Sciweavers

100 search results - page 12 / 20
» Structure From Motion Using Sequential Monte Carlo Methods
Sort
View
UAI
1996
13 years 8 months ago
Bayesian Learning of Loglinear Models for Neural Connectivity
This paper presents a Bayesian approach to learning the connectivity structure of a group of neurons from data on configuration frequencies. A major objective of the research is t...
Kathryn B. Laskey, Laura Martignon
CVPR
2004
IEEE
13 years 11 months ago
Modeling Complex Motion by Tracking and Editing Hidden Markov Graphs
In this paper, we propose a generative model for representing complex motion, such as wavy river, dancing fire and dangling cloth. Our generative method consists of four component...
Yizhou Wang, Song Chun Zhu
ICCV
2005
IEEE
14 years 9 months ago
Probabilistic Contour Extraction Using Hierarchical Shape Representation
In this paper, we address the issue of extracting contour of the object with a specific shape. A hierarchical graphical model is proposed to represent shape variations. A complex ...
Xin Fan, Chun Qi, Dequn Liang, Hua Huang
ECCV
2008
Springer
14 years 9 months ago
Extracting Moving People from Internet Videos
Abstract. We propose a fully automatic framework to detect and extract arbitrary human motion volumes from real-world videos collected from YouTube. Our system is composed of two s...
Juan Carlos Niebles, Bohyung Han, Andras Ferencz, ...
ICCV
2007
IEEE
14 years 9 months ago
Learning Multiscale Representations of Natural Scenes Using Dirichlet Processes
We develop nonparametric Bayesian models for multiscale representations of images depicting natural scene categories. Individual features or wavelet coefficients are marginally de...
Jyri J. Kivinen, Erik B. Sudderth, Michael I. Jord...