Sub-field · 13 papers
WiFi Deep Learning Human Sensing
WiFi-based human sensing and activity recognition using deep learning methods—including transformer architectures and CSI signals—forms the core technical thread, with papers addressing benchmarking frameworks, multi-user scenarios, and channel selection. A secondary cluster focuses on scientific document processing and digital library applications, applying language models and topic modeling to tasks such as research question identification, theorem extraction, and abstract simplification. The community is loosely unified by the application of attention mechanisms and neural network methods (drawing on foundational work like "Attention Is All You Need") across both wireless sensing and scholarly text analysis domains.
Papers in this community
- Attention Is All You Need 2017 DOI ↗
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing 2023 DOI ↗
- WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing 2025 DOI ↗
- Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents 2024 DOI ↗
- Round trip time meets transformers: high-fidelity human counting in cluttered environments 2025 DOI ↗
- Topic Modeling for Expertise Finding using Fuzzy LDA-sBERT Clusters 2024 DOI ↗
- Simplifying Scholarly Abstracts for Accessible Digital Libraries Using Language Models 2024 DOI ↗
- Leveraging Weight Vectors of Feature Words for Research Question Identification in Scientific Articles 2024 DOI ↗
- Identification of Countries' Distance from the Global Scientific Centers: A Bibliometric Analysis Based on Physics Journal Articles 2024 DOI ↗
- Energy and Policy Considerations for Deep Learning in NLP 2019 DOI ↗
- Heterogeneous Graph Attention Network 2019 DOI ↗
- SDP: A Unified Protocol and Benchmarking Framework for Reproducible Wireless Sensing 2026 DOI ↗
- CSI-Based NTC Using Ambient WiFi: Channel Selection, Topology Control and Traffic Interference 2026 DOI ↗