Sciweavers

472 search results - page 83 / 95
» On the Entropy of a Hidden Markov Process
Sort
View
CVPR
2010
IEEE
14 years 4 months ago
What's going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes
We present two novel methods to automatically learn spatio-temporal dependencies of moving agents in complex dynamic scenes. They allow to discover temporal rules, such as the rig...
Daniel Kuettel, Michael Breitenstein, Luc Van Gool...
WEBDB
2009
Springer
124views Database» more  WEBDB 2009»
14 years 3 months ago
Bridging the Terminology Gap in Web Archive Search
Web archives play an important role in preserving our cultural heritage for future generations. When searching them, a serious problem arises from the fact that terminology evolve...
Klaus Berberich, Srikanta J. Bedathur, Mauro Sozio...
CIARP
2009
Springer
14 years 3 months ago
Learning Relational Grammars from Sequences of Actions
Many tasks can be described by sequences of actions that normally exhibit some form of structure and that can be represented by a grammar. This paper introduces FOSeq, an algorithm...
Blanca Vargas-Govea, Eduardo F. Morales
ISM
2008
IEEE
136views Multimedia» more  ISM 2008»
14 years 2 months ago
Multimodal Speaker Segmentation in Presence of Overlapped Speech Segments
We propose a multimodal speaker segmentation algorithm with two main contributions: First, we suggest a hidden Markov model architecture that performs fusion of the three modaliti...
Viktor Rozgic, Kyu Jeong Han, Panayiotis G. Georgi...
FOCI
2007
IEEE
14 years 2 months ago
Almost All Learning Machines are Singular
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Sumio Watanabe