WiMANS is a publicly available benchmark dataset designed for multi-person activity recognition and counting using Wi-Fi CSI signals, capturing scenarios with varying numbers of simultaneous subjects performing different activities in indoor environments. It matters for the field because it enables reproducible evaluation of Wi-Fi sensing systems under realistic multi-user conditions, addressing a key generalizability challenge where most prior datasets focus on single-person scenarios. The dataset supports research into both activity classification and occupancy estimation tasks, making it a versatile resource for benchmarking models that must generalize across different numbers of users and activity combinations.
Source Papers
- A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects ↗ — A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techni
- A survey on CSI-based Wi-Fi sensing datasets and models with a focus on reproducibility ↗ — A survey on CSI-based Wi-Fi sensing datasets and models with
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing ↗ — WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activi