174 search results - page 20 / 35 » A Conditional Random Field for Multiple-Instance Learning |
CVPR
2008
IEEE
14 years 9 months ago
2008
IEEE
The notion of using context information for solving highlevel vision problems has been increasingly realized in the field. However, how to learn an effective and efficient context...
ICPR
2010
IEEE
13 years 11 months ago
2010
IEEE
Conditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by exte...
TIST
2011
13 years 2 months ago
2011
Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogue...
ICCV
2007
IEEE
14 years 9 months ago
2007
IEEE
Convolutional networks have achieved a great deal of success in high-level vision problems such as object recognition. Here we show that they can also be used as a general method ...
ICML
2004
IEEE
14 years 1 months ago
2004
IEEE
We introduce a new perceptron-based discriminative learning algorithm for labeling structured data such as sequences, trees, and graphs. Since it is fully kernelized and uses poin...