Towards Scalable Retrieval of Human Motion Episodes

D 2020

Towards Scalable Retrieval of Human Motion Episodes

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

Základní údaje

Originální název

Towards Scalable Retrieval of Human Motion Episodes

Autoři

BUDÍKOVÁ, Petra (203 Česká republika, domácí), Jan SEDMIDUBSKÝ (203 Česká republika, domácí), Ján HORVÁTH (703 Slovensko, domácí) a Pavel ZEZULA (203 Česká republika, domácí)

Vydání

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

Nakladatel

IEEE Computer Society

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Kód RIV

RIV/00216224:14330/20:00114354

Organizační jednotka

Fakulta informatiky

ISBN

978-1-7281-8697-9

DOI

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

UT WoS

000654273000009

Klíčová slova anglicky

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

Štítky

DISA, firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 16. 4. 2021 23:02, RNDr. Petra Budíková, Ph.D.

Anotace

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.

Návaznosti

GA19-02033S, projekt VaV

Název: Vyhledávání, analytika a anotace datových toků lidských pohybů

Investor: Grantová agentura ČR, Searching, Mining, and Annotating Human Motion Streams

Citovat

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

Podrobný výpis o publikaci