Sciweavers

110 search results - page 13 / 22
» Coupled hidden Markov models for complex action recognition
Sort
View
INTERSPEECH
2010
13 years 2 months ago
Deep-structured hidden conditional random fields for phonetic recognition
We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
Dong Yu, Li Deng
ICIP
2006
IEEE
14 years 1 months ago
Modelization of Limb Coordination for Human Action Analysis
This paper analyzes the movements of the human body limbs (hands, feet and head) and center of gravity in order to detect simple actions such as walking, jumping and displacing an...
Kosta Gaitanis, Pedro Correa, Benoit M. Macq
CVPR
1999
IEEE
14 years 9 months ago
Time-Series Classification Using Mixed-State Dynamic Bayesian Networks
We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of di...
Vladimir Pavlovic, Brendan J. Frey, Thomas S. Huan...
ICMCS
2005
IEEE
183views Multimedia» more  ICMCS 2005»
14 years 1 months ago
Sports Event Recognition Using Layered HMMS
The recognition of events in video data is a subject of much current interest. In this paper, we address several issues related to this topic. The first one is overfitting when ...
Mark Barnard, Jean-Marc Odobez
ATAL
2006
Springer
13 years 11 months ago
Learning executable agent behaviors from observation
We present a method for learning a human understandable, executable model of an agent's behavior using observations of its interaction with the environment. By executable we ...
Andrew Guillory, Hai Nguyen, Tucker R. Balch, Char...