Sciweavers

1927 search results - page 79 / 386
» Modeling the Evolution of Objects in Temporal Information Sy...
Sort
View
TNN
2008
132views more  TNN 2008»
13 years 7 months ago
Just-in-Time Adaptive Classifiers - Part I: Detecting Nonstationary Changes
Abstract--The stationarity requirement for the process generating the data is a common assumption in classifiers' design. When such hypothesis does not hold, e.g., in applicat...
Cesare Alippi, Manuel Roveri
CVPR
2007
IEEE
14 years 2 months ago
Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Association
We propose a framework for general multiple target tracking, where the input is a set of candidate regions in each frame, as obtained from a state of the art background learning, ...
Qian Yu, Gérard G. Medioni, Isaac Cohen
COSIT
1997
Springer
115views GIS» more  COSIT 1997»
13 years 12 months ago
Qualitative Representation of Change
Current geographic information systems (GISs) have been designed for querying and maintaining static databases representing static phenomena and give little support to those users ...
Kathleen Hornsby, Max J. Egenhofer
CONNECTION
2004
98views more  CONNECTION 2004»
13 years 7 months ago
Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting
While humans forget gradually, highly distributed connectionist networks forget catastrophically: newly learned information often completely erases previously learned information. ...
Bernard Ans, Stephane Rousset, Robert M. French, S...
SIGIR
2009
ACM
14 years 2 months ago
Temporal collaborative filtering with adaptive neighbourhoods
Recommender Systems, based on collaborative filtering (CF), aim to accurately predict user tastes, by minimising the mean error achieved on hidden test sets of user ratings, afte...
Neal Lathia, Stephen Hailes, Licia Capra