Slow features nonnegative matrix factorization for temporal data decomposition

Lazaros Zafeiriou, Symeon Nikitidis, Stefanos Zafeiriou, Maja Pantic

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

6 Citations (Scopus)
23 Downloads (Pure)

Abstract

In this paper, we combine the principles of temporal slowness and nonnegative parts-based learning into a single framework that aims to learn slow varying parts-based representations of time varying sequences. We demonstrate that the proposed algorithm arises naturally by embedding the Slow Features Analysis trace optimization problem in the nonnegative subspace learning framework and derive novel multiplicative update rules for its optimization. The usefulness of the developed algorithm is demonstrated for unsupervised facial behaviour dynamics analysis on MMI database.
Original languageUndefined
Title of host publicationProceedings of IEEE International Conference on Image Processing (ICIP 2014)
Place of PublicationUSA
PublisherIEEE Computer Society
Pages1430-1434
Number of pages5
ISBN (Print)978-1-4799-5751-4
DOIs
Publication statusPublished - Oct 2014
EventIEEE International Conference on Image Processing 2014 - Paris, France, Paris, France
Duration: 27 Oct 201430 Oct 2014
https://icip2014.wp.imt.fr/

Publication series

Name
PublisherIEEE Computer Society

Conference

ConferenceIEEE International Conference on Image Processing 2014
Abbreviated titleICIP 2014
CountryFrance
CityParis
Period27/10/1430/10/14
Internet address

Keywords

  • HMI-HF: Human Factors
  • EWI-25823
  • EC Grant Agreement nr.: FP7/2007-2013
  • EC Grant Agreement nr.: FP7/288235
  • IR-95230
  • Nonnegative Matrix Factorization
  • Slow Features Analysis
  • METIS-309949
  • Facial behaviour dynamics analysis

Cite this

Zafeiriou, L., Nikitidis, S., Zafeiriou, S., & Pantic, M. (2014). Slow features nonnegative matrix factorization for temporal data decomposition. In Proceedings of IEEE International Conference on Image Processing (ICIP 2014) (pp. 1430-1434). USA: IEEE Computer Society. https://doi.org/10.1109/ICIP.2014.7025286
Zafeiriou, Lazaros ; Nikitidis, Symeon ; Zafeiriou, Stefanos ; Pantic, Maja. / Slow features nonnegative matrix factorization for temporal data decomposition. Proceedings of IEEE International Conference on Image Processing (ICIP 2014). USA : IEEE Computer Society, 2014. pp. 1430-1434
@inproceedings{32572bc170f24476a23d27535cb11fde,
title = "Slow features nonnegative matrix factorization for temporal data decomposition",
abstract = "In this paper, we combine the principles of temporal slowness and nonnegative parts-based learning into a single framework that aims to learn slow varying parts-based representations of time varying sequences. We demonstrate that the proposed algorithm arises naturally by embedding the Slow Features Analysis trace optimization problem in the nonnegative subspace learning framework and derive novel multiplicative update rules for its optimization. The usefulness of the developed algorithm is demonstrated for unsupervised facial behaviour dynamics analysis on MMI database.",
keywords = "HMI-HF: Human Factors, EWI-25823, EC Grant Agreement nr.: FP7/2007-2013, EC Grant Agreement nr.: FP7/288235, IR-95230, Nonnegative Matrix Factorization, Slow Features Analysis, METIS-309949, Facial behaviour dynamics analysis",
author = "Lazaros Zafeiriou and Symeon Nikitidis and Stefanos Zafeiriou and Maja Pantic",
note = "eemcs-eprint-25823",
year = "2014",
month = "10",
doi = "10.1109/ICIP.2014.7025286",
language = "Undefined",
isbn = "978-1-4799-5751-4",
publisher = "IEEE Computer Society",
pages = "1430--1434",
booktitle = "Proceedings of IEEE International Conference on Image Processing (ICIP 2014)",
address = "United States",

}

Zafeiriou, L, Nikitidis, S, Zafeiriou, S & Pantic, M 2014, Slow features nonnegative matrix factorization for temporal data decomposition. in Proceedings of IEEE International Conference on Image Processing (ICIP 2014). IEEE Computer Society, USA, pp. 1430-1434, IEEE International Conference on Image Processing 2014, Paris, France, 27/10/14. https://doi.org/10.1109/ICIP.2014.7025286

Slow features nonnegative matrix factorization for temporal data decomposition. / Zafeiriou, Lazaros; Nikitidis, Symeon; Zafeiriou, Stefanos; Pantic, Maja.

Proceedings of IEEE International Conference on Image Processing (ICIP 2014). USA : IEEE Computer Society, 2014. p. 1430-1434.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Slow features nonnegative matrix factorization for temporal data decomposition

AU - Zafeiriou, Lazaros

AU - Nikitidis, Symeon

AU - Zafeiriou, Stefanos

AU - Pantic, Maja

N1 - eemcs-eprint-25823

PY - 2014/10

Y1 - 2014/10

N2 - In this paper, we combine the principles of temporal slowness and nonnegative parts-based learning into a single framework that aims to learn slow varying parts-based representations of time varying sequences. We demonstrate that the proposed algorithm arises naturally by embedding the Slow Features Analysis trace optimization problem in the nonnegative subspace learning framework and derive novel multiplicative update rules for its optimization. The usefulness of the developed algorithm is demonstrated for unsupervised facial behaviour dynamics analysis on MMI database.

AB - In this paper, we combine the principles of temporal slowness and nonnegative parts-based learning into a single framework that aims to learn slow varying parts-based representations of time varying sequences. We demonstrate that the proposed algorithm arises naturally by embedding the Slow Features Analysis trace optimization problem in the nonnegative subspace learning framework and derive novel multiplicative update rules for its optimization. The usefulness of the developed algorithm is demonstrated for unsupervised facial behaviour dynamics analysis on MMI database.

KW - HMI-HF: Human Factors

KW - EWI-25823

KW - EC Grant Agreement nr.: FP7/2007-2013

KW - EC Grant Agreement nr.: FP7/288235

KW - IR-95230

KW - Nonnegative Matrix Factorization

KW - Slow Features Analysis

KW - METIS-309949

KW - Facial behaviour dynamics analysis

U2 - 10.1109/ICIP.2014.7025286

DO - 10.1109/ICIP.2014.7025286

M3 - Conference contribution

SN - 978-1-4799-5751-4

SP - 1430

EP - 1434

BT - Proceedings of IEEE International Conference on Image Processing (ICIP 2014)

PB - IEEE Computer Society

CY - USA

ER -

Zafeiriou L, Nikitidis S, Zafeiriou S, Pantic M. Slow features nonnegative matrix factorization for temporal data decomposition. In Proceedings of IEEE International Conference on Image Processing (ICIP 2014). USA: IEEE Computer Society. 2014. p. 1430-1434 https://doi.org/10.1109/ICIP.2014.7025286