Multiple Object Tracking On Bdd100K Test 1
Metrics
mHOTA
mIDF1
mMOTA
Results
Performance results of various models on this benchmark
Model Name | mHOTA | mIDF1 | mMOTA | Paper Title | Repository |
|---|---|---|---|---|---|
| ContrasTR | 46.1 | 56.5 | 42.8 | Contrastive Learning for Multi-Object Tracking with Transformers | |
| ByteTrack | - | 55.8 | 40.1 | ByteTrack: Multi-Object Tracking by Associating Every Detection Box | |
| QDtrack | 41.8 | 52.3 | 35.6 | QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking | |
| SUSHI | 48.2 | 60.0 | 40.2 | Unifying Short and Long-Term Tracking with Graph Hierarchies | |
| Yu et al. | - | 44.7 | 26.3 | BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning |
0 of 5 row(s) selected.