Multiple Object Tracking On Bdd100K Val
Métriques
TETA
mIDF1
mMOTA
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | TETA | mIDF1 | mMOTA | Paper Title | Repository |
|---|---|---|---|---|---|
| Unicorn | - | 54.0 | 41.2 | Towards Grand Unification of Object Tracking | |
| ContrasTR | - | 52.9 | 41.7 | Contrastive Learning for Multi-Object Tracking with Transformers | |
| QDTrack | 47.8 | 50.8 | 36.6 | Quasi-Dense Similarity Learning for Multiple Object Tracking | |
| UNINEXT-H | - | 56.7 | 44.2 | Universal Instance Perception as Object Discovery and Retrieval | |
| TETer | 50.8 | 53.3 | 39.1 | Tracking Every Thing in the Wild | |
| MOTRv2 | - | 56.5 | 43.6 | MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors | |
| Adaptive-searching -windows Tracker | - | 56.5 | 34.4 | Tackling multiple object tracking with complicated motions—Re-designing the integration of motion and appearance | - |
| QDTrack | 51.3 | 54.3 | 42.1 | QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking | |
| ByteTrack | 55.7 | 54.8 | 45.5 | ByteTrack: Multi-Object Tracking by Associating Every Detection Box |
0 of 9 row(s) selected.