Fengxia Han

Learning Shared Semantic Representations from WiFi CSI for Unified Multi-Task Human Activity Recognition

The proposed UniSense-CSI is a unified multi-task framework that jointly learns dynamic gesture recognition, static posture classification, and fall detection and converts CSI signals into pseudo-RGB images, extracts spatio-temporal features using a customized ConvNeXt backbone, and leverages an improved PerceiverIO mo...