Stereoscopic video description for human action recognition

Ioannis Mademlis; Alexandros Iosifidis; Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas

doi:10.1109/CIMSIVP.2014.7013263

Stereoscopic video description for human action recognition

Ioannis Mademlis, Alexandros Iosifidis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas

Department of Electrical & Electronic Engineering

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

6 Citations (Scopus)

297 Downloads (Pure)

Abstract

In this paper, a stereoscopic video description method is proposed that indirectly incorporates scene geometry information derived from stereo disparity, through the manipulation of video interest points. This approach is flexible and able
to cooperate with any monocular low-level feature descriptor. The method is evaluated on the problem of recognizing complex human actions in natural settings, using a publicly available action recognition database of unconstrained stereoscopic 3D videos, coming from Hollywood movies. It is compared both
against competing depth-aware approaches and a state-of-the-art monocular algorithm. Experimental results denote that the proposed approach outperforms them and achieves state-of-the-art performance.

Original language	English
Title of host publication	2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014)
Subtitle of host publication	Proceedings of a meeting held 9-12 December 2014, Orlando, Florida, USA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781479945030
ISBN (Print)	9781479945023
DOIs	https://doi.org/10.1109/CIMSIVP.2014.7013263
Publication status	Published - Mar 2015
Event	2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP) - Orlando, FL, United States Duration: 9 Dec 2014 → 12 Dec 2014

Conference

Conference	2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP)
Country/Territory	United States
City	Orlando, FL
Period	9/12/14 → 12/12/14

Access to Document

10.1109/CIMSIVP.2014.7013263

Ioannis Pitas - Stereoscopic Video Description for Human Action Recognition - 2014
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7013263. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 663 KB

Handle.net

Persistent link

Cite this

Mademlis, I., Iosifidis, A., Tefas, A., Nikolaidis, N., & Pitas, I. (2015). Stereoscopic video description for human action recognition. In 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014) : Proceedings of a meeting held 9-12 December 2014, Orlando, Florida, USA (pp. 1-6). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CIMSIVP.2014.7013263

Mademlis, Ioannis ; Iosifidis, Alexandros ; Tefas, Anastasios et al. / Stereoscopic video description for human action recognition. 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014) : Proceedings of a meeting held 9-12 December 2014, Orlando, Florida, USA. Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 1-6

@inproceedings{1af34b3465394eb383bfee353fe496ad,

title = "Stereoscopic video description for human action recognition",

abstract = "In this paper, a stereoscopic video description method is proposed that indirectly incorporates scene geometry information derived from stereo disparity, through the manipulation of video interest points. This approach is flexible and ableto cooperate with any monocular low-level feature descriptor. The method is evaluated on the problem of recognizing complex human actions in natural settings, using a publicly available action recognition database of unconstrained stereoscopic 3D videos, coming from Hollywood movies. It is compared bothagainst competing depth-aware approaches and a state-of-the-art monocular algorithm. Experimental results denote that the proposed approach outperforms them and achieves state-of-the-art performance.",

author = "Ioannis Mademlis and Alexandros Iosifidis and Anastasios Tefas and Nikos Nikolaidis and Ioannis Pitas",

year = "2015",

month = mar,

doi = "10.1109/CIMSIVP.2014.7013263",

language = "English",

isbn = "9781479945023",

pages = "1--6",

booktitle = "2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014)",

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

address = "United States",

note = "2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP) ; Conference date: 09-12-2014 Through 12-12-2014",

}

Mademlis, I, Iosifidis, A, Tefas, A, Nikolaidis, N & Pitas, I 2015, Stereoscopic video description for human action recognition. in 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014) : Proceedings of a meeting held 9-12 December 2014, Orlando, Florida, USA. Institute of Electrical and Electronics Engineers (IEEE), pp. 1-6, 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP), Orlando, FL, United States, 9/12/14. https://doi.org/10.1109/CIMSIVP.2014.7013263

Stereoscopic video description for human action recognition. / Mademlis, Ioannis; Iosifidis, Alexandros; Tefas, Anastasios et al.
2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014) : Proceedings of a meeting held 9-12 December 2014, Orlando, Florida, USA. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 1-6.

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

TY - GEN

T1 - Stereoscopic video description for human action recognition

AU - Mademlis, Ioannis

AU - Iosifidis, Alexandros

AU - Tefas, Anastasios

AU - Nikolaidis, Nikos

AU - Pitas, Ioannis

PY - 2015/3

Y1 - 2015/3

N2 - In this paper, a stereoscopic video description method is proposed that indirectly incorporates scene geometry information derived from stereo disparity, through the manipulation of video interest points. This approach is flexible and ableto cooperate with any monocular low-level feature descriptor. The method is evaluated on the problem of recognizing complex human actions in natural settings, using a publicly available action recognition database of unconstrained stereoscopic 3D videos, coming from Hollywood movies. It is compared bothagainst competing depth-aware approaches and a state-of-the-art monocular algorithm. Experimental results denote that the proposed approach outperforms them and achieves state-of-the-art performance.

AB - In this paper, a stereoscopic video description method is proposed that indirectly incorporates scene geometry information derived from stereo disparity, through the manipulation of video interest points. This approach is flexible and ableto cooperate with any monocular low-level feature descriptor. The method is evaluated on the problem of recognizing complex human actions in natural settings, using a publicly available action recognition database of unconstrained stereoscopic 3D videos, coming from Hollywood movies. It is compared bothagainst competing depth-aware approaches and a state-of-the-art monocular algorithm. Experimental results denote that the proposed approach outperforms them and achieves state-of-the-art performance.

U2 - 10.1109/CIMSIVP.2014.7013263

DO - 10.1109/CIMSIVP.2014.7013263

M3 - Conference Contribution (Conference Proceeding)

SN - 9781479945023

SP - 1

EP - 6

BT - 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP)

Y2 - 9 December 2014 through 12 December 2014

ER -

Mademlis I, Iosifidis A, Tefas A, Nikolaidis N, Pitas I. Stereoscopic video description for human action recognition. In 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP 2014) : Proceedings of a meeting held 9-12 December 2014, Orlando, Florida, USA. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 1-6 Epub 2015 Feb 9. doi: 10.1109/CIMSIVP.2014.7013263

Stereoscopic video description for human action recognition

Abstract

Conference

Access to Document

Handle.net

Fingerprint

Cite this