Vision-language tracking on WebUOT-1M
57.5PrecisionOKTrack
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| OKTrackTraining Setting=Retraining2024.05 | 57.5 | — | 60 | — | — | |
| OSTrackTraining Setting=Retraining2024.05 | 55.1 | — | 57 | — | — | |
| CiteTracker-256Training Setting=Retraining2024.05 | 54.2 | — | 57.7 | — | — | |
| All-in-OneInput modality=Language prompt + bounding box2024.05 | 53.1 | 61.5 | 57.1 | 56.4 | 58 | |
| OSTrackTraining Setting=Original2024.05 | 52.9 | — | 56.5 | — | — | |
| UVLTrackInput modality=Language prompt + bounding box2024.05 | 52.5 | 60 | 55.8 | 55 | 56.6 | |
| CiteTracker-256Input modality=Language prompt + bounding box2024.05 | 49.3 | 58.4 | 54.6 | 53.7 | 55.2 | |
| CiteTracker-256Training Setting=Original2024.05 | 49.3 | — | 54.6 | — | — | |
| VLTTTInput modality=Language prompt + bounding box2024.05 | 41.7 | 52.1 | 48.3 | 47.3 | 48.8 | |
| VLTSCARInput modality=Language prompt + bounding box2024.05 | 33.4 | 44 | 37.8 | 36.4 | 38 | |
| SiamFCTraining Setting=Retraining2024.05 | 25.8 | — | 38.2 | — | — | |
| JointNLTInput modality=Language prompt + bounding box2024.05 | 25.5 | 34.9 | 32.7 | 31.5 | 32.8 | |
| UVLTrackInput modality=Language prompt2024.05 | 22.5 | 33.8 | 31.2 | 30.1 | 31.3 | |
| SiamFCTraining Setting=Original2024.05 | 22.5 | — | 31.6 | — | — | |
| JointNLTInput modality=Language prompt2024.05 | 22.4 | 32.2 | 31.2 | 29.8 | 31.2 | |
| ATOMTraining Setting=Retraining2024.05 | 21.4 | — | 32.6 | — | — | |
| ATOMTraining Setting=Original2024.05 | 18.9 | — | 27 | — | — |