825 search results - page 6 / 165 » Learning Parts-Based Representations of Data |
124
Voted
NIPS
2008
15 years 3 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...
107
click to vote
CVPR
2007
IEEE
16 years 3 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...
111
click to vote
ICML
2004
IEEE
16 years 2 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...
114
click to vote
ICML
2007
IEEE
16 years 2 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...
132
click to vote
ECAI
2008
Springer
15 years 3 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...