Research map / Point clouds / Point cloud classification
MiliPoint: A Point Cloud Dataset for mmWave Radar
Han Cui, Shu Zhong, Jiacheng Wu, Zichao Shen, Naim Dahnoun, Yiren Zhao
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 |
|---|---|---|---|
| pad each data packet instead of padding whole batch (ablation) | PointNet++ · MiliPoint identification | Top1 accuracy (%): 72.31% -> 87.30% | Improved |
| PointMLP instead of DGCNN | point-based DNN · MiliPoint identification | Top1 accuracy (%): 77.65 -> 95.88 | Improved |
| PointMLP instead of PointNet++ on action classification | point-based DNN · MiliPoint action classification | Top1 accuracy (%): 34.45 -> 18.37 | Hurt |
| PointNet++ instead of Pointformer | point-based DNN · MiliPoint action classification | Top1 accuracy (%): 29.27 -> 34.45 | Improved |
| PointMLP instead of PointNet++ on keypoint estimation (9 point) | point-based DNN · MiliPoint keypoint | MLE (cm): 13.55 -> 13.12 | Improved |
| PointMLP instead of DGCNN on keypoint estimation (18 point) | point-based DNN · MiliPoint keypoint | MLE (cm): 18.51 -> 14.11 | Improved |
| increase number of stacked frames s (ablation) | PointNet++ · keypoint estimation and action classification | MLE / Top1 accuracy | No clear effect |
| stack 50 frames instead of 5 for action classification (ablation) | PointNet++ · MiliPoint action classification | Top1 accuracy (%) | Improved |
| trained models versus random guess on action classification | DGCNN · MiliPoint action classification | Top1 accuracy (%): 2.59 -> 13.61 | Improved |
Closest papers by meaning
- milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing (ECCV 2024 · similarity 0.90)
- DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition (ECCV 2026 · similarity 0.89)
- Gait Recognition for Co-Existing Multiple People Using Millimeter Wave Sensing (AAAI 2020 · similarity 0.85)
- MVDoppler-Pose: Multi-Modal Multi-View mmWave Sensing for Long-Distance Self-Occluded Human Walking Pose Estimation (CVPR 2025 · similarity 0.84)
- MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception (NeurIPS 2026 · similarity 0.82)
- RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation (AAAI 2024 · similarity 0.82)
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.
