Widar is a publicly available benchmark dataset widely used in WiFi CSI-based human sensing research, containing channel state information measurements collected to support tasks such as gesture recognition and human activity recognition. It is significant to the field because it provides a standardized, reusable resource that enables fair comparison across different sensing algorithms and machine learning models, including self-supervised and deep learning approaches. The dataset is commonly referenced in multiple versions, most notably Widar3.0, which includes cross-domain scenarios with varying subjects, locations, and orientations, making it particularly valuable for evaluating model generalization.
Source Papers
- A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Channels ↗ — A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Cha
- Context-Aware Predictive Coding: A Representation Learning Framework for WiFi Sensing ↗ — Context-Aware Predictive Coding: A Representation Learning F
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing ↗ — SenseFi: A library and benchmark on deep-learning-empowered
- WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing ↗ — WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activi