Presentation | 2004/11/11 Marginalized Kernels for Online Action Recognition Masamichi SHIMOSAKA, Taketoshi MORI, Tatsuya HARADA, Tomomasa SATO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes a novel kernel computation algorithm between time-series human motion data that can be used for online action recognition. The proposed kernel is based on probabilistic models called switching linear dynamics (SLDs). SLDs are one of the powerful tools for tracking, analyzing and classifying human complex time-series motion. The proposed kernel incorporates information of the latent variables in SLDs by using technique of kernel design for probabilistic models called marginalized kernels. Compared with the other conventional kernels using SLDs, the main advantage of the proposed method is that the proposed method requires much less computational cost than the others. The empirical evaluation using real motion data shows that a classifier with our proposed kernel gets much better performance than the classifiers with some conventional kernel techniques. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Mixed-State Dynamics / Probabilistic Product Kernel / Complex Motion / Motion Capture |
Paper # | PRMU2004-95,HIP2004-35 |
Date of Issue |
Conference Information | |
Committee | HIP |
---|---|
Conference Date | 2004/11/11(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 | Human Information Processing (HIP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Marginalized Kernels for Online Action Recognition |
Sub Title (in English) | |
Keyword(1) | Mixed-State Dynamics |
Keyword(2) | Probabilistic Product Kernel |
Keyword(3) | Complex Motion |
Keyword(4) | Motion Capture |
1st Author's Name | Masamichi SHIMOSAKA |
1st Author's Affiliation | Graduate School of Information Science and Technology, the University of Tokyo() |
2nd Author's Name | Taketoshi MORI |
2nd Author's Affiliation | Graduate School of Information Science and Technology, the University of Tokyo:Graduafe School of Interdisciplinary Information Studies, the University of Tokyo |
3rd Author's Name | Tatsuya HARADA |
3rd Author's Affiliation | Graduate School of Information Science and Technology, the University of Tokyo |
4th Author's Name | Tomomasa SATO |
4th Author's Affiliation | Graduate School of Information Science and Technology, the University of Tokyo |
Date | 2004/11/11 |
Paper # | PRMU2004-95,HIP2004-35 |
Volume (vol) | vol.104 |
Number (no) | 449 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |