Sciweavers

93 search results - page 18 / 19
» Trajectory Optimization using Reinforcement Learning for Map...
Sort
View
TCSV
2011
12 years 12 months ago
Integrating Spatio-Temporal Context With Multiview Representation for Object Recognition in Visual Surveillance
—We present in this paper an integrated solution to rapidly recognizing dynamic objects in surveillance videos by exploring various contextual information. This solution consists...
Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, We...
CIKM
2009
Springer
13 years 11 months ago
Adaptive relevance feedback in information retrieval
Relevance Feedback has proven very effective for improving retrieval accuracy. A difficult yet important problem in all relevance feedback methods is how to optimally balance the...
Yuanhua Lv, ChengXiang Zhai
NIPS
1998
13 years 6 months ago
Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...
Michael J. Kearns, Satinder P. Singh
AMR
2007
Springer
143views Multimedia» more  AMR 2007»
13 years 11 months ago
User Modelling for Interactive User-Adaptive Collection Structuring
Abstract. Automatic structuring is one means to ease access to document collections, be it for organization or for exploration. Of even greater help would be a presentation that ad...
Andreas Nürnberger, Sebastian Stober
MM
2005
ACM
169views Multimedia» more  MM 2005»
13 years 10 months ago
An ambient intelligence platform for physical play
This paper describes an ambient intelligent prototype known as socio-ec(h)o. socio-ec(h)o explores the design and implementation of a system for sensing and display, user modeling...
Ron Wakkary, Marek Hatala, Robb Lovell, Milena Dro...