Exploiting subclass information in one-class support vector machine for video summarization

Vasileios Mygdalis; Alexandros Iosifidis; Anastasios Tefas; Ioannis Pitas

doi:10.1109/ICASSP.2015.7178373

Exploiting subclass information in one-class support vector machine for video summarization

Vasileios Mygdalis
, Alexandros Iosifidis
, Anastasios Tefas
, Ioannis Pitas

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

16 Citations (Scopus)

436 Downloads (Pure)

Abstract

In this paper, we propose a method for video summarization based on human activity description. We formulate this problem as the one of automatic video segment selection based on a learning process that employs salient video segment paradigms. For this one-class classification problem, we introduce a novel variant of the One-Class Support Vector Machine (OC-SVM) classifier that exploits subclass information in the OC-SVM optimization problem, in order to jointly minimize the data dispersion within each subclass and determine the optimal decision function. We evaluate the proposed approach in three Hollywood movies, where the performance of the proposed SOC-SVM algorithm is compared with that of the OC-SVM. Experimental results denote that the proposed approach is able to outperform OC-SVM-based video segment selection.

Original language	English
Title of host publication	2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)
Subtitle of host publication	Proceedings of a meeting held 19-24 April 2015, South Brisbane, Queensland, Australia
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	2259-2263
Number of pages	5
ISBN (Electronic)	9781467369978
ISBN (Print)	9781467369985
DOIs	https://doi.org/10.1109/ICASSP.2015.7178373
Publication status	Published - Sept 2015
Event	IEEE International Conference on Accoustics, Speech and Signal Processing (ICASSP) - Brisbane, Australia Duration: 19 Apr 2015 → 24 Apr 2015

Publication series

Name	Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)	1520-6149

Conference

Conference	IEEE International Conference on Accoustics, Speech and Signal Processing (ICASSP)
Country/Territory	Australia
City	Brisbane
Period	19/04/15 → 24/04/15

Keywords

One class classification
Subclass One-Class SVM
Supervised Video Summarization

Access to Document

10.1109/ICASSP.2015.7178373

Ioannis Pitas - Exploiting subclass information in one-class support vector machine for video summarization - 2015
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7178373. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 76.5 KB

Handle.net

Persistent link

Cite this

Mygdalis, V., Iosifidis, A., Tefas, A., & Pitas, I. (2015). Exploiting subclass information in one-class support vector machine for video summarization. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015) : Proceedings of a meeting held 19-24 April 2015, South Brisbane, Queensland, Australia (pp. 2259-2263). (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP.2015.7178373

Mygdalis, Vasileios ; Iosifidis, Alexandros ; Tefas, Anastasios et al. / Exploiting subclass information in one-class support vector machine for video summarization. 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015) : Proceedings of a meeting held 19-24 April 2015, South Brisbane, Queensland, Australia. Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 2259-2263 (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)).

@inproceedings{c6fa018451364b74bdb176e485b57664,

title = "Exploiting subclass information in one-class support vector machine for video summarization",

abstract = "In this paper, we propose a method for video summarization based on human activity description. We formulate this problem as the one of automatic video segment selection based on a learning process that employs salient video segment paradigms. For this one-class classification problem, we introduce a novel variant of the One-Class Support Vector Machine (OC-SVM) classifier that exploits subclass information in the OC-SVM optimization problem, in order to jointly minimize the data dispersion within each subclass and determine the optimal decision function. We evaluate the proposed approach in three Hollywood movies, where the performance of the proposed SOC-SVM algorithm is compared with that of the OC-SVM. Experimental results denote that the proposed approach is able to outperform OC-SVM-based video segment selection.",

keywords = "One class classification, Subclass One-Class SVM, Supervised Video Summarization",

author = "Vasileios Mygdalis and Alexandros Iosifidis and Anastasios Tefas and Ioannis Pitas",

year = "2015",

month = sep,

doi = "10.1109/ICASSP.2015.7178373",

language = "English",

isbn = "9781467369985",

series = "Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "2259--2263",

booktitle = "2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)",

address = "United States",

note = "IEEE International Conference on Accoustics, Speech and Signal Processing (ICASSP) ; Conference date: 19-04-2015 Through 24-04-2015",

}

Mygdalis, V, Iosifidis, A, Tefas, A & Pitas, I 2015, Exploiting subclass information in one-class support vector machine for video summarization. in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015) : Proceedings of a meeting held 19-24 April 2015, South Brisbane, Queensland, Australia. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers (IEEE), pp. 2259-2263, IEEE International Conference on Accoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, 19/04/15. https://doi.org/10.1109/ICASSP.2015.7178373

Exploiting subclass information in one-class support vector machine for video summarization. / Mygdalis, Vasileios; Iosifidis, Alexandros; Tefas, Anastasios et al.
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015) : Proceedings of a meeting held 19-24 April 2015, South Brisbane, Queensland, Australia. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 2259-2263 (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Exploiting subclass information in one-class support vector machine for video summarization

AU - Mygdalis, Vasileios

AU - Iosifidis, Alexandros

AU - Tefas, Anastasios

AU - Pitas, Ioannis

PY - 2015/9

Y1 - 2015/9

N2 - In this paper, we propose a method for video summarization based on human activity description. We formulate this problem as the one of automatic video segment selection based on a learning process that employs salient video segment paradigms. For this one-class classification problem, we introduce a novel variant of the One-Class Support Vector Machine (OC-SVM) classifier that exploits subclass information in the OC-SVM optimization problem, in order to jointly minimize the data dispersion within each subclass and determine the optimal decision function. We evaluate the proposed approach in three Hollywood movies, where the performance of the proposed SOC-SVM algorithm is compared with that of the OC-SVM. Experimental results denote that the proposed approach is able to outperform OC-SVM-based video segment selection.

AB - In this paper, we propose a method for video summarization based on human activity description. We formulate this problem as the one of automatic video segment selection based on a learning process that employs salient video segment paradigms. For this one-class classification problem, we introduce a novel variant of the One-Class Support Vector Machine (OC-SVM) classifier that exploits subclass information in the OC-SVM optimization problem, in order to jointly minimize the data dispersion within each subclass and determine the optimal decision function. We evaluate the proposed approach in three Hollywood movies, where the performance of the proposed SOC-SVM algorithm is compared with that of the OC-SVM. Experimental results denote that the proposed approach is able to outperform OC-SVM-based video segment selection.

KW - One class classification

KW - Subclass One-Class SVM

KW - Supervised Video Summarization

U2 - 10.1109/ICASSP.2015.7178373

DO - 10.1109/ICASSP.2015.7178373

M3 - Conference Contribution (Conference Proceeding)

SN - 9781467369985

T3 - Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

SP - 2259

EP - 2263

BT - 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - IEEE International Conference on Accoustics, Speech and Signal Processing (ICASSP)

Y2 - 19 April 2015 through 24 April 2015

ER -

Mygdalis V, Iosifidis A, Tefas A, Pitas I. Exploiting subclass information in one-class support vector machine for video summarization. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015) : Proceedings of a meeting held 19-24 April 2015, South Brisbane, Queensland, Australia. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 2259-2263. (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). Epub 2015 Aug 6. doi: 10.1109/ICASSP.2015.7178373

Exploiting subclass information in one-class support vector machine for video summarization

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this