WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network
This work addresses activity detection using WiFi signals, which is an incremental improvement for applications like smart homes or healthcare.
The paper tackles WiFi-based temporal activity detection by proposing a Dual Pyramid Network with novel encoders and fusion mechanisms, achieving superior performance over baselines on a new dataset of over 2,114 activity segments.
We address the challenge of WiFi-based temporal activity detection and propose an efficient Dual Pyramid Network that integrates Temporal Signal Semantic Encoders and Local Sensitive Response Encoders. The Temporal Signal Semantic Encoder splits feature learning into high and low-frequency components, using a novel Signed Mask-Attention mechanism to emphasize important areas and downplay unimportant ones, with the features fused using ContraNorm. The Local Sensitive Response Encoder captures fluctuations without learning. These feature pyramids are then combined using a new cross-attention fusion mechanism. We also introduce a dataset with over 2,114 activity segments across 553 WiFi CSI samples, each lasting around 85 seconds. Extensive experiments show our method outperforms challenging baselines.