Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Hrúz, Marek | |
dc.contributor.author | Gruber, Ivan | |
dc.contributor.author | Kanis, Jakub | |
dc.contributor.author | Boháček, Matyáš | |
dc.contributor.author | Hlaváč, Miroslav | |
dc.contributor.author | Krňoul, Zdeněk | |
dc.date.accessioned | 2023-03-06T11:00:26Z | - |
dc.date.available | 2023-03-06T11:00:26Z | - |
dc.date.issued | 2022 | |
dc.identifier.citation | HRÚZ, M. GRUBER, I. KANIS, J. BOHÁČEK, M. HLAVÁČ, M. KRŇOUL, Z. One Model is Not Enough: Ensembles for Isolated Sign Language Recognition. SENSORS, 2022, roč. 22, č. 13, s. nestránkováno. ISSN: 1424-8220 | cs |
dc.identifier.issn | 1424-8220 | |
dc.identifier.uri | 2-s2.0-85133217387 | |
dc.identifier.uri | http://hdl.handle.net/11025/51652 | |
dc.format | 17 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | MDPI | en |
dc.relation.ispartofseries | SENSORS | en |
dc.rights | © authors | en |
dc.title | One Model is Not Enough: Ensembles for Isolated Sign Language Recognition | en |
dc.type | článek | cs |
dc.type | article | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | In this paper, we dive into sign language recognition, focusing on the recognition of isolated signs. The task is defined as a classification problem, where a sequence of frames (i.e., images) is recognized as one of the given sign language glosses. We analyze two appearance-based approaches, I3D and TimeSformer, and one pose-based approach, SPOTER. The appearance-based approaches are trained on a few different data modalities, whereas the performance of SPOTER is evaluated on different types of preprocessing. All the methods are tested on two publicly available datasets: AUTSL and WLASL300. We experiment with ensemble techniques to achieve new state-of-the-art results of 73.84% accuracy on the WLASL300 dataset by using the CMA-ES optimization method to find the best ensemble weight parameters. Furthermore, we present an ensembling technique based on the Transformer model, which we call Neural Ensembler. | en |
dc.subject.translated | sign language recognition | en |
dc.subject.translated | CNN | en |
dc.subject.translated | Transformer | en |
dc.subject.translated | ensemble | en |
dc.identifier.doi | 10.3390/s22135043 | |
dc.type.status | Peer-reviewed | en |
dc.identifier.document-number | 824167200001 | |
dc.identifier.obd | 43937108 | |
dc.project.ID | TN01000024/Národní centrum kompetence - Kybernetika a umělá inteligence | cs |
dc.project.ID | 90042/Velká výzkumná infrastruktura povinnost (J) - CESNET II | cs |
dc.project.ID | EF15_003/0000466/Umělá inteligence a uvažování | cs |
Vyskytuje se v kolekcích: | Články / Articles (NTIS) Články / Articles (KKY) OBD |
Soubory připojené k záznamu:
Soubor | Velikost | Formát | |
---|---|---|---|
sensors-22-05043-v3-2.pdf | 1,12 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/51652
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.