Sciweavers

911 search results - page 94 / 183
» Modeling vs. Segmenting Images Using A Probabilistic Approac...
Sort
View
MM
2003
ACM
132views Multimedia» more  MM 2003»
14 years 2 months ago
On image auto-annotation with latent space models
Image auto-annotation, i.e., the association of words to whole images, has attracted considerable attention. In particular, unsupervised, probabilistic latent variable models of t...
Florent Monay, Daniel Gatica-Perez
ICCV
2007
IEEE
14 years 3 months ago
Multispectral Imaging Using Multiplexed Illumination
Many vision tasks such as scene segmentation, or the recognition of materials within a scene, become considerably easier when it is possible to measure the spectral reflectance o...
Jong-Il Park, Moon-Hyun Lee, Michael D. Grossberg,...
ICIP
2004
IEEE
14 years 10 months ago
Unsupervised motion detection using a markovian temporal model with global spatial constraints
In this work, we propose an unsupervised Bayesian model for the detection of moving objects from dynamic scenes. This unsupervised solution is a three-step approach that uses a st...
Pierre-Marc Jodoin, Max Mignotte
ECCV
2006
Springer
14 years 10 months ago
Unsupervised Texture Segmentation with Nonparametric Neighborhood Statistics
Abstract. This paper presents a novel approach to unsupervised texture segmentation that relies on a very general nonparametric statistical model of image neighborhoods. The method...
Suyash P. Awate, Tolga Tasdizen, Ross T. Whitaker
ICRA
2009
IEEE
190views Robotics» more  ICRA 2009»
14 years 3 months ago
Whole body motion primitive segmentation from monocular video
Abstract— This paper proposes a novel approach for motion primitive segmentation from continuous full body human motion captured on monocular video. The proposed approach does no...
Dana Kulic, Dongheui Lee, Yoshihiko Nakamura