Sciweavers

717 search results - page 40 / 144
» Multiple target detection using Bayesian learning
Sort
View
SEMWEB
2005
Springer
14 years 3 months ago
A Bayesian Network Approach to Ontology Mapping
This paper presents our ongoing effort on developing a principled methodology for automatic ontology mapping based on BayesOWL, a probabilistic framework we developed for modeling ...
Rong Pan, Zhongli Ding, Yang Yu, Yun Peng
ICRA
2010
IEEE
101views Robotics» more  ICRA 2010»
13 years 8 months ago
Searching for objects: Combining multiple cues to object locations using a maximum entropy model
— In this paper, we consider the problem of how background knowledge about usual object arrangements can be utilized by a mobile robot to more efficiently find an object in an ...
Dominik Joho, Wolfram Burgard
ACCV
2007
Springer
14 years 4 months ago
Combined Object Detection and Segmentation by Using Space-Time Patches
This paper presents a method for classifying the direction of movement and for segmenting objects simultaneously using features of space-time patches. Our approach uses vector quan...
Yasuhiro Murai, Hironobu Fujiyoshi, Takeo Kanade
CLEAR
2006
Springer
133views Biometrics» more  CLEAR 2006»
14 years 1 months ago
Multi-feature Graph-Based Object Tracking
We present an object detection and tracking algorithm that addresses the problem of multiple simultaneous targets tracking in realworld surveillance scenarios. The algorithm is bas...
Murtaza Taj, Emilio Maggio, Andrea Cavallaro
ICIP
2003
IEEE
14 years 3 months ago
Image classification using multimedia knowledge networks
This paper presents novel methods for classifying images based on knowledge discovered from annotated images using WordNet. The novelty of this work is the automatic class discove...
Ana B. Benitez, Shih-Fu Chang