171 search results - page 16 / 35 » A Boosting Approach to Multiple Instance Learning |
CVPR
2011
IEEE
13 years 4 months ago
2011
IEEE
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
JMLR
2012
11 years 10 months ago
2012
We consider the task of devising large-margin based surrogate losses for the learning to rank problem. In this learning to rank setting, the traditional hinge loss for structured ...
ECCV
2004
Springer
14 years 9 months ago
2004
Springer
The problem of tracking a varying number of non-rigid objects has two major difficulties. First, the observation models and target distributions can be highly non-linear and non-Ga...
ICML
2009
IEEE
13 years 5 months ago
2009
IEEE
We address the problem of learning classifiers using several kernel functions. On the contrary to many contributions in the field of learning from different sources of information...
TNN
2008
13 years 7 months ago
2008
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...