CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
In this paper, we deal with a generative model for multi-label, interactive segmentation. To estimate the pixel likelihoods for each label, we propose a new higher-order formulatio...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose at 4-10 frames per second using...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
Automatic facial action unit (AU) detection from video is a long-standing problem in computer vision. Two main approaches have been pursued: (1) static modeling--typically posed a...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
It has been shown that the 3D shape of a deformable surface in an image can be recovered by establishing correspondences between that image and a reference one in which the shape ...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
Given a multi-exposure sequence of a scene, our aim is to recover the absolute irradiance falling onto a linear camera sensor. The established approach is to perform a weighted av...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
We investigate dynamical models of human motion that can
support both synthesis and analysis tasks. Unlike coarser
discriminative models that work well when action classes are ...
CVPR
2010
IEEE
2010
IEEE
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
14 years 8 months ago
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
Optical character recognition (OCR) remains a difficult problem for noisy documents or documents not scanned at high resolution. Many current approaches rely on stored font models...
CVPR
2010
IEEE
14 years 8 months ago
2010
IEEE
Active learning methods aim to select the most informative unlabeled instances to label first, and can help to focus image or video annotations on the examples that will most impr...