Group interaction analysis in dynamic context

Peng Dai; Huijun Di; Ligeng Dong; Linmi Tao; Guangyou Xu

doi:10.1109/TSMCB.2007.909939

Group interaction analysis in dynamic context

Peng Dai^*, Huijun Di, Ligeng Dong, Linmi Tao, Guangyou Xu

^*Corresponding author for this work

Tsinghua University

Research output: Contribution to journal › Article › peer-review

43 Citations (Scopus)

Abstract

Computer understanding of human actions and interactions is one of the key research issues in human computing. In this regard, context plays an essential role in semantic understanding of human behavioral and social signals from sensor data. This paper put forward an event-based dynamic context model to address the problems of context awareness in the analysis of group interaction scenarios. Event-driven multilevel dynamic Bayesian network is correspondingly proposed to detect multilevel events, which underlies the context awareness mechanism. Online analysis can be achieved, which is superior over previous works. Experiments in our smart meeting room demonstrate the effectiveness of our approach.

Original language	English
Pages (from-to)	275-282
Number of pages	8
Journal	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume	38
Issue number	1
DOIs	https://doi.org/10.1109/TSMCB.2007.909939
Publication status	Published - Feb 2008
Externally published	Yes

Keywords

Dynamic Bayesian network (DBN)
Dynamic context model
Group interaction analysis
Meeting analysis

Access to Document

10.1109/TSMCB.2007.909939

Cite this

@article{2055ac45aa444fc4a27058c8f6800901,

title = "Group interaction analysis in dynamic context",

abstract = "Computer understanding of human actions and interactions is one of the key research issues in human computing. In this regard, context plays an essential role in semantic understanding of human behavioral and social signals from sensor data. This paper put forward an event-based dynamic context model to address the problems of context awareness in the analysis of group interaction scenarios. Event-driven multilevel dynamic Bayesian network is correspondingly proposed to detect multilevel events, which underlies the context awareness mechanism. Online analysis can be achieved, which is superior over previous works. Experiments in our smart meeting room demonstrate the effectiveness of our approach.",

keywords = "Dynamic Bayesian network (DBN), Dynamic context model, Group interaction analysis, Meeting analysis",

author = "Peng Dai and Huijun Di and Ligeng Dong and Linmi Tao and Guangyou Xu",

year = "2008",

month = feb,

doi = "10.1109/TSMCB.2007.909939",

language = "English",

volume = "38",

pages = "275--282",

journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",

issn = "1083-4419",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - Group interaction analysis in dynamic context

AU - Dai, Peng

AU - Di, Huijun

AU - Dong, Ligeng

AU - Tao, Linmi

AU - Xu, Guangyou

PY - 2008/2

Y1 - 2008/2

N2 - Computer understanding of human actions and interactions is one of the key research issues in human computing. In this regard, context plays an essential role in semantic understanding of human behavioral and social signals from sensor data. This paper put forward an event-based dynamic context model to address the problems of context awareness in the analysis of group interaction scenarios. Event-driven multilevel dynamic Bayesian network is correspondingly proposed to detect multilevel events, which underlies the context awareness mechanism. Online analysis can be achieved, which is superior over previous works. Experiments in our smart meeting room demonstrate the effectiveness of our approach.

AB - Computer understanding of human actions and interactions is one of the key research issues in human computing. In this regard, context plays an essential role in semantic understanding of human behavioral and social signals from sensor data. This paper put forward an event-based dynamic context model to address the problems of context awareness in the analysis of group interaction scenarios. Event-driven multilevel dynamic Bayesian network is correspondingly proposed to detect multilevel events, which underlies the context awareness mechanism. Online analysis can be achieved, which is superior over previous works. Experiments in our smart meeting room demonstrate the effectiveness of our approach.

KW - Dynamic Bayesian network (DBN)

KW - Dynamic context model

KW - Group interaction analysis

KW - Meeting analysis

UR - http://www.scopus.com/inward/record.url?scp=39649116026&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2007.909939

DO - 10.1109/TSMCB.2007.909939

M3 - Article

C2 - 18270099

AN - SCOPUS:39649116026

SN - 1083-4419

VL - 38

SP - 275

EP - 282

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

IS - 1

ER -

Group interaction analysis in dynamic context

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this