825 search results - page 6 / 165 » Learning Parts-Based Representations of Data |
NIPS
2008
14 years 11 months ago
2008
In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. These representa...
CVPR
2007
IEEE
15 years 11 months ago
2007
IEEE
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
ICML
2004
IEEE
15 years 10 months ago
2004
IEEE
Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
ICML
2007
IEEE
15 years 10 months ago
2007
IEEE
The k-Nearest Neighbors algorithm can be easily adapted to classify complex objects (e.g. sets, graphs) as long as a proper dissimilarity function is given over an input space. Bo...
ECAI
2008
Springer
14 years 11 months ago
2008
Springer
Abstract. We propose a framework that learns functional objectes from spatio-temporal data sets such as those abstracted from video. The data is represented as one activity graph t...