2566 search results - page 220 / 514 » Relating reinforcement learning performance to classificatio... |
193
click to vote
CVPR
1999
IEEE
16 years 8 months ago
1999
IEEE
We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of di...
153
Voted
ACCV
2009
Springer
16 years 1 months ago
2009
Springer
In this paper a framework “Temporal-Vector Trajectory Learning” (TVTL) for human action recognition is proposed. In this framework, the major concept is that we would like to a...
148
click to vote
PAMI
2008
15 years 6 months ago
2008
We address the issue of classifying complex data. We focus on three main sources of complexity, namely, the high dimensionality of the observed data, the dependencies between these...
185
click to vote
TOMCCAP
2010
15 years 1 months ago
2010
We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at semantic concept detection. We propose to extract a novel representation, the Sh...
136
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
This paper introduces a novel regularization strategy to address the generalization issues for large-margin classifiers from the Empirical Risk Minimization (ERM) perspective. Fi...