Sciweavers

17 search results - page 1 / 4
» Learning and Matching Line Aspects for Articulated Objects
Sort
View
CVPR
2007
IEEE
14 years 7 months ago
Learning and Matching Line Aspects for Articulated Objects
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...
Xiaofeng Ren
ECCV
2004
Springer
14 years 6 months ago
Tracking Aspects of the Foreground against the Background
In object tracking, change of object aspect is a cause of failure due to significant changes of object appearances. The paper proposes an approach to this problem without a priori ...
Hieu Tat Nguyen, Arnold W. M. Smeulders
CLOR
2006
13 years 8 months ago
Sequential Learning of Layered Models from Video
Abstract. A popular framework for the interpretation of image sequences is the layers or sprite model, see e.g. [1], [2]. Jojic and Frey [3] provide a generative probabilistic mode...
Michalis K. Titsias, Christopher K. I. Williams
DAGM
2006
Springer
13 years 8 months ago
On-Line, Incremental Learning of a Robust Active Shape Model
Abstract. Active Shape Models are commonly used to recognize and locate different aspects of known rigid objects. However, they require an off-line learning stage, such that the ex...
Michael Fussenegger, Peter M. Roth, Horst Bischof,...
CVPR
2009
IEEE
15 years 2 days ago
Layered Graph Matching by Composite Cluster Sampling with Collaborative and Competitive Interactions
This paper studies a framework for matching an unknown number of corresponding structures in two images (shapes), motivated by detecting objects in cluttered background and lear...
Kun Zeng, Liang Lin, Song Chun Zhu, Xiaobai Liu