Motion Words: A Text-like Representation of 3D Skeleton
Sequences

D 2020

Motion Words: A Text-like Representation of 3D Skeleton Sequences

SEDMIDUBSKÝ, Jan, Petra BUDÍKOVÁ, Vlastislav DOHNAL and Pavel ZEZULA

Basic information

Original name

Motion Words: A Text-like Representation of 3D Skeleton Sequences

Authors

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

Edition

Cham, 42nd European Conference on Information Retrieval (ECIR), p. 527-541, 15 pp. 2020

Publisher

Springer

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

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/20:00114026

Organization unit

Faculty of Informatics

ISBN

978-3-030-45438-8

ISSN

DOI

http://dx.doi.org/10.1007/978-3-030-45439-5_35

Keywords in English

3D skeleton sequence;motion word;motion vocabulary;quantization;border problem;text-based processing

Abstract

V originále

There is a growing amount of human motion data captured as a continuous 3D skeleton sequence without any information about its semantic partitioning. To make such unsegmented and unlabeled data efficiently accessible, we propose to transform them into a text-like representation and employ well-known text retrieval models. Specifically, we partition each motion synthetically into a sequence of short segments and quantize the segments into motion words, i.e. compact features with similar characteristics as words in text documents. We introduce several quantization techniques for building motion-word vocabularies and propose application-independent criteria for assessing the vocabulary quality. We verify these criteria on two real-life application scenarios.

Links

GA19-02033S, research and development project

Name: Vyhledávání, analytika a anotace datových toků lidských pohybů

Investor: Czech Science Foundation

Citovat

SEDMIDUBSKÝ, Jan, Petra BUDÍKOVÁ, Vlastislav DOHNAL and Pavel ZEZULA. Motion Words: A Text-like Representation of 3D Skeleton Sequences. Online. In 42nd European Conference on Information Retrieval (ECIR). Cham: Springer, 2020, p. 527-541. ISBN 978-3-030-45438-8. Available from: https://dx.doi.org/10.1007/978-3-030-45439-5_35.

@inproceedings{1603299,
   author = {Sedmidubský, Jan and Budíková, Petra and Dohnal, Vlastislav and Zezula, Pavel},
   address = {Cham},
   booktitle = {42nd European Conference on Information Retrieval (ECIR)},
   doi = {http://dx.doi.org/10.1007/978-3-030-45439-5_35},
   keywords = {3D skeleton sequence;motion word;motion vocabulary;quantization;border problem;text-based processing},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Cham},
   isbn = {978-3-030-45438-8},
   pages = {527-541},
   publisher = {Springer},
   title = {Motion Words: A Text-like Representation of 3D Skeleton Sequences},
   year = {2020}
}

TY  - JOUR
ID  - 1603299
AU  - Sedmidubský, Jan - Budíková, Petra - Dohnal, Vlastislav - Zezula, Pavel
PY  - 2020
TI  - Motion Words: A Text-like Representation of 3D Skeleton Sequences
PB  - Springer
CY  - Cham
SN  - 9783030454388
KW  - 3D skeleton sequence;motion word;motion vocabulary;quantization;border problem;text-based processing
N2  - There is a growing amount of human motion data captured as a continuous 3D skeleton sequence without any information about its semantic partitioning. To make such unsegmented and unlabeled data efficiently accessible, we propose to transform them into a text-like representation and employ well-known text retrieval models. Specifically, we partition each motion synthetically into a sequence of short segments and quantize the segments into motion words, i.e. compact features with similar characteristics as words in text documents. We introduce several quantization techniques for building motion-word vocabularies and propose application-independent criteria for assessing the vocabulary quality. We verify these criteria on two real-life application scenarios.
ER  -

SEDMIDUBSKÝ, Jan, Petra BUDÍKOVÁ, Vlastislav DOHNAL and Pavel ZEZULA. Motion Words: A Text-like Representation of 3D Skeleton Sequences. Online. In \textit{42nd European Conference on Information Retrieval (ECIR)}. Cham: Springer, 2020, p.~527-541. ISBN~978-3-030-45438-8. Available from: https://dx.doi.org/10.1007/978-3-030-45439-5\_{}35.

Detailed Information on Publication Record