Video action recognition with spatio-temporal graph embedding and spline modeling

Yin Yuan; Haomian Zheng; Zhu Li; Dapeng Zhang

doi:10.1109/ICASSP.2010.5496275

Video action recognition with spatio-temporal graph embedding and spline modeling

Yin Yuan, Haomian Zheng, Zhu Li, Dapeng Zhang

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

12 Citations (Scopus)

Abstract

In recent years, video analysis and event recognition are becoming a popular research topic with wide applications in surveillance and security. In this paper, we proposed a video action appearance modeling based on spatio-temporal graph embedding and video action recognition based on video luminance field trajectory spline modeling and aligned matching. Graphs are computed from spline re-sampling of training video data set. Matching is achieved from minimizing the average projection distance between query clips and training groups. Simulation with the Cambridge hand gesture data set demonstrates the effectiveness of the proposed solution.

Original language	English
Title of host publication	2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
Pages	2422-2425
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2010.5496275
Publication status	Published - 8 Nov 2010
Event	2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Dallas, TX, United States Duration: 14 Mar 2010 → 19 Mar 2010

Conference

Conference	2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
Country/Territory	United States
City	Dallas, TX
Period	14/03/10 → 19/03/10

Keywords

Appearance modeling
Graph embedding
Spline modeling
Video event analysis

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

More information

10.1109/ICASSP.2010.5496275

Cite this

@inproceedings{ba06c3c7a5ed41728b78f36b8091a128,

title = "Video action recognition with spatio-temporal graph embedding and spline modeling",

abstract = "In recent years, video analysis and event recognition are becoming a popular research topic with wide applications in surveillance and security. In this paper, we proposed a video action appearance modeling based on spatio-temporal graph embedding and video action recognition based on video luminance field trajectory spline modeling and aligned matching. Graphs are computed from spline re-sampling of training video data set. Matching is achieved from minimizing the average projection distance between query clips and training groups. Simulation with the Cambridge hand gesture data set demonstrates the effectiveness of the proposed solution.",

keywords = "Appearance modeling, Graph embedding, Spline modeling, Video event analysis",

author = "Yin Yuan and Haomian Zheng and Zhu Li and Dapeng Zhang",

year = "2010",

month = nov,

day = "8",

doi = "10.1109/ICASSP.2010.5496275",

language = "English",

isbn = "9781424442966",

pages = "2422--2425",

booktitle = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings",

note = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 ; Conference date: 14-03-2010 Through 19-03-2010",

}

Yuan, Y, Zheng, H, Li, Z & Zhang, D 2010, Video action recognition with spatio-temporal graph embedding and spline modeling. in 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings., 5496275, pp. 2422-2425, 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010, Dallas, TX, United States, 14/03/10. https://doi.org/10.1109/ICASSP.2010.5496275

Video action recognition with spatio-temporal graph embedding and spline modeling. / Yuan, Yin; Zheng, Haomian; Li, Zhu et al.
2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings. 2010. p. 2422-2425 5496275.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Video action recognition with spatio-temporal graph embedding and spline modeling

AU - Yuan, Yin

AU - Zheng, Haomian

AU - Li, Zhu

AU - Zhang, Dapeng

PY - 2010/11/8

Y1 - 2010/11/8

N2 - In recent years, video analysis and event recognition are becoming a popular research topic with wide applications in surveillance and security. In this paper, we proposed a video action appearance modeling based on spatio-temporal graph embedding and video action recognition based on video luminance field trajectory spline modeling and aligned matching. Graphs are computed from spline re-sampling of training video data set. Matching is achieved from minimizing the average projection distance between query clips and training groups. Simulation with the Cambridge hand gesture data set demonstrates the effectiveness of the proposed solution.

AB - In recent years, video analysis and event recognition are becoming a popular research topic with wide applications in surveillance and security. In this paper, we proposed a video action appearance modeling based on spatio-temporal graph embedding and video action recognition based on video luminance field trajectory spline modeling and aligned matching. Graphs are computed from spline re-sampling of training video data set. Matching is achieved from minimizing the average projection distance between query clips and training groups. Simulation with the Cambridge hand gesture data set demonstrates the effectiveness of the proposed solution.

KW - Appearance modeling

KW - Graph embedding

KW - Spline modeling

KW - Video event analysis

UR - http://www.scopus.com/inward/record.url?scp=78049387473&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2010.5496275

DO - 10.1109/ICASSP.2010.5496275

M3 - Conference article published in proceeding or book

SN - 9781424442966

SP - 2422

EP - 2425

BT - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings

T2 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010

Y2 - 14 March 2010 through 19 March 2010

ER -

Video action recognition with spatio-temporal graph embedding and spline modeling

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this