662 search results - page 45 / 133 » Making inferences with small numbers of training sets |
127
click to vote
CVPR
2011
IEEE
14 years 8 months ago
2011
IEEE
In this paper we explore the idea of using high-level semantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the constr...
ECML
2001
Springer
15 years 4 months ago
2001
Springer
Labeled data for classification could often be obtained by sampling that restricts or favors choice of certain classes. A classifier trained using such data will be biased, resulti...
151
click to vote
CVPR
2012
IEEE
13 years 2 months ago
2012
IEEE
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a...
239
click to vote
ICCV
2011
IEEE
13 years 12 months ago
2011
IEEE
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
AUTOMATICA
2000
14 years 11 months ago
2000
: For a large class of bounded-error estimation problems, the posterior feasible set 5 for the parameters can be dened by nonlinear inequalities. The set-inversion approach combine...