Spatial-temporal feature-based End-to-end Fourier network for 3D sign language recognition

Sunusi Bala Abdullahi, Kosin Chamnongthai, Verónica Bolón-Canedo, Brais Cancela

Abstract: Highlights•FS-EFCNN is an automatic sign-based FS model for sign language recognition.•The FS model combines 3D spatial–temporal features and Fourier features.•The FS-EFCNN is verified using 3D real-life data sets without complex preprocessing.•The FS-EFCNN model achieved state-of-the-art performance with compact features.