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 journalArticlepeer-review

11 Citations (Scopus)


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
Issue number2
Early online date16 Dec 2011
Publication statusPublished - Feb 2012

Bibliographical 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


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


Dive into the research topics of 'Tensor Discriminant Analysis with Multi-Scale Features for Action Modeling and Categorization'. Together they form a unique fingerprint.

Cite this