Multiview Detection On Multiviewx
评估指标
MODA
MODP
评测结果
各个模型在此基准测试上的表现结果
模型名称 | MODA | MODP | Paper Title | Repository |
|---|---|---|---|---|
| 3DROM | 90.0 | 83.7 | 3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization | |
| SHOT | 88.3 | 82.0 | Stacked Homography Transformations for Multi-View Pedestrian Detection | - |
| MVDet | 93.6 | 79.6 | Multiview Detection with Feature Perspective Transformation | |
| EarlyBird | 94.2 | 90.1 | EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View | |
| Deep-Occulsion | 75.2 | 54.7 | Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection | |
| MVDeTr | 93.7 | 91.3 | Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation) | |
| MVFP | 95.7 | 85.1 | Enhancing Multi-View Pedestrian Detection Through Generalized 3D Feature Pulling | - |
| M-MVOT | 96.7 | 86.1 | Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization | |
| TrackTacular (Bilinear Sampling) | 96.5 | 75.0 | Lifting Multi-View Detection and Tracking to the Bird's Eye View |
0 of 9 row(s) selected.