3318 search results - page 330 / 664 » The Weak Instance Model |
122
click to vote
ACL
2009
15 years 2 months ago
2009
It is usually assumed that the kind of noise existing in annotated data is random classification noise. Yet there is evidence that differences between annotators are not always ra...
174
click to vote
CVPR
2011
IEEE
15 years 12 days ago
2011
IEEE
We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
176
Voted
ACCV
2010
Springer
15 years 17 hour ago
2010
Springer
In this paper, we present an efficient algorithm for 3D object recognition in presence of clutter and occlusions in noisy, sparse and unsegmented range data. The method uses a robu...
194
click to vote
JMLR
2012
13 years 7 months ago
2012
A challenging problem of multi-label learning is that both the label space and the model complexity will grow rapidly with the increase in the number of labels, and thus makes the...
223
click to vote
CVPR
2009
IEEE
17 years 6 days ago
2009
IEEE
Given an image, we propose a hierarchical generative
model that classifies the overall scene, recognizes and segments
each object component, as well as annotates the image
with ...