Presentation 2008-07-15
Study of Recognizing Human Actions Similar to Each Other from a Video Sequence by a Tensor Decomposition Based Approach
Takayuki HORI, Jun OHYA, Jun KURUMISAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a Tensor Decomposition Based method that can recognize an unknown person's action from a video sequence, where the unknown person is not included in the database (tensor) used for the recognition. The tensor consists of persons, actions and time-series image features. For the observed unknown person's action, one of the actions stored in the tensor is assumed. Using the motion signature obtained from the assumption, the unknown person's actions are synthesized. The actions of one of the persons in the tensor are replaced by the synthesized actions. Then, the core tensor for the replaced tensor is computed. This process is repeated for the actions and persons. For each iteration, the difference between the replaced and original core tensors is computed. The assumption that gives the minimal difference is the action recognition result. Three image features are tested for recognition experiments. Experiments using 15 persons' seven kinds of action show the effectiveness of the recognition method and clarify the useful image features.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Tensor Decomposition / SVD / Motion Recognition / Core Tensor
Paper # IE2008-40,MVE2008-34
Date of Issue

Conference Information
Committee MVE
Conference Date 2008/7/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study of Recognizing Human Actions Similar to Each Other from a Video Sequence by a Tensor Decomposition Based Approach
Sub Title (in English)
Keyword(1) Tensor Decomposition
Keyword(2) SVD
Keyword(3) Motion Recognition
Keyword(4) Core Tensor
1st Author's Name Takayuki HORI
1st Author's Affiliation Graduate School of Global Information and Telecommunication Studies, Waseda University()
2nd Author's Name Jun OHYA
2nd Author's Affiliation Graduate School of Global Information and Telecommunication Studies, Waseda University
3rd Author's Name Jun KURUMISAWA
3rd Author's Affiliation Dept. of Policy Informatics, Chiba University of Commerce
Date 2008-07-15
Paper # IE2008-40,MVE2008-34
Volume (vol) vol.108
Number (no) 128
Page pp.pp.-
#Pages 6
Date of Issue