Towards Efficient Human Action Retrieval based on Triplet-Loss Metric Learning

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F22%3A00125807" target="_blank" >RIV/00216224:14330/22:00125807 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-031-12423-5_18" target="_blank" >http://dx.doi.org/10.1007/978-3-031-12423-5_18</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-12423-5_18" target="_blank" >10.1007/978-3-031-12423-5_18</a>

Result language
angličtina
Original language name
Towards Efficient Human Action Retrieval based on Triplet-Loss Metric Learning
Original language description
Recent pose-estimation methods enable digitization of human motion by extracting 3D skeleton sequences from ordinary video recordings. Such spatio-temporal skeleton representation offers attractive possibilities for a wide range of applications but, at the same time, requires effective and efficient content-based access to make the extracted data reusable. In this paper, we focus on content-based retrieval of pre-segmented skeleton sequences of human actions to identify the most similar ones to a query action. We mainly deal with the extraction of content-preserving action features, which are learned using the triplet-loss approach in an unsupervised way. Such features are (1) effective as they achieve a similar retrieval quality as the features learned in a supervised way, and (2) of a fixed size which enables the application of indexing structures for efficient retrieval.
Czech name
—
Czech description
—

Project
<a href="/en/project/EF16_019%2F0000822" target="_blank" >EF16_019/0000822: CyberSecurity, CyberCrime and Critical Information Infrastructures Center of Excellence</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
33rd International Conference on Database and Expert Systems Applications (DEXA)
ISBN
9783031124228
ISSN
0302-9743
e-ISSN
—
Number of pages
14
Pages from-to
234-247
Publisher name
Springer-Verlag
Place of publication
Berlin, Heidelberg
Event location
Vienna, Austria
Event date
Jan 1, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000877013800018

Similar results(10)