CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing

TL;DR

CSI-Bench introduces a comprehensive, real-world WiFi sensing dataset with diverse indoor environments and multiple tasks, enabling the development of more robust and generalizable human activity monitoring models.

Contribution

The paper presents CSI-Bench, a large-scale in-the-wild WiFi sensing dataset with multi-task annotations across diverse environments, addressing limitations of previous controlled datasets.

Findings

Provides over 461 hours of real-world WiFi data from 35 users.

Includes standardized evaluation splits and baseline results for multiple tasks.

Enables development of more robust, generalizable WiFi sensing models.

Abstract

WiFi sensing has emerged as a compelling contactless modality for human activity monitoring by capturing fine-grained variations in Channel State Information (CSI). Its ability to operate continuously and non-intrusively while preserving user privacy makes it particularly suitable for health monitoring. However, existing WiFi sensing systems struggle to generalize in real-world settings, largely due to datasets collected in controlled environments with homogeneous hardware and fragmented, session-based recordings that fail to reflect continuous daily activity. We present CSI-Bench, a large-scale, in-the-wild benchmark dataset collected using commercial WiFi edge devices across 26 diverse indoor environments with 35 real users. Spanning over 461 hours of effective data, CSI-Bench captures realistic signal variability under natural conditions. It includes task-specific datasets for fall detection, breathing monitoring, localization, and motion source recognition, as well as a co-labeled multitask dataset with joint annotations for user identity, activity, and proximity. To support the development of robust and generalizable models, CSI-Bench provides standardized evaluation splits and baseline results for both single-task and multi-task learning. CSI-Bench offers a foundation for scalable, privacy-preserving WiFi sensing systems in health and broader human-centric applications.