Analyzing human interactions with a network of dynamic probabilistic models

Heung Il Suk; Bong Kee Sin; Seong Whan Lee

doi:10.1109/WACV.2009.5403108

Analyzing human interactions with a network of dynamic probabilistic models

Heung Il Suk^*
, Bong Kee Sin
, Seong Whan Lee

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

In this paper, we propose a novel method for analyzing human interactions based on the walking trajectories of human subjects. Our principal assumption is that an interaction episode is composed of meaningful smaller unit interactions, which we call 'sub-interactions.' The whole interaction is represented by an ordered concatenation or a network of sub-interaction models. From the experiments, we could confirm the effectiveness and robustness of the proposed method by analyzing the internal work of an interaction network and comparing the performance with other previous approaches.

Original language	English
Title of host publication	2009 Workshop on Applications of Computer Vision, WACV 2009
Publisher	IEEE Computer Society
ISBN (Print)	9781424454976
DOIs	https://doi.org/10.1109/WACV.2009.5403108
Publication status	Published - 2009
Event	2009 Workshop on Applications of Computer Vision, WACV 2009 - Snowbird, UT, United States Duration: 2009 Dec 7 → 2009 Dec 8

Publication series

Name	2009 Workshop on Applications of Computer Vision, WACV 2009

Other

Other	2009 Workshop on Applications of Computer Vision, WACV 2009
Country/Territory	United States
City	Snowbird, UT
Period	09/12/7 → 09/12/8

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition

Access to Document

10.1109/WACV.2009.5403108

Cite this

Analyzing human interactions with a network of dynamic probabilistic models. / Suk, Heung Il; Sin, Bong Kee; Lee, Seong Whan.
2009 Workshop on Applications of Computer Vision, WACV 2009. IEEE Computer Society, 2009. 5403108 (2009 Workshop on Applications of Computer Vision, WACV 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Suk, HI, Sin, BK & Lee, SW 2009, Analyzing human interactions with a network of dynamic probabilistic models. in 2009 Workshop on Applications of Computer Vision, WACV 2009., 5403108, 2009 Workshop on Applications of Computer Vision, WACV 2009, IEEE Computer Society, 2009 Workshop on Applications of Computer Vision, WACV 2009, Snowbird, UT, United States, 09/12/7. https://doi.org/10.1109/WACV.2009.5403108

@inproceedings{af512474a4b247ba99a67fd953987783,

title = "Analyzing human interactions with a network of dynamic probabilistic models",

abstract = "In this paper, we propose a novel method for analyzing human interactions based on the walking trajectories of human subjects. Our principal assumption is that an interaction episode is composed of meaningful smaller unit interactions, which we call 'sub-interactions.' The whole interaction is represented by an ordered concatenation or a network of sub-interaction models. From the experiments, we could confirm the effectiveness and robustness of the proposed method by analyzing the internal work of an interaction network and comparing the performance with other previous approaches.",

author = "Suk, \{Heung Il\} and Sin, \{Bong Kee\} and Lee, \{Seong Whan\}",

year = "2009",

doi = "10.1109/WACV.2009.5403108",

language = "English",

isbn = "9781424454976",

series = "2009 Workshop on Applications of Computer Vision, WACV 2009",

publisher = "IEEE Computer Society",

booktitle = "2009 Workshop on Applications of Computer Vision, WACV 2009",

note = "2009 Workshop on Applications of Computer Vision, WACV 2009 ; Conference date: 07-12-2009 Through 08-12-2009",

}

TY - GEN

T1 - Analyzing human interactions with a network of dynamic probabilistic models

AU - Suk, Heung Il

AU - Sin, Bong Kee

AU - Lee, Seong Whan

PY - 2009

Y1 - 2009

N2 - In this paper, we propose a novel method for analyzing human interactions based on the walking trajectories of human subjects. Our principal assumption is that an interaction episode is composed of meaningful smaller unit interactions, which we call 'sub-interactions.' The whole interaction is represented by an ordered concatenation or a network of sub-interaction models. From the experiments, we could confirm the effectiveness and robustness of the proposed method by analyzing the internal work of an interaction network and comparing the performance with other previous approaches.

AB - In this paper, we propose a novel method for analyzing human interactions based on the walking trajectories of human subjects. Our principal assumption is that an interaction episode is composed of meaningful smaller unit interactions, which we call 'sub-interactions.' The whole interaction is represented by an ordered concatenation or a network of sub-interaction models. From the experiments, we could confirm the effectiveness and robustness of the proposed method by analyzing the internal work of an interaction network and comparing the performance with other previous approaches.

UR - https://www.scopus.com/pages/publications/77951147635

U2 - 10.1109/WACV.2009.5403108

DO - 10.1109/WACV.2009.5403108

M3 - Conference contribution

AN - SCOPUS:77951147635

SN - 9781424454976

T3 - 2009 Workshop on Applications of Computer Vision, WACV 2009

BT - 2009 Workshop on Applications of Computer Vision, WACV 2009

PB - IEEE Computer Society

T2 - 2009 Workshop on Applications of Computer Vision, WACV 2009

Y2 - 7 December 2009 through 8 December 2009

ER -

Analyzing human interactions with a network of dynamic probabilistic models

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this