEE
14 years 11 months ago
A Caratheodory-Fejer Approach to Dynamic Appearance Modeling
This paper presents a technique to learn dynamic appearance models from a small number of training frames. Under this framework, dynamic appearance is modelled as an unknown opera...
Hwasup Lim, Octavia I. Camps, Mario Sznaier
CVPR
2005
IEEE
14 years 11 months ago
A Two Level Approach for Scene Recognition
Classifying pictures into one of several semantic categories is a classical image understanding problem. In this paper, we present a stratified approach to both binary (outdoor-in...
Le Lu, Kentaro Toyama, Gregory D. Hager