Tag
This paper introduces EMG-CrossFormer, a hybrid convolutional-transformer model for multimodal sEMG hand gesture recognition, which achieves state-of-the-art accuracy on NinaPro datasets by fusing sEMG and inertial signals via cross-attention.
Proposes a lightweight neural architecture search performed directly on the deployment device for near-sensor computing, validated on sEMG sign language and fault diagnosis datasets, achieving improved accuracy and reduced RAM occupancy.