A neural-field-like approach for modeling human group actions in meetings

Stephan Reiter; Gerhard Rigoll

doi:10.1109/ICME.2005.1521354

A neural-field-like approach for modeling human group actions in meetings

Stephan Reiter, Gerhard Rigoll

Chair of Human-Machine Communication

Technical University of Munich

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

1 Scopus citations

Abstract

In this paper we investigate a new architecture for recognizing human group actions in meetings. These group actions provide a basis that enables effective browsing and querying in a meeting archive. For this task we propose an architecture that was inspired by the neural field theory. Our approach is particular, because contrary to other methods, we present all features to our classifier in parallel. The experiments show, that our system has comparable results to existing sequential techniques.

Original language	English
Title of host publication	IEEE International Conference on Multimedia and Expo, ICME 2005
Pages	37-40
Number of pages	4
DOIs	https://doi.org/10.1109/ICME.2005.1521354
State	Published - 2005
Event	IEEE International Conference on Multimedia and Expo, ICME 2005 - Amsterdam, Netherlands Duration: 6 Jul 2005 → 8 Jul 2005

Publication series

Name	IEEE International Conference on Multimedia and Expo, ICME 2005
Volume	2005

Conference

Conference	IEEE International Conference on Multimedia and Expo, ICME 2005
Country/Territory	Netherlands
City	Amsterdam
Period	6/07/05 → 8/07/05

Access to Document

10.1109/ICME.2005.1521354

Cite this

@inproceedings{78b4f190448945278ff6bba1c93e6086,

title = "A neural-field-like approach for modeling human group actions in meetings",

abstract = "In this paper we investigate a new architecture for recognizing human group actions in meetings. These group actions provide a basis that enables effective browsing and querying in a meeting archive. For this task we propose an architecture that was inspired by the neural field theory. Our approach is particular, because contrary to other methods, we present all features to our classifier in parallel. The experiments show, that our system has comparable results to existing sequential techniques.",

author = "Stephan Reiter and Gerhard Rigoll",

year = "2005",

doi = "10.1109/ICME.2005.1521354",

language = "English",

isbn = "0780393325",

series = "IEEE International Conference on Multimedia and Expo, ICME 2005",

pages = "37--40",

booktitle = "IEEE International Conference on Multimedia and Expo, ICME 2005",

note = "IEEE International Conference on Multimedia and Expo, ICME 2005 ; Conference date: 06-07-2005 Through 08-07-2005",

}

Reiter, S & Rigoll, G 2005, A neural-field-like approach for modeling human group actions in meetings. in IEEE International Conference on Multimedia and Expo, ICME 2005., 1521354, IEEE International Conference on Multimedia and Expo, ICME 2005, vol. 2005, pp. 37-40, IEEE International Conference on Multimedia and Expo, ICME 2005, Amsterdam, Netherlands, 6/07/05. https://doi.org/10.1109/ICME.2005.1521354

A neural-field-like approach for modeling human group actions in meetings. / Reiter, Stephan; Rigoll, Gerhard.
IEEE International Conference on Multimedia and Expo, ICME 2005. 2005. p. 37-40 1521354 (IEEE International Conference on Multimedia and Expo, ICME 2005; Vol. 2005).

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

TY - GEN

T1 - A neural-field-like approach for modeling human group actions in meetings

AU - Reiter, Stephan

AU - Rigoll, Gerhard

PY - 2005

Y1 - 2005

N2 - In this paper we investigate a new architecture for recognizing human group actions in meetings. These group actions provide a basis that enables effective browsing and querying in a meeting archive. For this task we propose an architecture that was inspired by the neural field theory. Our approach is particular, because contrary to other methods, we present all features to our classifier in parallel. The experiments show, that our system has comparable results to existing sequential techniques.

AB - In this paper we investigate a new architecture for recognizing human group actions in meetings. These group actions provide a basis that enables effective browsing and querying in a meeting archive. For this task we propose an architecture that was inspired by the neural field theory. Our approach is particular, because contrary to other methods, we present all features to our classifier in parallel. The experiments show, that our system has comparable results to existing sequential techniques.

UR - http://www.scopus.com/inward/record.url?scp=33750538650&partnerID=8YFLogxK

U2 - 10.1109/ICME.2005.1521354

DO - 10.1109/ICME.2005.1521354

M3 - Conference contribution

AN - SCOPUS:33750538650

SN - 0780393325

SN - 9780780393325

T3 - IEEE International Conference on Multimedia and Expo, ICME 2005

SP - 37

EP - 40

BT - IEEE International Conference on Multimedia and Expo, ICME 2005

T2 - IEEE International Conference on Multimedia and Expo, ICME 2005

Y2 - 6 July 2005 through 8 July 2005

ER -

A neural-field-like approach for modeling human group actions in meetings

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this