Sciweavers

441 search results - page 36 / 89
» Learning Patterns of Activity Using Real-Time Tracking
Sort
View
ICRA
2009
IEEE
132views Robotics» more  ICRA 2009»
14 years 2 months ago
Smoothed Sarsa: Reinforcement learning for robot delivery tasks
— Our goal in this work is to make high level decisions for mobile robots. In particular, given a queue of prioritized object delivery tasks, we wish to find a sequence of actio...
Deepak Ramachandran, Rakesh Gupta
TIP
2010
155views more  TIP 2010»
13 years 6 months ago
Laplacian Regularized D-Optimal Design for Active Learning and Its Application to Image Retrieval
—In increasingly many cases of interest in computer vision and pattern recognition, one is often confronted with the situation where data size is very large. Usually, the labels ...
Xiaofei He
RAS
2000
161views more  RAS 2000»
13 years 7 months ago
Active object recognition by view integration and reinforcement learning
A mobile agent with the task to classify its sensor pattern has to cope with ambiguous information. Active recognition of three-dimensional objects involves the observer in a sear...
Lucas Paletta, Axel Pinz
NN
2007
Springer
106views Neural Networks» more  NN 2007»
13 years 7 months ago
Machine learning approach to color constancy
A number of machine learning (ML) techniques have recently been proposed to solve color constancy problem in computer vision. Neural networks (NNs) and support vector regression (...
Vivek Agarwal, Andrei V. Gribok, Mongi A. Abidi
WACV
2002
IEEE
14 years 18 days ago
Activity maps for location-aware computing
Location-based context is important for many applications. Previous systems offered only coarse room-level features or used manually specified room regions to determine fine-sca...
David Demirdjian, Konrad Tollmar, Kimberle Koile, ...