Towards Scalable Retrieval of Human Motion Episodes

D 2020

Towards Scalable Retrieval of Human Motion Episodes

BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ, Ján HORVÁTH and Pavel ZEZULA

Basic information

Original name

Towards Scalable Retrieval of Human Motion Episodes

Authors

BUDÍKOVÁ, Petra (203 Czech Republic, belonging to the institution), Jan SEDMIDUBSKÝ (203 Czech Republic, belonging to the institution), Ján HORVÁTH (703 Slovakia, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

Washington, DC, 22nd IEEE International Symposium on Multimedia (ISM), p. 49-56, 8 pp. 2020

Publisher

IEEE Computer Society

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10200 1.2 Computer and information sciences

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

RIV identification code

RIV/00216224:14330/20:00114354

Organization unit

Faculty of Informatics

ISBN

978-1-7281-8697-9

DOI

http://dx.doi.org/10.1109/ISM.2020.00015

UT WoS

000654273000009

Keywords in English

skeleton data; human motion retrieval; motion episodes; text-based processing

Abstract

V originále

With the increasing availability of human motion data captured in the form of 2D/3D skeleton sequences, more complex motion recordings need to be processed. In this paper, we study the problem of similarity-based matching of medium-sized unsegmented skeleton sequences, which we denote as motion episodes. We first apply standard pose-based approaches for matching episodes and analyze their shortcomings. Then, we adopt a recent segment-based approach that transforms episode data into a text-like representation, and apply mature text-processing techniques for matching episodes. We demonstrate that this text-based approach achieves promising results in the terms of both effectiveness and efficiency, and can be further indexed to implement scalable episode retrieval.

Links

GA19-02033S, research and development project

Name: Vyhledávání, analytika a anotace datových toků lidských pohybů

Investor: Czech Science Foundation

Citovat

BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ, Ján HORVÁTH and Pavel ZEZULA. Towards Scalable Retrieval of Human Motion Episodes. Online. In 22nd IEEE International Symposium on Multimedia (ISM). Washington, DC: IEEE Computer Society, 2020, p. 49-56. ISBN 978-1-7281-8697-9. Available from: https://dx.doi.org/10.1109/ISM.2020.00015.

@inproceedings{1684078,
   author = {Budíková, Petra and Sedmidubský, Jan and Horváth, Ján and Zezula, Pavel},
   address = {Washington, DC},
   booktitle = {22nd IEEE International Symposium on Multimedia (ISM)},
   doi = {http://dx.doi.org/10.1109/ISM.2020.00015},
   keywords = {skeleton data; human motion retrieval; motion episodes; text-based processing},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Washington, DC},
   isbn = {978-1-7281-8697-9},
   pages = {49-56},
   publisher = {IEEE Computer Society},
   title = {Towards Scalable Retrieval of Human Motion Episodes},
   year = {2020}
}

TY  - JOUR
ID  - 1684078
AU  - Budíková, Petra - Sedmidubský, Jan - Horváth, Ján - Zezula, Pavel
PY  - 2020
TI  - Towards Scalable Retrieval of Human Motion Episodes
PB  - IEEE Computer Society
CY  - Washington, DC
SN  - 9781728186979
KW  - skeleton data
KW  - human motion retrieval
KW  - motion episodes
KW  - text-based processing
N2  - With the increasing availability of human motion data captured in the form of 2D/3D skeleton sequences, more complex motion recordings need to be processed. In this paper, we study the problem of similarity-based matching of medium-sized unsegmented skeleton sequences, which we denote as motion episodes. We first apply standard pose-based approaches for matching episodes and analyze their shortcomings. Then, we adopt a recent segment-based approach that transforms episode data into a text-like representation, and apply mature text-processing techniques for matching episodes. We demonstrate that this text-based approach achieves promising results in the terms of both effectiveness and efficiency, and can be further indexed to implement scalable episode retrieval.
ER  -

BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ, Ján HORVÁTH and Pavel ZEZULA. Towards Scalable Retrieval of Human Motion Episodes. Online. In \textit{22nd IEEE International Symposium on Multimedia (ISM)}. Washington, DC: IEEE Computer Society, 2020, p.~49-56. ISBN~978-1-7281-8697-9. Available from: https://dx.doi.org/10.1109/ISM.2020.00015.

Detailed Information on Publication Record