Incremental slow features analysis with indefinite kernel for online temporal video segmentation

Stephan Liwicki; Stefanos Zafeiriou; Maja Pantic

doi:10.1007/11817963.1

Incremental slow features analysis with indefinite kernel for online temporal video segmentation

Stephan Liwicki, Stefanos Zafeiriou, Maja Pantic

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

Abstract

Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA’s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.

Original language	Undefined
Title of host publication	Proceedings of the 11th Asian Conference on Computer Vision, ACCV 2012
Place of Publication	London
Publisher	Springer
Pages	162-176
Number of pages	14
ISBN (Print)	978-3-642-37443-2
DOIs	https://doi.org/10.1007/11817963.1 https://doi.org/10.1007/978-3-642-37444-9_13
Publication status	Published - Nov 2012
Event	11th Asian Conference on Computer Vision, ACCV 2012 - Daejeon, Korea, Republic of Duration: 5 Nov 2012 → 9 Nov 2012 Conference number: 11

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	7725

Conference

Conference	11th Asian Conference on Computer Vision, ACCV 2012
Abbreviated title	ACCV
Country/Territory	Korea, Republic of
City	Daejeon
Period	5/11/12 → 9/11/12

Keywords

HMI-MI: MULTIMODAL INTERACTIONS
METIS-296219
IR-84323
EWI-22888

Access to Document

http://eprints.eemcs.utwente.nl/secure2/22888/01/liwicki2012accv.pdf

Cite this

Liwicki, S., Zafeiriou, S., & Pantic, M. (2012). Incremental slow features analysis with indefinite kernel for online temporal video segmentation. In Proceedings of the 11th Asian Conference on Computer Vision, ACCV 2012 (pp. 162-176). (Lecture Notes in Computer Science; Vol. 7725). Springer. https://doi.org/10.1007/11817963.1, https://doi.org/10.1007/978-3-642-37444-9_13

@inproceedings{7b7bcbdfeddb4c1a91530307c12a8704,

title = "Incremental slow features analysis with indefinite kernel for online temporal video segmentation",

abstract = "Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA{\textquoteright}s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.",

keywords = "HMI-MI: MULTIMODAL INTERACTIONS, METIS-296219, IR-84323, EWI-22888",

author = "Stephan Liwicki and Stefanos Zafeiriou and Maja Pantic",

note = "10.1007/978-3-642-37444-9_13 ; 11th Asian Conference on Computer Vision, ACCV 2012 ; Conference date: 05-11-2012 Through 09-11-2012",

year = "2012",

month = nov,

doi = "10.1007/11817963.1",

language = "Undefined",

isbn = "978-3-642-37443-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "162--176",

booktitle = "Proceedings of the 11th Asian Conference on Computer Vision, ACCV 2012",

address = "Germany",

}

Liwicki, S, Zafeiriou, S & Pantic, M 2012, Incremental slow features analysis with indefinite kernel for online temporal video segmentation. in Proceedings of the 11th Asian Conference on Computer Vision, ACCV 2012. Lecture Notes in Computer Science, vol. 7725, Springer, London, pp. 162-176, 11th Asian Conference on Computer Vision, ACCV 2012, Daejeon, Korea, Republic of, 5/11/12. https://doi.org/10.1007/11817963.1, https://doi.org/10.1007/978-3-642-37444-9_13

Incremental slow features analysis with indefinite kernel for online temporal video segmentation. / Liwicki, Stephan; Zafeiriou, Stefanos; Pantic, Maja.
Proceedings of the 11th Asian Conference on Computer Vision, ACCV 2012. London: Springer, 2012. p. 162-176 (Lecture Notes in Computer Science; Vol. 7725).

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

TY - GEN

T1 - Incremental slow features analysis with indefinite kernel for online temporal video segmentation

AU - Liwicki, Stephan

AU - Zafeiriou, Stefanos

AU - Pantic, Maja

N1 - Conference code: 11

PY - 2012/11

Y1 - 2012/11

N2 - Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA’s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.

AB - Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA’s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - METIS-296219

KW - IR-84323

KW - EWI-22888

U2 - 10.1007/11817963.1

DO - 10.1007/11817963.1

M3 - Conference contribution

SN - 978-3-642-37443-2

T3 - Lecture Notes in Computer Science

SP - 162

EP - 176

BT - Proceedings of the 11th Asian Conference on Computer Vision, ACCV 2012

PB - Springer

CY - London

T2 - 11th Asian Conference on Computer Vision, ACCV 2012

Y2 - 5 November 2012 through 9 November 2012

ER -