Human action recognition based on bag of features and multi-view neural networks

Alexandros Iosifidis; Anastasios Tefas; Ioannis Pitas

doi:10.1109/ICIP.2014.7025302

Human action recognition based on bag of features and multi-view neural networks

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

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

9 Citations (Scopus)

328 Downloads (Pure)

Abstract

In this paper, we employ Single-hidden Layer Feedforward Neural networks in order to perform human action recognition based on multiple action representations. In order to determine both optimized network and action representation combination weights, we propose an optimization process that jointly minimizes the overall network training error and the within-class variance of the training data in the corresponding hidden layer spaces. The proposed approach has been evaluated by using the state-of-the-art Bag of Features-based action video representation on three publicly available action recognition databases, where it outperforms two commonly used video representation combination approaches, as well as the best single-descriptor classification outcome.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing (ICIP 2014)
Subtitle of host publication	Proceedings of a meeting held 27-30 October 2014, Paris, France
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1510-1514
Number of pages	5
ISBN (Electronic)	9781479957514
ISBN (Print)	9781479957521
DOIs	https://doi.org/10.1109/ICIP.2014.7025302
Publication status	Published - Mar 2015
Event	IEEE International Conference on Image Processing (ICIP) - Paris, France Duration: 27 Oct 2014 → 30 Oct 2014

Publication series

Name	IEEE International Conference on Image Processing (ICIP)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)	1522-4880

Conference

Conference	IEEE International Conference on Image Processing (ICIP)
Country/Territory	France
City	Paris
Period	27/10/14 → 30/10/14

Keywords

Single-hidden Layer Feedforward Neural networks
Multi-view Learning
Human Action Recognition
Bag of Features

Access to Document

10.1109/ICIP.2014.7025302

Ioannis Pitas - Human action recognition based on bag of features and multi-view neural networks - 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/xpls/abs_all.jsp?arnumber=7025302. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 0.98 MB

Handle.net

Persistent link

Cite this

Iosifidis, A., Tefas, A., & Pitas, I. (2015). Human action recognition based on bag of features and multi-view neural networks. In 2014 IEEE International Conference on Image Processing (ICIP 2014): Proceedings of a meeting held 27-30 October 2014, Paris, France (pp. 1510-1514). (IEEE International Conference on Image Processing (ICIP)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICIP.2014.7025302

Iosifidis, Alexandros ; Tefas, Anastasios ; Pitas, Ioannis. / Human action recognition based on bag of features and multi-view neural networks. 2014 IEEE International Conference on Image Processing (ICIP 2014): Proceedings of a meeting held 27-30 October 2014, Paris, France. Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 1510-1514 (IEEE International Conference on Image Processing (ICIP)).

@inproceedings{0707eee7a6974704a53b34009abb7a5f,

title = "Human action recognition based on bag of features and multi-view neural networks",

abstract = "In this paper, we employ Single-hidden Layer Feedforward Neural networks in order to perform human action recognition based on multiple action representations. In order to determine both optimized network and action representation combination weights, we propose an optimization process that jointly minimizes the overall network training error and the within-class variance of the training data in the corresponding hidden layer spaces. The proposed approach has been evaluated by using the state-of-the-art Bag of Features-based action video representation on three publicly available action recognition databases, where it outperforms two commonly used video representation combination approaches, as well as the best single-descriptor classification outcome.",

keywords = "Single-hidden Layer Feedforward Neural networks, Multi-view Learning, Human Action Recognition, Bag of Features",

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

year = "2015",

month = mar,

doi = "10.1109/ICIP.2014.7025302",

language = "English",

isbn = "9781479957521",

series = "IEEE International Conference on Image Processing (ICIP)",

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

pages = "1510--1514",

booktitle = "2014 IEEE International Conference on Image Processing (ICIP 2014)",

address = "United States",

note = "IEEE International Conference on Image Processing (ICIP) ; Conference date: 27-10-2014 Through 30-10-2014",

}

Iosifidis, A, Tefas, A & Pitas, I 2015, Human action recognition based on bag of features and multi-view neural networks. in 2014 IEEE International Conference on Image Processing (ICIP 2014): Proceedings of a meeting held 27-30 October 2014, Paris, France. IEEE International Conference on Image Processing (ICIP), Institute of Electrical and Electronics Engineers (IEEE), pp. 1510-1514, IEEE International Conference on Image Processing (ICIP), Paris, France, 27/10/14. https://doi.org/10.1109/ICIP.2014.7025302

Human action recognition based on bag of features and multi-view neural networks. / Iosifidis, Alexandros; Tefas, Anastasios; Pitas, Ioannis.
2014 IEEE International Conference on Image Processing (ICIP 2014): Proceedings of a meeting held 27-30 October 2014, Paris, France. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 1510-1514 (IEEE International Conference on Image Processing (ICIP)).

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

TY - GEN

T1 - Human action recognition based on bag of features and multi-view neural networks

AU - Iosifidis, Alexandros

AU - Tefas, Anastasios

AU - Pitas, Ioannis

PY - 2015/3

Y1 - 2015/3

N2 - In this paper, we employ Single-hidden Layer Feedforward Neural networks in order to perform human action recognition based on multiple action representations. In order to determine both optimized network and action representation combination weights, we propose an optimization process that jointly minimizes the overall network training error and the within-class variance of the training data in the corresponding hidden layer spaces. The proposed approach has been evaluated by using the state-of-the-art Bag of Features-based action video representation on three publicly available action recognition databases, where it outperforms two commonly used video representation combination approaches, as well as the best single-descriptor classification outcome.

AB - In this paper, we employ Single-hidden Layer Feedforward Neural networks in order to perform human action recognition based on multiple action representations. In order to determine both optimized network and action representation combination weights, we propose an optimization process that jointly minimizes the overall network training error and the within-class variance of the training data in the corresponding hidden layer spaces. The proposed approach has been evaluated by using the state-of-the-art Bag of Features-based action video representation on three publicly available action recognition databases, where it outperforms two commonly used video representation combination approaches, as well as the best single-descriptor classification outcome.

KW - Single-hidden Layer Feedforward Neural networks

KW - Multi-view Learning

KW - Human Action Recognition

KW - Bag of Features

U2 - 10.1109/ICIP.2014.7025302

DO - 10.1109/ICIP.2014.7025302

M3 - Conference Contribution (Conference Proceeding)

SN - 9781479957521

T3 - IEEE International Conference on Image Processing (ICIP)

SP - 1510

EP - 1514

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

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - IEEE International Conference on Image Processing (ICIP)

Y2 - 27 October 2014 through 30 October 2014

ER -

Iosifidis A, Tefas A, Pitas I. Human action recognition based on bag of features and multi-view neural networks. In 2014 IEEE International Conference on Image Processing (ICIP 2014): Proceedings of a meeting held 27-30 October 2014, Paris, France. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 1510-1514. (IEEE International Conference on Image Processing (ICIP)). Epub 2015 Jan 29. doi: 10.1109/ICIP.2014.7025302

Human action recognition based on bag of features and multi-view neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this