238 search results - page 29 / 48 » Learning for Optical Flow Using Stochastic Optimization |
ICPR
2000
IEEE
14 years 1 months ago
2000
IEEE
Traditional techniques for tracking non-rigid objects such as optical flow, correlation, active contours or color, can not deal with situations where image changes are not due to ...
FOCI
2007
IEEE
14 years 4 months ago
2007
IEEE
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
ICML
2010
IEEE
13 years 11 months ago
2010
IEEE
Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation...
TVLSI
2008
13 years 10 months ago
2008
Abstract--Technology scaling in the nanometer era has increased the transistor's susceptibility to process variations. The effects of such variations are having a huge impact ...
JMLR
2010
13 years 4 months ago
2010
Composite likelihood methods provide a wide spectrum of computationally efficient techniques for statistical tasks such as parameter estimation and model selection. In this paper,...