Sciweavers

213 search results - page 12 / 43
» Adaptable Model-Based Tracking Using Analysis-by-Synthesis T...
Sort
View
IBPRIA
2003
Springer
15 years 5 months ago
Probabilistic Observation Models for Tracking Based on Optical Flow
In this paper, we present two new observation models based on optical flow information to track objects using particle filter algorithms. Although optical flow information enabl...
Manuel J. Lucena, José M. Fuertes, Nicolas ...
ICPR
2004
IEEE
16 years 1 months ago
Robust Playfield Segmentation using MAP Adaptation
A vital task in sports video annotation is to detect and segment areas of the playfield. This is an important first step in player or ball tracking and detecting the location of t...
Jean-Marc Odobez, Mark Barnard
100
Voted
ISMDA
2005
Springer
15 years 6 months ago
Endocardial Tracking in Contrast Echocardiography Using Optical Flow
Myocardial Contrast Echocardiography (MCE) is a recent technique that allows to measure regional perfusion in the cardiac wall. Segmentation of MCE sequences would allow simultaneo...
Norberto Malpica, Juan Francisco Garamendi, Manuel...
98
Voted
TNN
2008
177views more  TNN 2008»
15 years 9 days ago
Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model
Previous work on statistical language modeling has shown that it is possible to train a feed-forward neural network to approximate probabilities over sequences of words, resulting...
Yoshua Bengio, Jean-Sébastien Senecal
CVPR
2003
IEEE
16 years 2 months ago
Mean-shift Blob Tracking through Scale Space
The mean-shift algorithm is an efficient technique for tracking 2D blobs through an image. Although the scale of the mean-shift kernel is a crucial parameter, there is presently n...
Robert T. Collins