Sciweavers

1351 search results - page 20 / 271
» Learning from compressed observations
Sort
View
ICRA
2009
IEEE
179views Robotics» more  ICRA 2009»
14 years 2 months ago
Automatic weight learning for multiple data sources when learning from demonstration
— Traditional approaches to programming robots are generally inaccessible to non-robotics-experts. A promising exception is the Learning from Demonstration paradigm. Here a polic...
Brenna Argall, Brett Browning, Manuela M. Veloso
ECCV
2010
Springer
14 years 18 days ago
Compressive Acquisition of Dynamic Scenes
Abstract. Compressive sensing (CS) is a new approach for the acquisition and recovery of sparse signals and images that enables sampling rates significantly below the classical Ny...
CORR
2008
Springer
72views Education» more  CORR 2008»
13 years 7 months ago
Lossless Compression with Security Constraints
Secure distributed data compression in the presence of an eavesdropper is explored. Two correlated sources that need to be reliably transmitted to a legitimate receiver are availab...
Deniz Gündüz, Elza Erkip, H. Vincent Poo...
CVPR
2009
IEEE
15 years 2 months ago
Co-training with Noisy Perceptual Observations
Many perception and multimedia indexing problems involve datasets that are naturally comprised of multiple streams or modalities for which supervised training data is only sparsely...
Ashish Kapoor, Chris Mario Christoudias, Raquel Ur...
ICRA
2002
IEEE
128views Robotics» more  ICRA 2002»
14 years 10 days ago
Generation of a Task Model by Integrating Multiple Observations of Human Demonstrations
This paper describes a new approach on how to teach a robot everyday manipulation tasks under the “Learning from Observation” framework. Most of the approaches so far assume t...
Koichi Ogawara, Jun Takamatsu, Hiroshi Kimura, Kat...