Research map / Point clouds / Point cloud classification
SpaRTA Tracking Across Occlusions via Partitioning of 3D Clouds of Points
Andrea Cavagna, Stefania Melillo, Leonardo Parisi, Federico Ricci‐Tersenghi
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 SpaRTA COP-RT instead of SIP-RT MHT | tracking · Davis-08 sparse | MOTA: 64.1 -> 87.4 | Improved |
| use SpaRTA instead of SIP-RT SDD-MHT | tracking · Davis-08 sparse | MOTA: 78.9 -> 87.4 | Improved |
| use SpaRTA instead of SIP-RT MHT | tracking · Davis-08 sparse | IDS: 97 -> 25 | Improved |
| use SpaRTA instead of SIP-TR CP(LDQD) | tracking · Davis-08 sparse | MOTA: 88.1 -> 87.4 | No clear effect |
| use SpaRTA instead of SIP-TR CP(LDQD) | tracking · Davis-08 sparse | IDS: 126 -> 25 | Improved |
| use SpaRTA instead of SIP-TR GReTA | tracking · Davis-08 sparse | IDS: 9 -> 25 | Hurt |
| use SpaRTA instead of MHT | tracking · Davis-08 dense | MOTA: -32.0 -> 86.3 | Improved |
| use SpaRTA instead of SDD-MHT | tracking · Davis-08 dense | MOTA: 44.9 -> 86.3 | Improved |
| use SpaRTA instead of CP(LDQD) | tracking · Davis-08 dense | MOTA: 80.5 -> 86.3 | Improved |
| use SpaRTA instead of GReTA | tracking · Davis-08 dense | IDS: 7 -> 19 | Hurt |
| use SpaRTA instead of CP(LDQD) | tracking · Davis-08 dense | IDS: 156 -> 19 | Improved |
| use SpaRTA instead of SIP-RT MHT | tracking · Davis-08 sparse | ML: 0 -> 0.5 | Hurt |
Closest papers by meaning
- Tracking Through Containers and Occluders in the Wild (CVPR 2023 · similarity 0.86)
- Robust, Real-Time 3D Tracking of Multiple Objects With Similar Appearances (CVPR 2016 · similarity 0.86)
- SpatialTracker: Tracking Any 2D Pixels in 3D Space (CVPR 2024 · similarity 0.85)
- M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking (AAAI 2024 · similarity 0.85)
- TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (NeurIPS 2024 · similarity 0.84)
- TGFormer: Transformer with Track Query Group for Multi-Object Tracking (AAAI 2025 · similarity 0.84)
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.
