304 search results - page 22 / 61 » Computational Experience with the Batch Means Method |
173
click to vote
ECCV
2010
Springer
15 years 6 months ago
2010
Springer
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
155
click to vote
ICPR
2004
IEEE
16 years 7 months ago
2004
IEEE
This paper addresses the problem of rigid motion estimation and 3D reconstruction in vision systems where it is possible to recover the incident direction from image points. Such ...
158
click to vote
EDOC
2000
IEEE
15 years 10 months ago
2000
IEEE
Practical experience indicates that the definition of realworld workflow applications is a complex and error-prone process. Existing workflow management systems provide the means,...
168
click to vote
ACL
2009
15 years 3 months ago
2009
We consider the problem of learning context-dependent mappings from sentences to logical form. The training examples are sequences of sentences annotated with lambda-calculus mean...
171
click to vote
TMM
2011
15 years 28 days ago
2011
—Visual categorization is important to manage large collections of digital images and video, where textual metadata is often incomplete or simply unavailable. The bag-of-words mo...