15 search results - page 2 / 3 » Excentric Labeling: Dynamic Neighborhood Labeling for Data V... |
ICANN
2010
Springer
13 years 6 months ago
2010
Springer
Abstract. We investigate the extent to which eye movements in natural dynamic scenes can be predicted with a simple model of bottom-up saliency, which learns on different visual re...
DEXAW
2010
IEEE
13 years 6 months ago
2010
IEEE
Automatic generation of taxonomies can be useful for a wide area of applications. In our application scenario a topical hierarchy should be constructed reasonably fast from a large...
TMM
2010
12 years 12 months ago
2010
Communication between humans deeply relies on the capability of expressing and recognizing feelings. For this reason, research on human-machine interaction needs to focus on the re...
ICPR
2002
IEEE
14 years 6 months ago
2002
IEEE
Bayesian networks are an attractive modeling tool for human sensing, as they combine an intuitive graphical representation with ef?cient algorithms for inference and learning. Ear...
ECCV
2010
Springer
13 years 5 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 ...