Multiview Detection On Cvcs
평가 지표
F1_score (0.5m)
F1_score (1m)
MODA (0.5m)
MODA (1m)
MODP (1m)
Precision (1m)
Recall (1m)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | F1_score (0.5m) | F1_score (1m) | MODA (0.5m) | MODA (1m) | MODP (1m) | Precision (1m) | Recall (1m) | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|---|
| SVCW | / | 68.4 | / | 46.2 | 78.4 | 81.2 | 59.1 | Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting | |
| 3DROM | - | 55.1 | - | 33.9 | 73.9 | 79.5 | 42.2 | 3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization | |
| SHOT | - | 67.0 | - | 45.0 | 77.4 | 83.6 | 55.9 | Stacked Homography Transformations for Multi-View Pedestrian Detection | - |
| MVDeTr | - | 61.0 | - | 39.8 | 84.1 | 95.3 | 44.9 | Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation) | |
| MVDet | - | 60.9 | - | 36.6 | 71.0 | 79.4 | 49.4 | Multiview Detection with Feature Perspective Transformation | |
| M-MVOT | - | - | 43.5 | / | - | - | - | Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization |
0 of 6 row(s) selected.