Research map / Large language models / AI and society
WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing
Shuokang Huang, Kaihan Li, Di You, Yichong Chen, Arvin Lin, Siying Liu, Xiaohui Li, Julie A. McCann
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use 5 GHz instead of 2.4 GHz WiFi CSI (ablation) | WiFi-based sensing models · WiMANS Classroom | activity accuracy (%): 61.8 -> 64.2 | Improved |
| combine 2.4 and 5 GHz samples together (ablation) | WiFi-based sensing models · WiMANS Classroom | identity accuracy (%): 99.7 -> 94.6 | No clear effect |
| increase maximum number of users per sample from 1 to 5 (ablation) | THAT · WiMANS Classroom | activity accuracy: decreases by 25.74% | Hurt |
| increase maximum number of users per sample from 1 to 5 (ablation) | THAT · WiMANS Classroom | identity accuracy: decreases by 5.70% | Hurt |
| use video-based models instead of WiFi-based models | multi-user activity recognition · WiMANS Meeting Room | activity accuracy (%): 62.1 -> 98.0 | Improved |
| use WiFi-based models instead of video-based models for cost | multi-user sensing · WiMANS model complexity | identity throughput (Recs/s): 113.86 -> 1937.48 | Improved |
| hybrid CNN-LSTM (CLSTM) versus other WiFi models for activity recognition | WiFi-based HAR · WiMANS Empty Room 5 GHz | activity accuracy (%): 57.3 -> 64.8 | Improved |
Closest papers by meaning
- CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing (NeurIPS 2025 · similarity 0.92)
- ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking (AAAI 2025 · similarity 0.86)
- WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network (AAAI 2025 · similarity 0.86)
- Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions (ICML 2025 · similarity 0.82)
- UniMTS: Unified Pre-training for Motion Time Series (NeurIPS 2024 · similarity 0.82)
- Inertia-1: An Open Exploration of Wearable Motion Foundation Models (NeurIPS 2026 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
