Sciweavers

CVPR
2007
IEEE
14 years 11 months ago
Flash Cut: Foreground Extraction with Flash and No-flash Image Pairs
In this paper, we propose a novel approach for foreground layer extraction using flash/no-flash image pairs, which we call flash cut. Flash cut is based on the simple observation t...
Jian Sun, Sing Bing Kang, Zong-Ben Xu, Xiaoou Tang...
CVPR
2007
IEEE
14 years 11 months ago
Radiometric Calibration from Noise Distributions
A method is proposed for estimating radiometric response functions from noise observations. From the statistical properties of noise sources, the noise distribution for each scene...
Yasuyuki Matsushita, Stephen Lin
CVPR
2007
IEEE
14 years 11 months ago
A Unified Probabilistic Framework for Facial Activity Modeling and Understanding
Facial activities are the most natural and powerful means of human communication. Spontaneous facial activity is characterized by rigid head movements, non-rigid facial muscular m...
Yan Tong, Wenhui Liao, Zheng Xue, Qiang Ji
CVPR
2007
IEEE
14 years 11 months ago
A practical algorithm for L triangulation with outliers
This paper addresses the problem of robust optimal multi-view triangulation. We propose an abstract framework, as well as a practical algorithm, which finds the best 3D reconstruc...
Hongdong Li
CVPR
2007
IEEE
14 years 11 months ago
Kernel Sharing With Joint Boosting For Multi-Class Concept Detection
Object/scene detection by discriminative kernel-based classification has gained great interest due to its promising performance and flexibility. In this paper, unlike traditional ...
Wei Jiang, Shih-Fu Chang, Alexander C. Loui
CVPR
2007
IEEE
14 years 11 months ago
Image Matching via Saliency Region Correspondences
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
Alexander Toshev, Jianbo Shi, Kostas Daniilidis
CVPR
2007
IEEE
14 years 11 months ago
Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection
Tracking objects using the mean shift method is performed by iteratively translating a kernel in the image space such that the past and current object observations are similar. Tr...
Alper Yilmaz
CVPR
2007
IEEE
14 years 11 months ago
Modulation Domain Template Tracking
For the first time, we perform normalized correlation template tracking in the modulation domain. For each frame of the video sequence, we compute a multi-component AM-FM image mo...
Chuong T. Nguyen, Joseph P. Havlicek, Mark B. Year...