DeSIRe: Deep Signer-Invariant Representations for Sign Language Recognition

• Tipo: Artigo em Revista Científica Internacional
• Data: 2019

Autores

Pedro M. Ferreira (Autor) Outra; Diogo Pernes (Autor) Outra; Ana Rebelo (Autor) Outra; Jaime S. Cardoso (Autor) FEUP

Revista

Título: IEEE Transactions on Systems, Man, and Cybernetics: Systems

Páginas: 1-16

ISSN: 2168-2216

Editora: IEEE

Indexação

ISI Web of Knowledge - 8 Citações

Scopus - 10 Citações

Outras Informações

ID Authenticus: P-00R-HFD

DOI: 10.1109/tsmc.2019.2957347

Abstract (EN): As a key technology to help bridging the gap between deaf and hearing people, sign language recognition (SLR) has become one of the most active research topics in the human–computer interaction field. Although several SLR methodologies have been proposed, the development of a realworld SLR system is still a very challenging task. One of the main challenges is related to the large intersigner variability that exists in the manual signing process of sign languages. To address this problem, we propose a novel end-to-end deep neural network that explicitly models highly discriminative signer-independent latent representations from the input data. The key idea of our model is to learn a distribution over latent representations, conditionally independent of signer identity. Accordingly, the learned latent representations will preserve as much information as possible about the signs, and discard signer-specific traits that are irrelevant for recognition. By imposing such regularization in the representation space, the result is a truly signer-independent model which is robust to different and new test signers. The experimental results demonstrate the effectiveness of the proposed model in several SLR databases.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 16