Název:	One Model is Not Enough: Ensembles for Isolated Sign Language Recognition
Autoři:	Hrúz, Marek Gruber, Ivan Kanis, Jakub Boháček, Matyáš Hlaváč, Miroslav Krňoul, Zdeněk
Citace zdrojového dokumentu:	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
Datum vydání:	2022
Nakladatel:	MDPI
Typ dokumentu:	článek article
URI:	2-s2.0-85133217387 http://hdl.handle.net/11025/51652
ISSN:	1424-8220
Klíčová slova v dalším jazyce:	sign language recognition;CNN;Transformer;ensemble
Abstrakt v dalším jazyce:	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.
Práva:	© authors
Vyskytuje se v kolekcích:	Články / Articles (NTIS) Články / Articles (KKY) OBD

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.