68 search results - page 10 / 14 » Recognition by Variance: Learning Rules for Spatiotemporal P... |
KDD
2005
ACM
14 years 8 months ago
2005
ACM
We describe an algorithm for converting linear support vector machines and any other arbitrary hyperplane-based linear classifiers into a set of non-overlapping rules that, unlike...
NIPS
1994
13 years 9 months ago
1994
Ideally pattern recognition machines provide constant output when the inputs are transformed under a group G of desired invariances. These invariances can be achieved by enhancing...
BICA
2010
13 years 2 months ago
2010
Deep-layer machine learning architectures continue to emerge as a promising biologically-inspired framework for achieving scalable perception in artificial agents. State inference ...
MM
2003
ACM
14 years 26 days ago
2003
ACM
In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represent...
ICCV
2009
IEEE
13 years 5 months ago
2009
IEEE
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...