Efficient Indexing of 3D Human Motions

D 2021

Efficient Indexing of 3D Human Motions

BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ a Pavel ZEZULA

Základní údaje

Originální název

Efficient Indexing of 3D Human Motions

Autoři

BUDÍKOVÁ, Petra (203 Česká republika, garant, domácí), Jan SEDMIDUBSKÝ (203 Česká republika, domácí) a Pavel ZEZULA (203 Česká republika, domácí)

Vydání

Neuveden, ACM International Conference on Multimedia Retrieval (ICMR), od s. 10-18, 9 s. 2021

Nakladatel

ACM

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"

Odkazy

URL

Kód RIV

RIV/00216224:14330/21:00118943

Organizační jednotka

Fakulta informatiky

ISBN

978-1-4503-8463-6

DOI

http://dx.doi.org/10.1145/3460426.3463646

UT WoS

000723651900002

Klíčová slova anglicky

human motion data; skeleton sequences; motion word; text-based processing; indexing; extended inverted files; ranked retrieval; approximate searching; scalability

Štítky

core_B, DISA, firank_A

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 20. 4. 2022 11:27, RNDr. Petra Budíková, Ph.D.

Anotace

V originále

Digitization of human motion using 2D or 3D skeleton representations offers exciting possibilities for many applications but, at the same time, requires scalable content-based retrieval techniques to make such data reusable. Although a lot of research effort focuses on extracting content-preserving motion features, there is a lack of techniques that support efficient similarity search on a large scale. In this paper, we introduce a new indexing scheme for organizing large collections of spatio-temporal skeleton sequences. Specifically, we apply the motion-word concept to transform skeleton sequences into structured text-like motion documents, and index such documents using an extended inverted-file approach. Over this index, we design a new similarity search algorithm that exploits the properties of the motion-word representation and provides efficient retrieval with a variable level of approximation, possibly reaching constant search costs disregarding the collection size. Experimental results confirm the usefulness of the proposed approach.

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 a Pavel ZEZULA. Efficient Indexing of 3D Human Motions. Online. In ACM International Conference on Multimedia Retrieval (ICMR). Neuveden: ACM, 2021, s. 10-18. ISBN 978-1-4503-8463-6. Dostupné z: https://dx.doi.org/10.1145/3460426.3463646.

@inproceedings{1763301,
   author = {Budíková, Petra and Sedmidubský, Jan and Zezula, Pavel},
   address = {Neuveden},
   booktitle = {ACM International Conference on Multimedia Retrieval (ICMR)},
   doi = {http://dx.doi.org/10.1145/3460426.3463646},
   keywords = {human motion data; skeleton sequences; motion word; text-based processing; indexing; extended inverted files; ranked retrieval; approximate searching; scalability},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Neuveden},
   isbn = {978-1-4503-8463-6},
   pages = {10-18},
   publisher = {ACM},
   title = {Efficient Indexing of 3D Human Motions},
   url = {https://dl.acm.org/doi/10.1145/3460426.3463646},
   year = {2021}
}

TY  - JOUR
ID  - 1763301
AU  - Budíková, Petra - Sedmidubský, Jan - Zezula, Pavel
PY  - 2021
TI  - Efficient Indexing of 3D Human Motions
PB  - ACM
CY  - Neuveden
SN  - 9781450384636
KW  - human motion data
KW  - skeleton sequences
KW  - motion word
KW  - text-based processing
KW  - indexing
KW  - extended inverted files
KW  - ranked retrieval
KW  - approximate searching
KW  - scalability
UR  - https://dl.acm.org/doi/10.1145/3460426.3463646
N2  - Digitization of human motion using 2D or 3D skeleton representations offers exciting possibilities for many applications but, at the same time, requires scalable content-based retrieval techniques to make such data reusable. Although a lot of research effort focuses on extracting content-preserving motion features, there is a lack of techniques that support efficient similarity search on a large scale. In this paper, we introduce a new indexing scheme for organizing large collections of spatio-temporal skeleton sequences. Specifically, we apply the motion-word concept to transform skeleton sequences into structured text-like motion documents, and index such documents using an extended inverted-file approach. Over this index, we design a new similarity search algorithm that exploits the properties of the motion-word representation and provides efficient retrieval with a variable level of approximation, possibly reaching constant search costs disregarding the collection size. Experimental results confirm the usefulness of the proposed approach.
ER  -

BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ a Pavel ZEZULA. Efficient Indexing of 3D Human Motions. Online. In \textit{ACM International Conference on Multimedia Retrieval (ICMR)}. Neuveden: ACM, 2021, s.~10-18. ISBN~978-1-4503-8463-6. Dostupné z: https://dx.doi.org/10.1145/3460426.3463646.

Podrobný výpis o publikaci