Sciweavers

2300 search results - page 86 / 460
» Learning Dialogue POMDP Models from Data
Sort
View
NPL
2006
85views more  NPL 2006»
15 years 3 months ago
A Neural Model for Context-dependent Sequence Learning
A novel neural network model is described that implements context-dependent learning of complex sequences. The model utilises leaky integrate-and-fire neurons to extract timing inf...
Luc Berthouze, Adriaan G. Tijsseling
NECO
2007
152views more  NECO 2007»
15 years 3 months ago
3D Periodic Human Motion Reconstruction from 2D Motion Sequences
In this report, we present and evaluate a method of reconstructing three-dimensional (3D) periodic human motion from two-dimensional (2D) motion sequences. Based on a Fourier deco...
Zonghua Zhang, Nikolaus F. Troje
WEBI
2010
Springer
15 years 1 months ago
Relations Expansion: Extracting Relationship Instances from the Web
In this paper, we propose a Relation Expansion framework, which uses a few seed sentences marked up with two entities to expand a set of sentences containing target relations. Duri...
Haibo Li, Yutaka Matsuo, Mitsuru Ishizuka
IJRR
2007
186views more  IJRR 2007»
15 years 3 months ago
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields
Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract a person’s activities and significant plac...
Lin Liao, Dieter Fox, Henry A. Kautz
HUMO
2000
Springer
15 years 7 months ago
Realistic Synthesis of Novel Human Movements from a Database of Motion Capture Examples
In this paper we present a system that can synthesise novel motion sequences from a database of motion capture examples. This is achieved through learning a statistical model from...
L. M. Tanco, Adrian Hilton