Visual event detection using multi-dimensional concept dynamics

Shahram Ebadollahi; Lexing Xie; Shih Fu Chang; John R. Smith

doi:10.1109/ICME.2006.262691

Visual event detection using multi-dimensional concept dynamics

Shahram Ebadollahi^*, Lexing Xie, Shih Fu Chang, John R. Smith

^*Corresponding author for this work

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

50 Citations (Scopus)

Abstract

A novel framework is introduced for visual event detection. Visual events are viewed as stochastic temporal processes in the semantic concept space. In this concept-centered approach to visual event modeling, the dynamic pattern of an event is modeled through the collective evolution patterns of the individual semantic concepts in the course of the visual event. Video clips containing different events are classified by employing information about how well their dynamics in the direction of each semantic concept matches those of a given event. Results indicate that such a data-driven statistical approach is in fact effective in detecting different visual events such as exiting car, riot, and airplane flying.

Original language	English
Title of host publication	2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings
Pages	881-884
Number of pages	4
DOIs	https://doi.org/10.1109/ICME.2006.262691
Publication status	Published - 2006
Externally published	Yes
Event	2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Toronto, ON, Canada Duration: 9 Jul 2006 → 12 Jul 2006

Publication series

Name	2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings
Volume	2006

Conference

Conference	2006 IEEE International Conference on Multimedia and Expo, ICME 2006
Country/Territory	Canada
City	Toronto, ON
Period	9/07/06 → 12/07/06

Access to Document

10.1109/ICME.2006.262691

Cite this

Ebadollahi, S., Xie, L., Chang, S. F., & Smith, J. R. (2006). Visual event detection using multi-dimensional concept dynamics. In 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings (pp. 881-884). Article 4036741 (2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings; Vol. 2006). https://doi.org/10.1109/ICME.2006.262691

@inproceedings{ea78a2ff4a8d4f0aa63e3c217623a7a1,

title = "Visual event detection using multi-dimensional concept dynamics",

abstract = "A novel framework is introduced for visual event detection. Visual events are viewed as stochastic temporal processes in the semantic concept space. In this concept-centered approach to visual event modeling, the dynamic pattern of an event is modeled through the collective evolution patterns of the individual semantic concepts in the course of the visual event. Video clips containing different events are classified by employing information about how well their dynamics in the direction of each semantic concept matches those of a given event. Results indicate that such a data-driven statistical approach is in fact effective in detecting different visual events such as exiting car, riot, and airplane flying.",

author = "Shahram Ebadollahi and Lexing Xie and Chang, {Shih Fu} and Smith, {John R.}",

year = "2006",

doi = "10.1109/ICME.2006.262691",

language = "English",

isbn = "1424403677",

series = "2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings",

pages = "881--884",

booktitle = "2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings",

note = "2006 IEEE International Conference on Multimedia and Expo, ICME 2006 ; Conference date: 09-07-2006 Through 12-07-2006",

}

Ebadollahi, S, Xie, L, Chang, SF & Smith, JR 2006, Visual event detection using multi-dimensional concept dynamics. in 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings., 4036741, 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings, vol. 2006, pp. 881-884, 2006 IEEE International Conference on Multimedia and Expo, ICME 2006, Toronto, ON, Canada, 9/07/06. https://doi.org/10.1109/ICME.2006.262691

Visual event detection using multi-dimensional concept dynamics. / Ebadollahi, Shahram; Xie, Lexing; Chang, Shih Fu et al.
2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings. 2006. p. 881-884 4036741 (2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings; Vol. 2006).

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

TY - GEN

T1 - Visual event detection using multi-dimensional concept dynamics

AU - Ebadollahi, Shahram

AU - Xie, Lexing

AU - Chang, Shih Fu

AU - Smith, John R.

PY - 2006

Y1 - 2006

N2 - A novel framework is introduced for visual event detection. Visual events are viewed as stochastic temporal processes in the semantic concept space. In this concept-centered approach to visual event modeling, the dynamic pattern of an event is modeled through the collective evolution patterns of the individual semantic concepts in the course of the visual event. Video clips containing different events are classified by employing information about how well their dynamics in the direction of each semantic concept matches those of a given event. Results indicate that such a data-driven statistical approach is in fact effective in detecting different visual events such as exiting car, riot, and airplane flying.

AB - A novel framework is introduced for visual event detection. Visual events are viewed as stochastic temporal processes in the semantic concept space. In this concept-centered approach to visual event modeling, the dynamic pattern of an event is modeled through the collective evolution patterns of the individual semantic concepts in the course of the visual event. Video clips containing different events are classified by employing information about how well their dynamics in the direction of each semantic concept matches those of a given event. Results indicate that such a data-driven statistical approach is in fact effective in detecting different visual events such as exiting car, riot, and airplane flying.

UR - http://www.scopus.com/inward/record.url?scp=34247591036&partnerID=8YFLogxK

U2 - 10.1109/ICME.2006.262691

DO - 10.1109/ICME.2006.262691

M3 - Conference contribution

SN - 1424403677

SN - 9781424403677

T3 - 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings

SP - 881

EP - 884

BT - 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings

T2 - 2006 IEEE International Conference on Multimedia and Expo, ICME 2006

Y2 - 9 July 2006 through 12 July 2006

ER -

Visual event detection using multi-dimensional concept dynamics

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this