Visual Object Tracking on AVisT (SUC)
64.7SUCGOT-Edit-378
Evaluation Results
| Method | Links | |
|---|---|---|
| GOT-Edit-378Semantic Feature=DINOv2-L, Geometry Feature=DA3-L, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=28M, Input Resolution=378x3782026.07 | 64.7 | |
| GOT-Edit-378Semantic Feature=DINOv2-L, Geometry Feature=VGGT, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=53M, Input Resolution=378x3782026.07 | 64.5 | |
| GOT-JEPAVariant=Highest-resolution / ViT-L prioritized2026.02 | 63.7 | |
| GOT-Edit-378Semantic Feature=DINOv2-L, Geometry Feature=VGGT, Training Data of Tracker=Base, Frames=3, Trainable Parameters=53M, Input Resolution=378x3782026.07 | 63.7 | |
| GOT-JEPAVariant=Highest-resolution (ViT-L prioritized)2026.07 | 63.7 | |
| GOT-Edit-252Semantic Feature=DINOv2-L, Geometry Feature=DA3-L, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=51M, Input Resolution=252x2522026.07 | 63 | |
| MCITrack-384Semantic Feature=Fast-iTPN-L, Training Data of Tracker=Base+VastTrack, Frames=5, Trainable Parameters=287M, Input Resolution=3842026.07 | 62.9 | |
| PiVOTYear=20252026.02 | 62.2 | |
| PiVOT-378Semantic Feature=DINOv2-L, Training Data of Tracker=Base, Frames=3, Trainable Parameters=34M, Input Resolution=3782026.07 | 62.2 | |
| PiVOTYear=2025, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 62.2 | |
| LoRATYear=20242026.02 | 62 | |
| LoRAT-378Semantic Feature=DINOv2-L, Training Data of Tracker=Base, Frames=3, Trainable Parameters=32M, Input Resolution=3782026.07 | 62 | |
| ToMP-378 (Reproduced)Semantic Feature=DINOv2-L, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=25M, Input Resolution=3782026.07 | 62 | |
| LoRATYear=2024, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 62 | |
| ToMP-378Semantic Feature=DINOv2-L, Training Data of Tracker=Base, Frames=3, Trainable Parameters=25M, Input Resolution=3782026.07 | 61.5 | |
| ROMTrackYear=20232026.02 | 59.1 | |
| ROMTrackYear=2023, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 59.1 | |
| SATrackYear=20252026.02 | 58.4 | |
| SATrackYear=2025, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 58.4 | |
| UniSOTYear=20262026.02 | 57.8 | |
| SeqTrack-384Semantic Feature=ViT-MAE-L, Training Data of Tracker=Base, Frames=3, Trainable Parameters=309M, Input Resolution=3842026.07 | 57.8 | |
| UniSOTYear=2026, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 57.8 | |
| OSTrackYear=20222026.02 | 57.7 | |
| OSTrackYear=2022, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 57.7 | |
| GRMYear=20232026.02 | 54.5 | |
| GRM-320Semantic Feature=ViT-MAE-L, Training Data of Tracker=Base, Frames=3, Input Resolution=3202026.07 | 54.5 | |
| GRMYear=2023, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 54.5 | |
| ToMPYear=20222026.02 | 50.9 | |
| ToMPYear=2022, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 50.9 |