Tensor Discriminant Analysis with Multi-Scale Features for Action Modeling and Categorization

Zhe-Zhou Yu, Cheng-Cheng Jia, Wei Pang, Can-Yan Zhang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

This letter addresses the problem of analyzing spatio–temporal patterns for action recognition. In this letter we organize the whole training set in a single tensor, with each mode indicating one factor which influences the result of recognition, e.g., various view points. A novel method is proposed for tensor decomposition by discriminant analysis of multiscale features which represent the motion details on different scales. In addition, the nearest neighbor classifier (NNC) is employed for action classification. Experiments on the self-manufactured action database under ideal conditions showed that the proposed method was better than state-of-the-art methods under various view angles in terms of accuracy. Experiments on the commonly used KTH database also showed that the proposed method had low time complexity and was robust against changing view points.
Original languageEnglish
Pages (from-to)95-98
Number of pages4
JournalIEEE Signal Processing Letters
Volume19
Issue number2
Early online date16 Dec 2011
DOIs
Publication statusPublished - Feb 2012

Fingerprint

Discriminant analysis
Categorization
Discriminant Analysis
Tensors
Tensor
Modeling
Classifiers
Experiments
Tensor Decomposition
Decomposition
Action Recognition
Spatio-temporal Patterns
Low Complexity
Time Complexity
Experiment
Nearest Neighbor
Classifier
Angle
Motion

Keywords

  • Action recognition
  • discriminant analysis
  • multiscale features
  • multiview
  • tensor

Cite this

Tensor Discriminant Analysis with Multi-Scale Features for Action Modeling and Categorization. / Yu, Zhe-Zhou; Jia, Cheng-Cheng; Pang, Wei; Zhang, Can-Yan.

In: IEEE Signal Processing Letters, Vol. 19, No. 2, 02.2012, p. 95-98.

Research output: Contribution to journalArticle

Yu, Zhe-Zhou ; Jia, Cheng-Cheng ; Pang, Wei ; Zhang, Can-Yan. / Tensor Discriminant Analysis with Multi-Scale Features for Action Modeling and Categorization. In: IEEE Signal Processing Letters. 2012 ; Vol. 19, No. 2. pp. 95-98.
@article{5925e21078e04ce8974bf6fa15bb4305,
title = "Tensor Discriminant Analysis with Multi-Scale Features for Action Modeling and Categorization",
abstract = "This letter addresses the problem of analyzing spatio–temporal patterns for action recognition. In this letter we organize the whole training set in a single tensor, with each mode indicating one factor which influences the result of recognition, e.g., various view points. A novel method is proposed for tensor decomposition by discriminant analysis of multiscale features which represent the motion details on different scales. In addition, the nearest neighbor classifier (NNC) is employed for action classification. Experiments on the self-manufactured action database under ideal conditions showed that the proposed method was better than state-of-the-art methods under various view angles in terms of accuracy. Experiments on the commonly used KTH database also showed that the proposed method had low time complexity and was robust against changing view points.",
keywords = "Action recognition, discriminant analysis, multiscale features, multiview, tensor",
author = "Zhe-Zhou Yu and Cheng-Cheng Jia and Wei Pang and Can-Yan Zhang",
note = "Author's personal website and employer's publicly accessible websites Preprint - Must be removed upon publication of final version and replaced with either full citation to IEEE work with a Digital Object Identifier or link to article abstract in IEEE Xplore or Authors post-print Preprint - Set-phrase must be added once submitted to IEEE for publication ({"}This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible{"}) Preprint - Set phrase must be added when accepted by IEEE for publication ({"}(c) 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.{"}) Preprint - IEEE must be informed as to the electronic address of the pre-print Postprint - Publisher copyright and source must be acknowledged (see above set statement) Publisher's version/PDF cannot be used Publisher copyright and source must be acknowledged",
year = "2012",
month = "2",
doi = "10.1109/LSP.2011.2180018",
language = "English",
volume = "19",
pages = "95--98",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Tensor Discriminant Analysis with Multi-Scale Features for Action Modeling and Categorization

AU - Yu, Zhe-Zhou

AU - Jia, Cheng-Cheng

AU - Pang, Wei

AU - Zhang, Can-Yan

N1 - Author's personal website and employer's publicly accessible websites Preprint - Must be removed upon publication of final version and replaced with either full citation to IEEE work with a Digital Object Identifier or link to article abstract in IEEE Xplore or Authors post-print Preprint - Set-phrase must be added once submitted to IEEE for publication ("This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible") Preprint - Set phrase must be added when accepted by IEEE for publication ("(c) 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.") Preprint - IEEE must be informed as to the electronic address of the pre-print Postprint - Publisher copyright and source must be acknowledged (see above set statement) Publisher's version/PDF cannot be used Publisher copyright and source must be acknowledged

PY - 2012/2

Y1 - 2012/2

N2 - This letter addresses the problem of analyzing spatio–temporal patterns for action recognition. In this letter we organize the whole training set in a single tensor, with each mode indicating one factor which influences the result of recognition, e.g., various view points. A novel method is proposed for tensor decomposition by discriminant analysis of multiscale features which represent the motion details on different scales. In addition, the nearest neighbor classifier (NNC) is employed for action classification. Experiments on the self-manufactured action database under ideal conditions showed that the proposed method was better than state-of-the-art methods under various view angles in terms of accuracy. Experiments on the commonly used KTH database also showed that the proposed method had low time complexity and was robust against changing view points.

AB - This letter addresses the problem of analyzing spatio–temporal patterns for action recognition. In this letter we organize the whole training set in a single tensor, with each mode indicating one factor which influences the result of recognition, e.g., various view points. A novel method is proposed for tensor decomposition by discriminant analysis of multiscale features which represent the motion details on different scales. In addition, the nearest neighbor classifier (NNC) is employed for action classification. Experiments on the self-manufactured action database under ideal conditions showed that the proposed method was better than state-of-the-art methods under various view angles in terms of accuracy. Experiments on the commonly used KTH database also showed that the proposed method had low time complexity and was robust against changing view points.

KW - Action recognition

KW - discriminant analysis

KW - multiscale features

KW - multiview

KW - tensor

U2 - 10.1109/LSP.2011.2180018

DO - 10.1109/LSP.2011.2180018

M3 - Article

VL - 19

SP - 95

EP - 98

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 2

ER -