From User Recognition to Activity Counting: An Identity-Agnostic Approach to Multi-User WiFi Sensing

2026-04-17

AI Summary

This work addresses the limited generalizability of existing Wi-Fi-based multi-user activity recognition methods, which rely on known user identities and struggle with unseen users or environments. To overcome this limitation, the authors propose an identity-agnostic activity counting paradigm that directly estimates the number of participants per activity class, thereby eliminating dependence on user identification. The approach leverages Wi-Fi channel state information (CSI), employing spatial projection transformations and a pre-trained convolutional backbone to extract discriminative features, followed by a regression model for count estimation. Evaluated on the WiMANS dataset, the method achieves a mean absolute error of 0.1081 under standard conditions and demonstrates robust performance with unseen users—unlike conventional approaches, whose macro F1-score drops sharply from 80.38% to 32.61%. These results substantiate the proposed method’s significantly enhanced generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Active Learning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Wi-Fi Channel State Information (CSI) enables device-free human activity recognition, but existing multi-user approaches assume a fixed set of known users during both training and inference. This closed-set assumption limits deployment, as models trained on a specific user set degrade when applied to new individuals or environments. We reformulate multi-user activity recognition as activity counting, estimating how many users perform each activity type at a given time, without associating actions with specific individuals. We propose a pipeline that converts CSI measurements into spatial projections and extracts features using a pretrained convolutional backbone. Two formulations are evaluated on the WiMANS dataset: a conventional identity-dependent model that assigns activities to fixed user slots, and an identity-agnostic model that estimates scene-level activity composition through regression. Under standard evaluation, the identity-agnostic model achieves a mean absolute error of 0.1081 on a 0-5 count scale. Under unseen-user evaluation, the identity-dependent model's macro-F1 drops from 80.38 to 32.61, while the identity-agnostic model's counting error remains stable. Feature space analysis confirms that identity-agnostic representations are more user-invariant, which explains their stronger generalization. These results suggest that activity counting provides a more practical and generalizable alternative to identity-dependent formulations for multi-user WiFi sensing.

Problem

• WiFi sensing
• multi-user activity recognition
• identity-agnostic
• activity counting
• generalization

Innovation

• activity counting
• identity-agnostic
• WiFi sensing
• Channel State Information
• user-invariant representation