Vision-language tracking on LaSOT ext
0.559AUCGLAD-L384
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GLAD-L384Input Modality=Vision-language, Input Resolution=3842026.01 | 0.559 | 0.646 | |
| All-in-oneInput Modality=Vision-language2026.01 | 0.545 | 0.62 | |
| SUTrack-L256Input Modality=Vision-only, Input Resolution=256, Variant=Entry 12026.01 | 0.54 | 0.617 | |
| SUTrack-L256Input Modality=Vision-only, Input Resolution=256, Variant=Entry 22026.01 | 0.536 | 0.605 | |
| ARTrack-L384Input Modality=Vision-only, Input Resolution=3842026.01 | 0.528 | 0.597 | |
| DMTrack-384Input Modality=Vision-language, Input Resolution=3842026.01 | 0.511 | 0.583 | |
| SeqTrack-L384Input Modality=Vision-only, Input Resolution=3842026.01 | 0.507 | 0.575 | |
| MixFormerV2Input Modality=Vision-only2026.01 | 0.506 | 0.569 | |
| GLAD-B256Input Modality=Vision-language, Input Resolution=2562026.01 | 0.506 | 0.557 | |
| SeqTrack-B256Input Modality=Vision-only, Input Resolution=2562026.01 | 0.495 | 0.563 | |
| MMTrackInput Modality=Vision-language2026.01 | 0.494 | 0.553 | |
| VLTTTInput Modality=Vision-language2026.01 | 0.484 | 0.559 | |
| OSTrackInput Modality=Vision-only2026.01 | 0.474 | 0.533 | |
| DMTrack-256Input Modality=Vision-language, Input Resolution=2562026.01 | 0.473 | 0.521 | |
| ARTrack-B256Input Modality=Vision-only, Input Resolution=2562026.01 | 0.464 | 0.523 | |
| TransTInput Modality=Vision-only2026.01 | 0.451 | 0.512 | |
| DiMPInput Modality=Vision-only2026.01 | 0.392 | 0.451 | |
| SNLTInput Modality=Vision-language2026.01 | 0.262 | 0.3 |