Sciweavers

3449 search results - page 395 / 690
» A Framework for Multiple-Instance Learning
Sort
View
SIGMOD
2009
ACM
177views Database» more  SIGMOD 2009»
16 years 5 months ago
Exploiting context analysis for combining multiple entity resolution systems
Entity Resolution (ER) is an important real world problem that has attracted significant research interest over the past few years. It deals with determining which object descript...
Zhaoqi Chen, Dmitri V. Kalashnikov, Sharad Mehrotr...
ECCV
2004
Springer
16 years 6 months ago
Recognition by Probabilistic Hypothesis Construction
We present a probabilistic framework for recognizing objects in images of cluttered scenes. Hundreds of objects may be considered and searched in parallel. Each object is learned f...
Pierre Moreels, Michael Maire, Pietro Perona
ICML
2008
IEEE
16 years 5 months ago
Random classification noise defeats all convex potential boosters
A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. This class...
Philip M. Long, Rocco A. Servedio
ICML
2005
IEEE
16 years 5 months ago
Q-learning of sequential attention for visual object recognition from informative local descriptors
This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects...
Lucas Paletta, Gerald Fritz, Christin Seifert
ICML
2005
IEEE
16 years 5 months ago
Coarticulation: an approach for generating concurrent plans in Markov decision processes
We study an approach for performing concurrent activities in Markov decision processes (MDPs) based on the coarticulation framework. We assume that the agent has multiple degrees ...
Khashayar Rohanimanesh, Sridhar Mahadevan