Augmenting Spatio-Temporal Human Motion Data for Effective 3D Action Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F19%3A00107708" target="_blank" >RIV/00216224:14330/19:00107708 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/ISM46123.2019.00044" target="_blank" >http://dx.doi.org/10.1109/ISM46123.2019.00044</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ISM46123.2019.00044" target="_blank" >10.1109/ISM46123.2019.00044</a>
Alternative languages
Result language
angličtina
Original language name
Augmenting Spatio-Temporal Human Motion Data for Effective 3D Action Recognition
Original language description
Action recognition is a fundamental operation in 3D human motion analysis. Existing deep learning classifiers achieve a high recognition accuracy if large amounts of training data are provided. However, such data are difficult to obtain in a variety of application scenarios, mainly due to the high costs of motion capture technologies and an absence of suitable actors. In this paper, we propose augmentation techniques to artificially enlarge existing collections of 3D human skeleton sequences. The proposed techniques are especially useful for datasets distinguishing in a high number of classes, each of them characterized by only a limited number of action samples. We experimentally demonstrate that the augmented data help to significantly increase the recognition accuracy even using a standard deep learning architecture.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10200 - Computer and information sciences
Result continuities
Project
<a href="/en/project/GA19-02033S" target="_blank" >GA19-02033S: Searching, Mining, and Annotating Human Motion Streams</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
21st IEEE International Symposium on Multimedia (ISM)
ISBN
9781728156064
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
204-207
Publisher name
IEEE Computer Society
Place of publication
Neuveden
Event location
San Diego, California, USA
Event date
Jan 1, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000528909200033