Description

Convolutional Neural Networks apply learnable convolutional kernels with weight-sharing across spatial / temporal axes. They are the default backbone for CSI sensing because the natural CSI tensor (subcarriers × time × antenna pairs, or amplitude/phase spectrograms) has clear translation-invariant structure. ResNet-style residual stacks dominate the deeper variants used on crowd-density regression heatmaps.

When it's used

  • Spectrogram-based HAR / gesture / gait pipelines
  • Density-map regression for crowd counting
  • Backbones inside transfer-learning and self-supervised-learning setups
  • Lightweight encoders for embedded CSI deployment

Limitations

  • Receptive field grows slowly without dilation or pyramid pooling
  • Less effective at very long temporal context vs RNN/Transformer
  • Spatial assumption breaks if CSI tensor is permuted along feature axis

Source Papers

  • sreenu2019_6f76 — CNNs in crowd-analysis review
  • chaudhari2024_6efc — CNN occupancy classifier
  • bendalibraham2021_476e — CNN density estimation
  • atagong2025_0071 — CNN-based CSI processing
  • vaswani2017_ab85 — context paper: attention vs CNN

30 vault papers use this method

Titles and DOIs only — no abstracts, no analyses.

  • WiFi Sensing with Channel State Information 2020 DOI ↗
  • Towards Environment Independent Device Free Human Activity Recognition 2018 DOI ↗
  • Towards Environment Independent Device Free Human Activity Recognition 2018 DOI ↗
  • A Survey on Human Behavior Recognition Using Channel State Information 2019 DOI ↗
  • Cross-Domain WiFi Sensing with Channel State Information: A Survey 2023 DOI ↗
  • DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-Shot Learning 2023 DOI ↗
  • SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing 2023 DOI ↗
  • Toward Accurate Crowd Counting in Large Surveillance Areas Based on Passive WiFi Sensing 2023 DOI ↗
  • Fast and Robust Stationary Crowd Counting With Commodity WiFi 2026 DOI ↗
  • Channel State Information (CSI) Amplitude Coloring Scheme for Enhancing Accuracy of an Indoor Occupancy Detection System Using Wi-Fi Sensing 2024 DOI ↗
  • LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations 2024 DOI ↗
  • WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing 2025 DOI ↗
  • WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing 2025 DOI ↗
  • WiFi CSI-Based Device-free Multi-room Presence Detection using Conditional Recurrent Network 2021 DOI ↗
  • WiFi CSI-Based Device-free Multi-room Presence Detection using Conditional Recurrent Network 2021 DOI ↗
  • Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents 2024 DOI ↗
  • Group Counting Using Micro-Doppler Signatures From a 77GHz FMCW Radar 2023 DOI ↗
  • Group Counting Using Micro-Doppler Signatures From a 77GHz FMCW Radar 2023 DOI ↗
  • Advances in Security, Trust and Privacy in Internet of Things 2026 DOI ↗
  • On CSI and Passive Wi-Fi Radar for Opportunistic Physical Activity Recognition 2022 DOI ↗
  • Towards Energy Efficient Wireless Sensing by Leveraging Ambient Wi-Fi Traffic 2024 DOI ↗
  • MUSE-Fi: Contactless MUti-person SEnsing Exploiting Near-field Wi-Fi Channel Variation 2023 DOI ↗
  • Fundamentals, Algorithms, and Technologies of Occupancy Detection for Smart Buildings Using IoT Sensors 2024 DOI ↗
  • Human Sensing by Using Radio Frequency Signals: A Survey on Occupancy and Activity Detection 2023 DOI ↗
  • A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects 2026 DOI ↗
  • Building occupancy estimation and detection: A review 2018 DOI ↗
  • Heterogeneous Dual-Attentional Network for WiFi and Video-Fused Multi-Modal Crowd Counting 2024 DOI ↗
  • Efficient machine learning for Wi-Fi CSI-based human activity recognition using fast Monte Carlo based feature extraction 2026 DOI ↗
  • WiFi-Based Human Sensing With Deep Learning: Recent Advances, Challenges, and Opportunities 2024 DOI ↗
  • <i>STRmt</i>: A state transition based model for real‐time crowd counting in a metro system 2024 DOI ↗