Recent advances in quantum machine learning have motivated the exploration of quantum neural network (QNN) for sensing and signal processing tasks. In this paper, we propose a hybrid quantum-classical neural network framework for RF sensing, designed to address the challenges of noise, non-linearity, and complex spatio-temporal dependencies in RF signals. In our approach, RF time-series measurements are encoded into quantum states and processed by parameterized quantum circuits to perform convolution-like operations, while a classical classifier produces the final predictions. Overall, this work highlights the potential of QNN to enhance accuracy, parameter efficiency, and robustness in wireless sensing, and suggests a promising direction for next-generation RF sensing activity recognition and crossdomain sensing applications.
