mmPoint-Attention: A Unified Attention Framework for Human Pose and Activity Recognition From mmWave Radar Point Clouds

Millimeter-wave (mmWave) radar-based pose estimation and activity recognition provide robust, precise tracking of human movement, unaffected by lighting or environmental challenges. However, existing human pose estimation methods using point cloud data typically rely on single-frame inputs or apply voxelization, both of which have inherent limitations. Moreover, the conventional methods for activity recognition using point cloud often rely on multi-step processes that lose contextual information and depend on pose accuracy. To address these issues, in this paper, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mmPoint-Attention</i>, a unified attention and Transformer-based model that directly utilizes multi-frame point cloud data for both pose estimation and activity recognition without voxelization. Leveraging temporal context and attention mechanisms, our model achieves accurate 3D joint estimation and activity classification, with post-processing to enhance sequence consistency. This approach enables high recognition accuracy and computational efficiency across diverse activities compared with conventional methods.