Sciweavers

138 search results - page 12 / 28
» Modeling Dynamic Scenes with Active Appearance
Sort
View
ICCV
2011
IEEE
12 years 9 months ago
Discovering Object Instances from Scenes of Daily Living
We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered sce...
Hongwen Kang, Martial Hebert, Takeo Kanade
CVPR
2005
IEEE
14 years 11 months ago
A Hybrid Graphical Model for Robust Feature Extraction from Video
We consider a visual scene analysis scenario where objects (e.g. people, cars) pass through the viewing field of a static camera and need to be detected and segmented from the bac...
Ali Taylan Cemgil, Wojciech Zajdel, Ben J. A. Kr&o...
ICASSP
2011
IEEE
13 years 1 months ago
A robust lip tracking algorithm using localized color active contours and deformable models
Lip tracking is crucial to the success of a lipreading recognition system. This paper presents a robust lip tracking algorithm using localized color active contours and deformable...
Xin Liu, Yiu-ming Cheung
CVPR
2008
IEEE
14 years 11 months ago
Multi-object shape estimation and tracking from silhouette cues
This paper deals with the 3D shape estimation from silhouette cues of multiple moving objects in general indoor or outdoor 3D scenes with potential static obstacles, using multipl...
Li Guan, Jean-Sébastien Franco, Marc Pollef...
TMI
2011
182views more  TMI 2011»
13 years 4 months ago
Active Volume Models for Medical Image Segmentation
—In this paper, we propose a novel predictive model, active volume model (AVM), for object boundary extraction. It is a dynamic “object” model whose manifestation includes a ...
Tian Shen, Hongsheng Li, Xiaolei Huang