Sciweavers

1601 search results - page 105 / 321
» Learning Gaussian processes from multiple tasks
Sort
View
160
Voted
CEAS
2004
Springer
15 years 9 months ago
Extracting social networks and contact information from email and the Web
We present an end-to-end system that extracts a user’s social network and its members’ contact information given the user’s email inbox. The system identifies unique people...
Aron Culotta, Ron Bekkerman, Andrew McCallum
VMV
2001
178views Visualization» more  VMV 2001»
15 years 4 months ago
Consistent Visual Information Processing Applied to Object Recognition Landmark Definition and Real-Time Tracking
The handling of situations where multiple visual information occurs requires the fusion of visual information. This is a very common task found in the processing of multisource / ...
Axel Pinz
ATAL
2008
Springer
15 years 5 months ago
Teaching multi-robot coordination using demonstration of communication and state sharing
Solutions to complex tasks often require the cooperation of multiple robots, however, developing multi-robot policies can present many challenges. In this work, we introduce teach...
Sonia Chernova, Manuela M. Veloso
ECCV
2002
Springer
16 years 5 months ago
Nonlinear Shape Statistics in Mumford-Shah Based Segmentation
We present a variational integration of nonlinear shape statistics into a Mumford?Shah based segmentation process. The nonlinear statistics are derived from a set of training silho...
Christoph Schnörr, Daniel Cremers, Timo Kohlb...
158
Voted
RSS
2007
176views Robotics» more  RSS 2007»
15 years 5 months ago
Active Policy Learning for Robot Planning and Exploration under Uncertainty
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...