Shenzhen
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Lung segmentation | Shenzhen dataset (test) | Dice Score96.9 | 69 | |
| Road Network-based Trajectory Generation | ShenZhen | JSD0.01 | 60 | |
| Traffic Prediction | Shenzhen | MAE (10 min)1.2403 | 42 | |
| Probabilistic forecasting | Shenzhen (Step 6) | QS3.9787 | 20 | |
| Landmark Detection | Shenzhen (test) | MRE2.58 | 18 | |
| Segmentation | Shenzhen (test) | DSC95 | 15 | |
| 1-step forecasting | Shenzhen Dataset | QS1.5943 | 13 | |
| Spatio-Temporal Kriging | Shenzhen | MAE0.046 | 10 | |
| Classification | ShenZhen (test) | AUROC98.88 | 10 | |
| Medical Imaging Classification | Shenzhen public (test) | Accuracy90.15 | 9 | |
| Classification | Shenzhen 21 (test) | F1 Score81.3 | 9 | |
| Trajectory Generation | Shenzhen 168 hours | Displacement0.0012 | 9 | |
| PM2.5 Forecasting | Shenzhen 3-Day | MAE12.69 | 7 | |
| PM2.5 Forecasting | Shenzhen (2-Day) | MAE12.27 | 7 | |
| PM2.5 Forecasting | Shenzhen 1-Day | MAE10.55 | 7 | |
| Probabilistic forecasting | Shenzhen (Step 12) | QS9.3349 | 7 | |
| Vehicle rebalancing | Shenzhen (test) | Inference Time (min)0.001 | 6 | |
| Next-edge prediction | ShenZhen (test) | Cross-Entropy Loss0.81 | 5 | |
| Next-location prediction | Shenzhen dataset | ACC87.65 | 3 | |
| Synthetic Image Generation | Shenzhen | Accuracy83.85 | 3 | |
| Classification | Shenzhen | AUROC99.47 | 2 | |
| Computer-Aided Diagnosis (CAD) | Shenzhen | AUC0.6221 | 2 | |
| Epidemic Simulation | Shenzhen (test) | MAPE (E Active)0.1078 | 2 |
Showing 23 of 23 rows