Efficient Indexing of 3D Human Motions

D 2021

Efficient Indexing of 3D Human Motions

BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ and Pavel ZEZULA

Basic information

Original name

Efficient Indexing of 3D Human Motions

Authors

BUDÍKOVÁ, Petra (203 Czech Republic, guarantor, belonging to the institution), Jan SEDMIDUBSKÝ (203 Czech Republic, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

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

Publisher

ACM

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

References:

URL

RIV identification code

RIV/00216224:14330/21:00118943

Organization unit

Faculty of Informatics

ISBN

978-1-4503-8463-6

DOI

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

UT WoS

000723651900002

Keywords in English

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

Abstract

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.

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 and Pavel ZEZULA. Efficient Indexing of 3D Human Motions. Online. In ACM International Conference on Multimedia Retrieval (ICMR). Neuveden: ACM, 2021, p. 10-18. ISBN 978-1-4503-8463-6. Available from: 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 and Pavel ZEZULA. Efficient Indexing of 3D Human Motions. Online. In \textit{ACM International Conference on Multimedia Retrieval (ICMR)}. Neuveden: ACM, 2021, p.~10-18. ISBN~978-1-4503-8463-6. Available from: https://dx.doi.org/10.1145/3460426.3463646.

Detailed Information on Publication Record