Multi Object Tracking On Tao
Métriques
AssocA
ClsA
LocA
TETA
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | AssocA | ClsA | LocA | TETA | Paper Title | Repository |
|---|---|---|---|---|---|---|
| TETer-HTC | 37.53 | 15.70 | 57.53 | 36.85 | Tracking Every Thing in the Wild | |
| GLEE-Lite | 39.9 | 24.1 | 56.3 | 40.1 | General Object Foundation Model for Images and Videos at Scale | |
| AED (RegionCLIP) | 38.1 | 16.2 | 56.7 | 37.0 | Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown | |
| TETer-SwinT | 36.71 | 15.03 | 52.10 | 34.61 | Tracking Every Thing in the Wild | |
| GLEE-Plus | 40.9 | 30.8 | 52.9 | 41.5 | General Object Foundation Model for Images and Videos at Scale | |
| TETer | 35.02 | 13.16 | 51.58 | 33.25 | Tracking Every Thing in the Wild | |
| GLEE-Pro | 46.2 | 29.1 | 66.2 | 47.2 | General Object Foundation Model for Images and Videos at Scale | |
| AOA | 30.56 | 21.86 | 23.40 | 25.27 | 1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking | |
| AED (Co-DETR) | 52.4 | 41.7 | 71.8 | 55.3 | Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown |
0 of 9 row(s) selected.