Open access
Oct 2026
Dual-stream attention and feature fusion for human activity recognition via wearable sensors
A new Temporal and Sensor-Modality Attention with Feature Fusion Network (TSFF) is proposed, which jointly modelling temporal and sensor-modality information with adaptive global–local fusion improves performance over the corresponding backbone under the evaluated settings.
Jiang-Tao Fan, Anish Jindal, Amir Atapour-Abarghouei
· Scientific Reports · 0 citations