3716 search results - page 196 / 744 » On the monotonization of the training set |
228
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
Simply choosing one model out of a large set of possibilities for a given vision task is a surprisingly difficult problem, especially if there is limited evaluation data with whi...
160
click to vote
PODS
2002
ACM
16 years 6 months ago
2002
ACM
We study two classes of view update problems in relational databases. We are given a source database S, a monotone query Q, and the view Q(S) generated by the query. The first pro...
168
click to vote
IJCAI
1993
15 years 7 months ago
1993
We introduce and use a new methodology for the study of logics for action and change. The methodology allows one to define a taxonomy of reasoning problems, based in particular on...
187
click to vote
ICCV
2009
IEEE
16 years 11 months ago
2009
IEEE
Image auto-annotation is an important open problem in
computer vision. For this task we propose TagProp, a discriminatively
trained nearest neighbor model. Tags of test
images a...
179
click to vote
CVPR
2000
IEEE
16 years 8 months ago
2000
IEEE
We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Ou...