Multi Object Tracking On Wildtrack
Metrics
IDF1
MOTA
Results
Performance results of various models on this benchmark
Model Name | IDF1 | MOTA | Paper Title | Repository |
|---|---|---|---|---|
| GLMB-DO | 72.5 | 70.1 | A Bayesian Filter for Multi-view 3D Multi-object Tracking with Occlusion Handling | - |
| DMCT Stack | 81.9 | 74.6 | Real-time 3D Deep Multi-Camera Tracking | - |
| GLMB-YOLOv3 | 74.3 | 69.7 | A Bayesian Filter for Multi-view 3D Multi-object Tracking with Occlusion Handling | - |
| BEV-SUSHI | 95.6 | 92.6 | BEV-SUSHI: Multi-Target Multi-Camera 3D Detection and Tracking in Bird's-Eye View | - |
| DMCT | 77.8 | 72.8 | Real-time 3D Deep Multi-Camera Tracking | - |
| ReST | 86.7 | 84.9 | ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking | |
| EarlyBird | 92.3 | 89.5 | EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View | |
| TrackTacular (Bilinear Sampling) | 95.3 | 91.8 | Lifting Multi-View Detection and Tracking to the Bird's Eye View | |
| MVFlow | 93.5 | 91.3 | Multi-view Tracking Using Weakly Supervised Human Motion Prediction |
0 of 9 row(s) selected.