2025/12/04 by Gang Liu, Yanling Hao, Liu, Gang +3
Computer Science · Engineering · #Autoencoder #Channel (broadcasting) #Channel state information #Feature learning #Indoor and Outdoor Localization Technologies #Key (lock) #Masking (illustration) #Representation (politics) #Semantics (computer science) #Wireless Networks and Protocols #Wireless Signal Modulation Classification
paper · pdf · doi:10.1109/jiot.2026.3696504
published in IEEE Internet of Things Journal, 1 (Institute of Electrical and Electronics Engineers)
openalex created_date 2025/12/06 · openalex publication_date 2026/01/01 · openalex updated_date 2026/07/28
Human Action Recognition using WiFi Channel State Information (CSI) has emerged as an attractive alternative to vision-based methods due to its ubiquity, device-agnostic nature, and inherent privacy-preserving capabilities. However, the high cost of manual annotation and the limited scale of publicly available CSI datasets restrict the performance of supervised approaches. Self-supervised learning (SSL) offers a promising avenue, but existing contrastive paradigms rely on data augmentations that conflict with the physical semantics of radio signals and require large-batch training, making them poorly suited for CSI. To overcome these challenges, we introduce CIG-MAE—a Cross-Modal Information-Guided Masked Autoencoder—that reconstructs both the amplitude and phase of CSI using a symmetric dual-stream architecture with a high masking ratio. Specifically, we propose an Adaptive Information-Guided Masking strategy that dynamically allocates attention to time–frequency regions with high information density to improve learning efficiency, and we incorporate a Barlow Twins regularizer to align cross-modal representations without negative samples. Experiments on three public datasets show that CIG-MAE consistently outperforms SOTA SSL methods and even surpasses a fully supervised baseline, demonstrating superior data efficiency, robustness, and representation generalization.