518 search results - page 4 / 104 » Object correspondence as a machine learning problem |
ICML
2007
IEEE
16 years 12 days ago
2007
IEEE
We study the problem of learning kernel machines transductively for structured output variables. Transductive learning can be reduced to combinatorial optimization problems over a...
108
click to vote
JMLR
2010
14 years 10 months ago
2010
We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by ge...
ICIP
2006
IEEE
16 years 1 months ago
2006
IEEE
In this paper we present a new scheme for detection and tracking of specific objects in a knowledge-based framework. The scheme uses a supervised learning method: Support Vector M...
101
click to vote
HIS
2007
15 years 1 months ago
2007
—Machine learning is inherently a multiobjective task. Traditionally, however, either only one of the objectives is adopted as the cost function or multiple objectives are aggreg...
ICML
2008
IEEE
16 years 12 days ago
2008
IEEE
Semi-supervised learning aims at taking advantage of unlabeled data to improve the efficiency of supervised learning procedures. For discriminative models however, this is a chall...