Research map / Video / Action recognition
MORIC: CSI Delay-Doppler Decomposition for Robust Wi-Fi-based Human Activity Recognition
Navid Hasanzadeh, Shahrokh Valaee
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 multipath delay-separated Doppler velocities with MORIC instead of SHARP Doppler spectrogram | Wi-Fi HAR · UTHAMO 4-class, orientation 180, All APs | accuracy (%): 34.8% -> 56.3% | Improved |
| use MORIC instead of APNSS + APSC single Doppler velocity | Wi-Fi HAR · UTHAMO 4-class, orientation 180, SAP 5 | accuracy (%): 39.1% -> 51.5% | Improved |
| use CSI ratio phase with random kernels instead of raw magnitude | Wi-Fi HAR · UTHAMO 4-class, orientation 180, All APs | accuracy (%): 33.7% -> 36.1% | Improved |
| use Doppler velocity inputs instead of raw CSI magnitude | Wi-Fi HAR · UTHAMO 4-class, orientation 180, SAP 5 | accuracy (%): 27.4% -> 39.1% | Improved |
| use all five APs instead of AP 5 only for MORIC | MORIC · UTHAMO 4-class, orientation 180 | accuracy (%): 51.5% -> 56.3% | Improved |
| place user to block the LOS path to AP 5 | MORIC · UTHAMO 4-class, orientation 180, SAP 5 | accuracy (%): 37.9% -> 51.5% | Improved |
| reduce to binary gesture pairs rather than four classes | MORIC · UTHAMO orientation 180, All APs | accuracy (%): 56.3% -> 80.9% | Improved |
| distinguish push-pull vs left-right gestures | MORIC · UTHAMO binary, orientation 180 | accuracy (%): 91.7% -> 50.4% | Hurt |
| use multiple delay-separated Doppler projections instead of one per antenna (ablation) | MORIC feature extraction · AP 5 t-SNE | feature separability | Improved |
Closest papers by meaning
- CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing (NeurIPS 2025 · similarity 0.89)
- ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking (AAAI 2025 · similarity 0.87)
- WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network (AAAI 2025 · similarity 0.87)
- Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition (AAAI 2025 · similarity 0.82)
- MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition (NeurIPS 2025 · similarity 0.82)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.81)
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.
