Sciweavers

Share
CVPR
2008
IEEE
8 years 10 months ago
Extracting smooth and transparent layers from a single image
Layer decomposition from a single image is an underconstrained problem, because there are more unknowns than equations. This paper studies a slightly easier but very useful altern...
Sai Kit Yeung, Tai-Pang Wu, Chi-Keung Tang
CVPR
2008
IEEE
8 years 10 months ago
A rank constrained continuous formulation of multi-frame multi-target tracking problem
This paper presents a multi-frame data association algorithm for tracking multiple targets in video sequences. Multi-frame data association involves finding the most probable corr...
Khurram Shafique, Mun Wai Lee, Niels Haering
CVPR
2008
IEEE
8 years 10 months ago
Motion blur identification from image gradients
Restoration of a degraded image from motion blurring is highly dependent on the estimation of the blurring kernel. Most of the existing motion deblurring techniques model the blur...
Hui Ji, Chaoqiang Liu
CVPR
2008
IEEE
9 years 2 months ago
General Constraints for Batch Multiple-Target Tracking Applied to Large-Scale Videomicroscopy
While there is a large class of Multiple-Target Tracking (MTT) problems for which batch processing is possible and desirable, batch MTT remains relatively unexplored in comparis...
Kevin Smith, Alan Carleton, Vincent Lepetit
CVPR
2008
IEEE
9 years 2 months ago
Recovering Shape Characteristics on Near-flat Specular Surfaces
We consider the problem of capturing shape characteristics on specular (refractive and reflective) surfaces that are nearly flat. These surfaces are difficult to model using tradit...
Yuanyuan Ding and Jingyi Yu
CVPR
2008
IEEE
9 years 2 months ago
3D face tracking and expression inference from a 2D sequence using manifold learning
We propose a person-dependent, manifold-based approach for modeling and tracking rigid and nonrigid 3D facial deformations from a monocular video sequence. The rigid and nonrigid ...
Wei-Kai Liao, Gérard G. Medioni
CVPR
2008
IEEE
9 years 2 months ago
Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses
We propose a method that detects and segments multiple, partially occluded objects in images. A part hierarchy is defined for the object class. Whole-object segmentor and part de...
Bo Wu, Ram Nevatia, Yuan Li
CVPR
2008
IEEE
9 years 2 months ago
Learning a geometry integrated image appearance manifold from a small training set
While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
Yilei Xu, Amit K. Roy Chowdhury
CVPR
2008
IEEE
9 years 2 months ago
Object image retrieval by exploiting online knowledge resources
We describe a method to retrieve images found on web pages with specified object class labels, using an analysis of text around the image and of image appearance. Our method dete...
Gang Wang, David A. Forsyth
books