Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance

C. Beecks; M. Hassani; F. Obeloer; T. Seidl

doi:10.1109/ISM.2015.86

Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance

C. Beecks, M. Hassani, F. Obeloer, T. Seidl

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

5 Citations (Scopus)

Abstract

One of the most fundamental challenges when accessing gestural patterns in 3D motion capture databases is the definition of spatiotemporal similarity. While distance-based similarity models such as the Gesture Matching Distance on gesture signatures are able to leverage the spatial and temporal characteristics of gestural patterns, their applicability to large 3D motion capture databases is limited due to their high computational complexity. To this end, we present a lower bound approximation of the Gesture Matching Distance that can be utilized in an optimal multi-step query processing architecture in order to provide efficient query processing. We investigate the performance in terms of accuracy and efficiency based on 3D motion capture databases and show that our approach is able to achieve an increase in efficiency of more than one order of magnitude with a negligible loss in accuracy. © 2015 IEEE.

Original language	English
Title of host publication	2015 IEEE International Symposium on Multimedia (ISM 2015) : 14-16 December 2015, Miami, Florida, USA : Proceedings
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	148-153
Number of pages	6
ISBN (Electronic)	9781509003792
DOIs	https://doi.org/10.1109/ISM.2015.86
Publication status	Published - 25 Mar 2016
Externally published	Yes
Event	2015 IEEE International Symposium on Multimedia (ISM 2015) - Florida International University , Miami Beach, United States Duration: 14 Dec 2015 → 16 Dec 2015 http://www.globaleventslist.elsevier.com/events/2015/12/international-symposium-on-multimedia-ism/

Conference

Conference	2015 IEEE International Symposium on Multimedia (ISM 2015)
Abbreviated title	ISM 2015
Country/Territory	United States
City	Miami Beach
Period	14/12/15 → 16/12/15
Internet address	http://www.globaleventslist.elsevier.com/events/2015/12/international-symposium-on-multimedia-ism/

Keywords

3D motion capture data
dynamic time warping
efficient query processing
gestural patterns
gesture matching distance
gesture signature
spatiotemporal data

Access to Document

10.1109/ISM.2015.86

http://www.mendeley.com/research/efficient-query-processing-3d-motion-capture-databases-via-lower-bound-approximation-gesture-matchin

Cite this

Beecks, C., Hassani, M., Obeloer, F., & Seidl, T. (2016). Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance. In 2015 IEEE International Symposium on Multimedia (ISM 2015) : 14-16 December 2015, Miami, Florida, USA : Proceedings (pp. 148-153). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISM.2015.86

@inproceedings{63bbc9a0ade74d7b87f3529b554a3418,

title = "Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance",

abstract = "One of the most fundamental challenges when accessing gestural patterns in 3D motion capture databases is the definition of spatiotemporal similarity. While distance-based similarity models such as the Gesture Matching Distance on gesture signatures are able to leverage the spatial and temporal characteristics of gestural patterns, their applicability to large 3D motion capture databases is limited due to their high computational complexity. To this end, we present a lower bound approximation of the Gesture Matching Distance that can be utilized in an optimal multi-step query processing architecture in order to provide efficient query processing. We investigate the performance in terms of accuracy and efficiency based on 3D motion capture databases and show that our approach is able to achieve an increase in efficiency of more than one order of magnitude with a negligible loss in accuracy. {\textcopyright} 2015 IEEE.",

keywords = "3D motion capture data, dynamic time warping, efficient query processing, gestural patterns, gesture matching distance, gesture signature, spatiotemporal data",

author = "C. Beecks and M. Hassani and F. Obeloer and T. Seidl",

year = "2016",

month = mar,

day = "25",

doi = "10.1109/ISM.2015.86",

language = "English",

pages = "148--153",

booktitle = "2015 IEEE International Symposium on Multimedia (ISM 2015) : 14-16 December 2015, Miami, Florida, USA : Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2015 IEEE International Symposium on Multimedia (ISM 2015), ISM 2015 ; Conference date: 14-12-2015 Through 16-12-2015",

url = "http://www.globaleventslist.elsevier.com/events/2015/12/international-symposium-on-multimedia-ism/",

}

Beecks, C, Hassani, M, Obeloer, F & Seidl, T 2016, Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance. in 2015 IEEE International Symposium on Multimedia (ISM 2015) : 14-16 December 2015, Miami, Florida, USA : Proceedings. Institute of Electrical and Electronics Engineers, Piscataway, pp. 148-153, 2015 IEEE International Symposium on Multimedia (ISM 2015), Miami Beach, Florida, United States, 14/12/15. https://doi.org/10.1109/ISM.2015.86

Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance. / Beecks, C.; Hassani, M.; Obeloer, F. et al.

2015 IEEE International Symposium on Multimedia (ISM 2015) : 14-16 December 2015, Miami, Florida, USA : Proceedings. Piscataway : Institute of Electrical and Electronics Engineers, 2016. p. 148-153.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance

AU - Beecks, C.

AU - Hassani, M.

AU - Obeloer, F.

AU - Seidl, T.

PY - 2016/3/25

Y1 - 2016/3/25

N2 - One of the most fundamental challenges when accessing gestural patterns in 3D motion capture databases is the definition of spatiotemporal similarity. While distance-based similarity models such as the Gesture Matching Distance on gesture signatures are able to leverage the spatial and temporal characteristics of gestural patterns, their applicability to large 3D motion capture databases is limited due to their high computational complexity. To this end, we present a lower bound approximation of the Gesture Matching Distance that can be utilized in an optimal multi-step query processing architecture in order to provide efficient query processing. We investigate the performance in terms of accuracy and efficiency based on 3D motion capture databases and show that our approach is able to achieve an increase in efficiency of more than one order of magnitude with a negligible loss in accuracy. © 2015 IEEE.

AB - One of the most fundamental challenges when accessing gestural patterns in 3D motion capture databases is the definition of spatiotemporal similarity. While distance-based similarity models such as the Gesture Matching Distance on gesture signatures are able to leverage the spatial and temporal characteristics of gestural patterns, their applicability to large 3D motion capture databases is limited due to their high computational complexity. To this end, we present a lower bound approximation of the Gesture Matching Distance that can be utilized in an optimal multi-step query processing architecture in order to provide efficient query processing. We investigate the performance in terms of accuracy and efficiency based on 3D motion capture databases and show that our approach is able to achieve an increase in efficiency of more than one order of magnitude with a negligible loss in accuracy. © 2015 IEEE.

KW - 3D motion capture data

KW - dynamic time warping

KW - efficient query processing

KW - gestural patterns

KW - gesture matching distance

KW - gesture signature

KW - spatiotemporal data

U2 - 10.1109/ISM.2015.86

DO - 10.1109/ISM.2015.86

M3 - Conference contribution

SP - 148

EP - 153

BT - 2015 IEEE International Symposium on Multimedia (ISM 2015) : 14-16 December 2015, Miami, Florida, USA : Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 2015 IEEE International Symposium on Multimedia (ISM 2015)

Y2 - 14 December 2015 through 16 December 2015

ER -

Beecks C, Hassani M, Obeloer F, Seidl T. Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance. In 2015 IEEE International Symposium on Multimedia (ISM 2015) : 14-16 December 2015, Miami, Florida, USA : Proceedings. Piscataway: Institute of Electrical and Electronics Engineers. 2016. p. 148-153 doi: 10.1109/ISM.2015.86

Efficient query processing in 3D motion capture databases via lower bound approximation of the gesture matching distance

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this