6113 search results - page 393 / 1223 » Learning Features for Tracking |
272
click to vote
Book
"Reinforcement learning is learning what to do how to map situations to actions so as to maximize a numerical reward signal. The learner is not told which actions to take, as ...
157
click to vote
ICANN
2009
Springer
16 years 1 months ago
2009
Springer
The best recent supervised sequence learning methods use gradient descent to train networks of miniature nets called memory cells. The most popular cell structure seems somewhat ar...
198
click to vote
ICCV
1995
IEEE
15 years 10 months ago
1995
IEEE
A new technique is presented for computing 3D scene structure from point and line features in monocular image sequences. Unlike previous methods, the technique guarantees the comp...
215
click to vote
CVPR
1998
IEEE
16 years 8 months ago
1998
IEEE
We describe a vision system that monitors activity in a site over extended periods of time. The system uses a distributed set of sensors to cover the site, and an adaptive tracker...
218
click to vote
SDM
2011
SIAM
14 years 9 months ago
2011
SIAM
Multi-instance (MI) learning is a variant of supervised learning where labeled examples consist of bags (i.e. multi-sets) of feature vectors instead of just a single feature vecto...