3449 search results - page 320 / 690 » A Framework for Multiple-Instance Learning |
161
click to vote
JMLR
2010
14 years 11 months ago
2010
Probabilistic grammars offer great flexibility in modeling discrete sequential data like natural language text. Their symbolic component is amenable to inspection by humans, while...
160
click to vote
JMLR
2010
14 years 11 months ago
2010
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
151
click to vote
ACCV
2010
Springer
14 years 11 months ago
2010
Springer
Abstract. We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We tre...
159
click to vote
CVPR
2011
IEEE
14 years 8 months ago
2011
IEEE
Object segmentation needs to be driven by top-down knowledge to produce semantically meaningful results. In this paper, we propose a supervised segmentation approach that tightly ...
224
Voted
ICWE
2011
Springer
14 years 8 months ago
2011
Springer
In this paper, we investigate whether semantic relationships between entities can be learnt from analyzing microblog posts published on Twitter. We identify semantic links between ...