Low-rank based compact representation of motion capture data

Junhui Hou; Lap Pui Chau; Ying He; Nadia Magnenat-Thalmann

doi:10.1109/ICIP.2014.7025296

Low-rank based compact representation of motion capture data

Junhui Hou, Lap Pui Chau, Ying He, Nadia Magnenat-Thalmann

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

7 Citations (Scopus)

Abstract

In this paper, we propose a practical, elegant and effective scheme for compact mocap data representation. Guided by our analysis of the unique properties of mocap data, the input mocap sequence is optimally segmented into a set of subsequences. Then, we project the subsequences onto a pair of computational orthogonal matrices to explore strong low-rank characteristic within and among the subsequences. The experimental results show that the proposed scheme is much more effective for reducing the data size, compared with the existing techniques.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1480-1484
Number of pages	5
ISBN (Electronic)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7025296
Publication status	Published - 28 Jan 2014
Externally published	Yes

Publication series

Name	2014 IEEE International Conference on Image Processing, ICIP 2014

Keywords

compression
low-rank
Motion capture

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

More information

10.1109/ICIP.2014.7025296

Cite this

Hou, J., Chau, L. P., He, Y., & Magnenat-Thalmann, N. (2014). Low-rank based compact representation of motion capture data. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 1480-1484). Article 7025296 (2014 IEEE International Conference on Image Processing, ICIP 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025296

@inproceedings{98c678109cf14c1b85150e3edda73597,

title = "Low-rank based compact representation of motion capture data",

abstract = "In this paper, we propose a practical, elegant and effective scheme for compact mocap data representation. Guided by our analysis of the unique properties of mocap data, the input mocap sequence is optimally segmented into a set of subsequences. Then, we project the subsequences onto a pair of computational orthogonal matrices to explore strong low-rank characteristic within and among the subsequences. The experimental results show that the proposed scheme is much more effective for reducing the data size, compared with the existing techniques.",

keywords = "compression, low-rank, Motion capture",

author = "Junhui Hou and Chau, {Lap Pui} and Ying He and Nadia Magnenat-Thalmann",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7025296",

language = "English",

series = "2014 IEEE International Conference on Image Processing, ICIP 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1480--1484",

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

}

Hou, J, Chau, LP, He, Y & Magnenat-Thalmann, N 2014, Low-rank based compact representation of motion capture data. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025296, 2014 IEEE International Conference on Image Processing, ICIP 2014, Institute of Electrical and Electronics Engineers Inc., pp. 1480-1484. https://doi.org/10.1109/ICIP.2014.7025296

Low-rank based compact representation of motion capture data. / Hou, Junhui; Chau, Lap Pui; He, Ying et al.
2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1480-1484 7025296 (2014 IEEE International Conference on Image Processing, ICIP 2014).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Low-rank based compact representation of motion capture data

AU - Hou, Junhui

AU - Chau, Lap Pui

AU - He, Ying

AU - Magnenat-Thalmann, Nadia

PY - 2014/1/28

Y1 - 2014/1/28

N2 - In this paper, we propose a practical, elegant and effective scheme for compact mocap data representation. Guided by our analysis of the unique properties of mocap data, the input mocap sequence is optimally segmented into a set of subsequences. Then, we project the subsequences onto a pair of computational orthogonal matrices to explore strong low-rank characteristic within and among the subsequences. The experimental results show that the proposed scheme is much more effective for reducing the data size, compared with the existing techniques.

AB - In this paper, we propose a practical, elegant and effective scheme for compact mocap data representation. Guided by our analysis of the unique properties of mocap data, the input mocap sequence is optimally segmented into a set of subsequences. Then, we project the subsequences onto a pair of computational orthogonal matrices to explore strong low-rank characteristic within and among the subsequences. The experimental results show that the proposed scheme is much more effective for reducing the data size, compared with the existing techniques.

KW - compression

KW - low-rank

KW - Motion capture

UR - http://www.scopus.com/inward/record.url?scp=84946230344&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025296

DO - 10.1109/ICIP.2014.7025296

M3 - Conference article published in proceeding or book

AN - SCOPUS:84946230344

T3 - 2014 IEEE International Conference on Image Processing, ICIP 2014

SP - 1480

EP - 1484

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Low-rank based compact representation of motion capture data

Abstract

Publication series

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this