Sciweavers

48 search results - page 2 / 10
» Predicting future object states using learned affordances
Sort
View
GIS
2007
ACM
13 years 11 months ago
Predicting future locations using clusters' centroids
As technology advances we encounter more available data on moving objects, thus increasing our ability to mine spatiotemporal data. We can use this data for learning moving object...
Sigal Elnekave, Mark Last, Oded Maimon
TIP
2008
86views more  TIP 2008»
13 years 4 months ago
Learning the Dynamics and Time-Recursive Boundary Detection of Deformable Objects
We propose a principled framework for recursively segmenting deformable objects across a sequence of frames. We demonstrate the usefulness of this method on left ventricular segmen...
Walter Sun, Müjdat Çetin, Raymond C. C...
ICML
2009
IEEE
14 years 5 months ago
Proto-predictive representation of states with simple recurrent temporal-difference networks
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
Takaki Makino
ATAL
2008
Springer
13 years 6 months ago
Approximate predictive state representations
Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses ...
Britton Wolfe, Michael R. James, Satinder P. Singh
IVC
2000
104views more  IVC 2000»
13 years 4 months ago
Learning spatio-temporal patterns for predicting object behaviour
Rule-based systems employed to model complex object behaviours, do not necessarily provide a realistic portrayal of true behaviour. To capture the real characteristics in a specif...
Neil Sumpter, Andrew J. Bulpitt