Assessing similarity models for human-motion retrieval
applications

J 2016

Assessing similarity models for human-motion retrieval applications

VALČÍK, Jakub, Jan SEDMIDUBSKÝ and Pavel ZEZULA

Basic information

Original name

Assessing similarity models for human-motion retrieval applications

Authors

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

Edition

Computer Animation and Virtual Worlds, John Wiley & Sons Ltd, 2016, 1546-4261

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Impact factor

Impact factor: 0.424

RIV identification code

RIV/00216224:14330/16:00087724

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1002/cav.1674

UT WoS

000385614100003

Keywords in English

human-motion retrieval; similarity model; effectiveness evaluation; motion capture data; action recognition

Abstract

V originále

The development of motion capturing devices poses new challenges in the exploitation of human-motion data for various application fields, such as computer animation, visual surveillance, sports or physical medicine. Recently, a number of approaches dealing with motion data have been proposed, suggesting characteristic motion features to be extracted and compared on the basis of similarity. Unfortunately, almost each approach defines its own set of motion features and comparison methods, thus it is hard to fairly decide which similarity model is the most suitable for a given kind of human-motion retrieval application. To cope with this problem, we propose the HumAn Motion Model EvaluatoR (HAMMER) which is a generic framework for assessing candidate similarity models with respect to the purpose of the target application. The application purpose is specified by a user in form of a representative sample of categorized motion data. Respecting such categorization, the similarity models are assessed from the effectiveness and efficiency points of view using a set of space-complexity, information-retrieval, and performance measures. The usability of the framework is demonstrated by case studies of three practical examples of retrieval applications focusing on recognition of actions, detection of similar events, and identification of subjects.

Links

GBP103/12/G084, research and development project

Name: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Czech Science Foundation

Citovat

VALČÍK, Jakub, Jan SEDMIDUBSKÝ and Pavel ZEZULA. Assessing similarity models for human-motion retrieval applications. Computer Animation and Virtual Worlds. John Wiley & Sons Ltd, 2016, vol. 27, No 5, p. 484-500. ISSN 1546-4261. Available from: https://dx.doi.org/10.1002/cav.1674.

@article{1305925,
   author = {Valčík, Jakub and Sedmidubský, Jan and Zezula, Pavel},
   article_number = {5},
   doi = {http://dx.doi.org/10.1002/cav.1674},
   keywords = {human-motion retrieval; similarity model; effectiveness evaluation; motion capture data; action recognition},
   language = {eng},
   issn = {1546-4261},
   journal = {Computer Animation and Virtual Worlds},
   title = {Assessing similarity models for human-motion retrieval applications},
   volume = {27},
   year = {2016}
}

TY  - JOUR
ID  - 1305925
AU  - Valčík, Jakub - Sedmidubský, Jan - Zezula, Pavel
PY  - 2016
TI  - Assessing similarity models for human-motion retrieval applications
JF  - Computer Animation and Virtual Worlds
VL  - 27
IS  - 5
SP  - 484-500
EP  - 484-500
PB  - John Wiley & Sons Ltd
SN  - 15464261
KW  - human-motion retrieval
KW  - similarity model
KW  - effectiveness evaluation
KW  - motion capture data
KW  - action recognition
N2  - The development of motion capturing devices poses new challenges in the exploitation of human-motion data for various application fields, such as computer animation, visual surveillance, sports or physical medicine. Recently, a number of approaches dealing with motion data have been proposed, suggesting characteristic motion features to be extracted and compared on the basis of similarity. Unfortunately, almost each approach defines its own set of motion features and comparison methods, thus it is hard to fairly decide which similarity model is the most suitable for a given kind of human-motion retrieval application. To cope with this problem, we propose the HumAn Motion Model EvaluatoR (HAMMER) which is a generic framework for assessing candidate similarity models with respect to the purpose of the target application. The application purpose is specified by a user in form of a representative sample of categorized motion data. Respecting such categorization, the similarity models are assessed from the effectiveness and efficiency points of view using a set of space-complexity, information-retrieval, and performance measures. The usability of the framework is demonstrated by case studies of three practical examples of retrieval applications focusing on recognition of actions, detection of similar events, and identification of subjects.
ER  -

VALČÍK, Jakub, Jan SEDMIDUBSKÝ and Pavel ZEZULA. Assessing similarity models for human-motion retrieval applications. \textit{Computer Animation and Virtual Worlds}. John Wiley \&{} Sons Ltd, 2016, vol.~27, No~5, p.~484-500. ISSN~1546-4261. Available from: https://dx.doi.org/10.1002/cav.1674.

Detailed Information on Publication Record