Sciweavers

1585 search results - page 52 / 317
» Using a Non-prior Training Active Feature Model
Sort
View
146
Voted
ICCV
2009
IEEE
16 years 9 months ago
Active Skeleton for Non-rigid Object Detection
We present a shape-based algorithm for detecting and recognizing non-rigid objects from natural images. The existing literature in this domain often cannot model the objects ver...
Xiang Bai, Xinggang Wang, Longin Jan Latecki, Weny...
ICIP
2008
IEEE
16 years 5 months ago
Activity-based temporal segmentation for videos of interacting objects using invariant trajectory features
This paper presents a content-based approach for temporal segmentation of videos. Tracked objects are characterized by their 2D trajectories which are used in a meaningful way to ...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
BMVC
2010
15 years 2 months ago
Additive Update Predictors in Active Appearance Models
The Active Appearance Model (AAM) provides an efficient method for localizing objects that vary in both shape and texture, and uses a linear regressor to predict updates to model ...
Philip A. Tresadern, Patrick Sauer, Timothy F. Coo...
FGR
2011
IEEE
271views Biometrics» more  FGR 2011»
14 years 7 months ago
Active conditional models
— Matching images with large geometric and iconic changes (e.g. faces under different poses and facial expressions) is an open research problem in computer vision. There are two ...
Ying Chen, Fernando De la Torre
ICIP
1999
IEEE
16 years 5 months ago
Perceptual Grouping of 3-D Features in Aerial Image Using Decision Tree Classifier
We address a new perceptual grouping algorithmfor aerial images, which employs a decision tree classifier and hierarchical multilevel grouping strategy an a bottom-up fashion. In ...
In Kyu Park, Kyoung Mu Lee, Sang Uk Lee