The NGT200 Dataset: Geometric Multi-View Isolated Sign Recognition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ranum, Oline, Wessels, David R., Otterspeer, Gomer, Bekkers, Erik J., Roelofsen, Floris, Andersen, Jari I.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912041981181952
author Ranum, Oline
Wessels, David R.
Otterspeer, Gomer
Bekkers, Erik J.
Roelofsen, Floris
Andersen, Jari I.
author_facet Ranum, Oline
Wessels, David R.
Otterspeer, Gomer
Bekkers, Erik J.
Roelofsen, Floris
Andersen, Jari I.
contents Sign Language Processing (SLP) provides a foundation for a more inclusive future in language technology; however, the field faces several significant challenges that must be addressed to achieve practical, real-world applications. This work addresses multi-view isolated sign recognition (MV-ISR), and highlights the essential role of 3D awareness and geometry in SLP systems. We introduce the NGT200 dataset, a novel spatio-temporal multi-view benchmark, establishing MV-ISR as distinct from single-view ISR (SV-ISR). We demonstrate the benefits of synthetic data and propose conditioning sign representations on spatial symmetries inherent in sign language. Leveraging an SE(2) equivariant model improves MV-ISR performance by 8%-22% over the baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15284
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The NGT200 Dataset: Geometric Multi-View Isolated Sign Recognition
Ranum, Oline
Wessels, David R.
Otterspeer, Gomer
Bekkers, Erik J.
Roelofsen, Floris
Andersen, Jari I.
Computer Vision and Pattern Recognition
Computation and Language
Sign Language Processing (SLP) provides a foundation for a more inclusive future in language technology; however, the field faces several significant challenges that must be addressed to achieve practical, real-world applications. This work addresses multi-view isolated sign recognition (MV-ISR), and highlights the essential role of 3D awareness and geometry in SLP systems. We introduce the NGT200 dataset, a novel spatio-temporal multi-view benchmark, establishing MV-ISR as distinct from single-view ISR (SV-ISR). We demonstrate the benefits of synthetic data and propose conditioning sign representations on spatial symmetries inherent in sign language. Leveraging an SE(2) equivariant model improves MV-ISR performance by 8%-22% over the baseline.
title The NGT200 Dataset: Geometric Multi-View Isolated Sign Recognition
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2409.15284