CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
We describe an unsupervised method to segment objects detected in images using a novel variant of an interest point template, which is very efficient to train and evaluate. Once a...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
We present a parameter free approach that utilizes multiple cues for image segmentation. Beginning with an image, we execute a sequence of bottom-up aggregation steps in which pix...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
In this paper, we present a method using pixel-level information, local region-level information and global-level information to remove shadow. At the pixel-level, we employ GMM t...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
We introduce an epitomic representation for modeling human activities in video sequences. A video sequence is divided into segments within which the dynamics of objects is assumed...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
While face recognition techniques have rapidly advanced in the last few years, most of the work is in the domain of security applications. For consumer imaging applications, perso...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
We present DIGITABLE, an experimental platform we hope lessen the gap between co-present and distant interaction. DIGITABLE is combining a multiuser tactile interactive tabletop, ...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
We propose a framework for detecting and tracking multiple interacting objects, while explicitly handling the dual problems of fragmentation (an object may be broken into several ...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
Many vision tasks are posed as either graph partitioning (coloring) or graph matching (correspondence) problems. The former include segmentation and grouping, and the latter inclu...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous se...