Research map / 3D vision / Human pose estimation
Through-Wall Human Pose Estimation Using Radio Signals
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 RF signals instead of camera images for pose estimation | RF-Pose vs OpenPose · Visible scenes | AP: 68.8 -> 62.4 | Hurt |
| Use RF signals instead of camera images for pose estimation | RF-Pose vs OpenPose · Visible scenes | AP50: 77.8 -> 93.3 | Helped |
| Use RF signals for pose estimation through a wall | RF-Pose · Through-wall scenes | AP: 58.1; vision-based system fails completely | Helped |
| Use RF signals instead of camera images for pose estimation | RF-Pose vs OpenPose · Visible scenes | AP75: 72.6 -> 70.7 | Hurt |
| Use 100 RF input frames rather than 6 (ablation) | RF-Pose · Visible scenes | AP: 30.8 -> 62.4 | Helped |
| Use 50 RF input frames rather than 20 (ablation) | RF-Pose · Visible scenes | AP: 50.8 -> 59.1 | Helped |
| Use 100 RF input frames rather than 50 (ablation) | RF-Pose · Visible scenes | AP: 59.1 -> 62.4 | Helped |
Closest papers by meaning
- 3D Human Pose Estimation Using Spatio-Temporal Networks with Explicit Occlusion Training (AAAI 2020 · similarity 0.84)
- Deep Dual Consecutive Network for Human Pose Estimation (CVPR 2021 · similarity 0.83)
- Deep Reinforcement Learning for Active Human Pose Estimation (AAAI 2020 · similarity 0.83)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.83)
- Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos (CVPR 2017 · similarity 0.83)
- Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi (CVPR 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.