Incorporating uncertainty in a layered HMM architecture for human activity recognition

Authors:
Michael Glodek;Lutz Bigalke;Martin Schels;Friedhelm Schwenker
Affiliations:
University of Ulm, Ulm, Germany;University of Ulm, Ulm, Germany;University of Ulm, Ulm, Germany;University of Ulm, Ulm, Germany
Venue:
J-HGBU '11 Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding
Year:
2011

Citing 1
Cited 5

Layered Representations for Human Activity Recognition

ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces

Joint ACM workshop on human gesture and behavior understanding: (J-HGBU'11)

MM '11 Proceedings of the 19th ACM international conference on Multimedia
Detecting actions by integrating sequential symbolic and sub-symbolic information in human activity recognition

MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
Multiple classifier combination using reject options and markov fusion networks

Proceedings of the 14th ACM international conference on Multimodal interaction
Recognizing human activities using a layered markov architecture

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Spectral graph features for the classification of graphs and graph sequences

Computational Statistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, conditioned HMM (CHMM), which inherit the structure from the latent-dynamic conditional random field(LDCRF) proposed by Morency et al. but is also based on a Bayesian network [1, 2]. Within the model a sequence of class labels is influencing a Markov chain of hidden states which are able to emit observations. The structure allows that several classes make use of the same hidden state.