Visual Object Tracking on OTB99 (AUC, PRE)
0.764AUCVLTTT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VLTTTInitialize=NL+BB2023.03 | 0.764 | 0.931 | |
| VLTTTType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.74 | 0.898 | |
| OneTrackerV2-L384Unified Param=true, Onestep Training=true2026.05 | 0.732 | 0.953 | |
| OneTrackerV2-L224Unified Param=true, Onestep Training=true2026.05 | 0.729 | 0.946 | |
| OneTrackerV2-B384Unified Param=true, Onestep Training=true2026.05 | 0.728 | 0.95 | |
| SUTrack-L224Unified Param=true, Onestep Training=true2026.05 | 0.727 | 0.944 | |
| OneTrackerV2-B224Unified Param=true, Onestep Training=true2026.05 | 0.725 | 0.948 | |
| SeqTrackv2-L384Unified Param=true, Onestep Training=false2026.05 | 0.714 | 0.936 | |
| SUTrack-L384Unified Param=true, Onestep Training=true2026.05 | 0.712 | 0.931 | |
| DUTrackType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.709 | 0.939 | |
| SUTrack-B224Unified Param=true, Onestep Training=true2026.05 | 0.708 | 0.934 | |
| DTLLMType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.706 | 0.911 | |
| SVLTrack-V384Type=Vision-only, Supervised=Init.BBox, Initialize=BBox, Resolution=3842026.05 | 0.706 | 0.932 | |
| MMTrackType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.705 | 0.918 | |
| SUTrack-B384Unified Param=true, Onestep Training=true2026.05 | 0.697 | 0.912 | |
| OneTrackerUnified Param=false, Onestep Training=false2026.05 | 0.697 | 0.915 | |
| UVLTrackType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.693 | 0.899 | |
| ATTrackerType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.693 | 0.903 | |
| TNL2K-2Initialize=NL+BB2023.03 | 0.68 | 0.88 | |
| TNL2K-IIType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.68 | 0.88 | |
| SSTrack-256Type=Vision-only, Supervised=Init.BBox, Initialize=BBox2026.05 | 0.679 | — | |
| SVLTrack-V256Type=Vision-only, Supervised=Init.BBox, Initialize=BBox, Resolution=2562026.05 | 0.679 | 0.912 | |
| SVLTrack-L384Type=Vision-Language, Supervised=Init.Lang, Initialize=NL, Resolution=3842026.05 | 0.667 | 0.893 | |
| SNLTInitialize=NL+BB2023.03 | 0.666 | 0.804 | |
| SNLTType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.666 | 0.848 | |
| Diff-TrackerType=Vision-only, Supervised=No, Initialize=BBox2026.05 | 0.661 | 0.898 | |
| SVLTrack-L256Type=Vision-Language, Supervised=Init.Lang, Initialize=NL, Resolution=2562026.05 | 0.654 | 0.877 | |
| JointNLTInitialize=NL+BB2023.03 | 0.653 | 0.856 | |
| JointNLTType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 0.653 | 0.856 | |
| TADSType=Vision-only, Supervised=Init.BBox, Initialize=BBox2026.05 | 0.653 | — | |
| ULASTType=Vision-only, Supervised=No, Initialize=BBox2026.05 | 0.648 | 0.879 | |
| RTTNLDInitialize=NL+BB2023.03 | 0.61 | 0.79 | |
| LUDTType=Vision-only, Supervised=No, Initialize=BBox2026.05 | 0.602 | 0.769 | |
| UVLTrackType=Vision-Language, Supervised=Yes, Initialize=NL2026.05 | 0.601 | 0.791 | |
| UDTType=Vision-only, Supervised=No, Initialize=BBox2026.05 | 0.594 | 0.301 | |
| JointNLTInitialize=NL2023.03 | 0.592 | 0.776 | |
| JointNLTType=Vision-Language, Supervised=Yes, Initialize=NL2026.05 | 0.592 | 0.776 | |
| USOTType=Vision-only, Supervised=No, Initialize=BBox2026.05 | 0.589 | 0.806 | |
| GTIInitialize=NL2023.03 | 0.581 | 0.732 | |
| ATTrackerType=Vision-Language, Supervised=Init.Info, Initialize=NL+BBox2026.05 | 0.555 | 0.775 | |
| TNLS-IIIInitialize=NL+BB2023.03 | 0.55 | 0.72 | |
| RTTNLDInitialize=NL2023.03 | 0.54 | 0.78 | |
| CTRNLTInitialize=NL2023.03 | 0.53 | 0.72 | |
| TNLS-IIInitialize=NL2023.03 | 0.25 | 0.29 | |
| TNL2K-1Initialize=NL2023.03 | 0.19 | 0.24 |