Sciweavers

85 search results - page 1 / 17
» Finding and Tracking People from the Bottom Up
Sort
View
CVPR
2003
IEEE
14 years 7 months ago
Finding and Tracking People from the Bottom Up
We describe a tracker that can track moving people in long sequences without manual initialization. Moving people are modeled with the assumption that, while configuration can var...
Deva Ramanan, David A. Forsyth
ICCV
1999
IEEE
14 years 6 months ago
Finding People by Sampling
We show how to use a sampling method to find sparsely clad people in static images. People are modeled as an assembly of nine cylindrical segments. Segments are found using an EM ...
Sergey Ioffe, David A. Forsyth
AUSDM
2007
Springer
131views Data Mining» more  AUSDM 2007»
13 years 11 months ago
A Bottom-Up Projection Based Algorithm for Mining High Utility Itemsets
Mining High Utility Itemsets from a transaction database is to find itemsests that have utility above a user-specified threshold. This problem is an extension of Frequent Itemset ...
Alva Erwin, Raj P. Gopalan, N. R. Achuthan
CADE
2006
Springer
14 years 5 months ago
Blocking and Other Enhancements for Bottom-Up Model Generation Methods
In this paper we introduce several new improvements to the bottom-up model generation (BUMG) paradigm. Our techniques are based on non-trivial transformations of first-order probl...
Peter Baumgartner, Renate A. Schmidt
CVPR
2006
IEEE
14 years 7 months ago
Robust People Tracking with Global Trajectory Optimization
Given three or four synchronized videos taken at eye level and from different angles, we show that we can effectively use dynamic programming to accurately follow up to six indivi...
François Fleuret, Jérôme Bercl...