Visual Object Tracking on TNL2K
69.5AUCOneTrackerV2-L384
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| OneTrackerV2-L384Unified Param=true, Onestep Training=true2026.05 | 69.5 | 76 | — | — | — | |
| SUTrack-L384Unified Param=true, Onestep Training=true2026.05 | 67.9 | 72.1 | — | — | — | |
| OneTrackerV2-L224Unified Param=true, Onestep Training=true2026.05 | 67.5 | 73 | — | — | — | |
| SUTrack-L224Unified Param=true, Onestep Training=true2026.05 | 66.7 | 70.3 | — | — | — | |
| OneTrackerV2-B384Unified Param=true, Onestep Training=true2026.05 | 66.4 | 71.9 | — | — | — | |
| OneTrackerV2-B224Unified Param=true, Onestep Training=true2026.05 | 65.8 | 70.2 | — | — | — | |
| SUTrack-B384Unified Param=true, Onestep Training=true2026.05 | 65.6 | 69.3 | — | — | — | |
| SUTrack-B224Unified Param=true, Onestep Training=true2026.05 | 65 | 67.9 | — | — | — | |
| UVLTrack-LReference Setting=NL+BBOX2024.01 | 64.9 | 69.3 | — | — | — | |
| DUTrackType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 64.9 | 70.6 | 82.9 | — | — | |
| UVLTrack-LVariant Type=Performance-oriented2024.01 | 64.8 | 68.8 | — | — | — | |
| OneTrackerV2-B224-CompressLayers=6, FPS=1592026.05 | 64.7 | 68.5 | — | — | — | |
| DTPTrack-L378Model Variant=L, Input Resolution=3782026.04 | 63.7 | — | — | — | — | |
| RELO-L256Model Scale=Large, Input Resolution=2562026.05 | 63.6 | — | — | — | — | |
| MemVLTType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 63.3 | 67.4 | 80.9 | — | — | |
| UVLTrack-BReference Setting=NL+BBOX2024.01 | 63.1 | 66.7 | — | — | — | |
| UVLTrackType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 63.1 | 66.7 | — | — | — | |
| UVLTrack-BVariant Type=Basic2024.01 | 62.7 | 65.4 | — | — | — | |
| SeqTrackv2-L384Unified Param=true, Onestep Training=false2026.05 | 62.4 | 66.1 | — | — | — | |
| LoRAT-L378Supervision type=Fully Supervised Tracking, Input resolution=3782026.05 | 62.3 | — | — | — | — | |
| SPMTrack-BModel Variant=B2026.04 | 62 | — | — | — | — | |
| ODTrackVariant=Large2024.01 | 61.7 | — | — | — | — | |
| ODTrack-L384Train=Seq, Temp.=32025.05 | 61.7 | — | — | — | — | |
| ARTrackV2-L384Train=Seq, Temp.=22025.05 | 61.6 | — | — | — | — | |
| DreamTrackSupervision type=Fully Supervised Tracking2026.05 | 61.2 | — | — | — | — | |
| LoRAT-L224Model Scale=Large, Input Resolution=2242026.05 | 61.1 | — | — | — | — | |
| ODTrackVariant=Base2024.01 | 60.9 | — | — | — | — | |
| ODTrack-B384Train=Seq, Temp.=32025.05 | 60.9 | — | — | — | — | |
| ODTrack-B384Model Variant=B, Input Resolution=3842026.04 | 60.9 | — | — | — | — | |
| SUTrack-T224FPS=1002026.05 | 60.9 | 62.3 | — | — | — | |
| RELO-B256Model Scale=Base, Input Resolution=2562026.05 | 60.9 | — | — | — | — | |
| ARTrack-L384Train=Seq, Temp.=12025.05 | 60.8 | 64.5 | 77.5 | — | — | |
| SeqTrack-L384 + MPTTrain=Frame, Temp.=22025.05 | 60.4 | 64.2 | 77.5 | — | — | |
| DTPTrack-B224Model Variant=B, Input Resolution=2242026.04 | 60.3 | — | — | — | — | |
| ARTrack-L384Model Scale=Large, Input Resolution=3842026.05 | 60.3 | — | — | — | — | |
| ARTrack2024.01 | 59.8 | — | — | — | — | |
| SeqTrack-L384Train=Frame, Temp.=22025.05 | 59.6 | 63.5 | 76.6 | — | — | |
| UNINEXTBackbone=ViT-H2023.03 | 59.3 | 62.8 | — | — | — | |
| ARTrackV2-B256Train=Seq, Temp.=22025.05 | 59.2 | — | — | — | — | |
| ARTrackV2-B256Model Variant=B, Input Resolution=2562026.04 | 59.2 | — | — | — | — | |
| MMTrackType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 58.6 | 59.4 | 75.2 | — | — | |
| ARTrack-B256 + MPTTrain=Frame, Temp.=12025.05 | 58.5 | 60.9 | 75.2 | — | — | |
| UVLTrack-LReference Setting=NL2024.01 | 58.2 | 60.9 | — | — | — | |
| UNINEXTBackbone=ConvNeXt-L2023.03 | 58.1 | 60.7 | — | — | — | |
| OneTrackerTU=false2023.04 | 58 | 59.1 | — | — | — | |
| OneTracker-3842026.05 | 58 | 59.1 | — | — | — | |
| OneTrackerUnified Param=false, Onestep Training=false2026.05 | 58 | 59.1 | — | — | — | |
| ARTrack-B256Train=Seq, Temp.=12025.05 | 57.9 | 59.6 | 74 | — | — | |
| SeqTrackBackbone=Large, Resolution=3842023.04 | 57.8 | — | — | — | — | |
| SeqTrack-B256 + MPTTrain=Frame, Temp.=22025.05 | 57.8 | 60.3 | 75.9 | — | — | |
| OSTrack-B384 + MPTTrain=Frame, Temp.=12025.05 | 57.8 | 59.5 | 74.8 | — | — | |
| OSTrack-B384Train=Frame, Temp.=12025.05 | 57.5 | 58.6 | 74.2 | — | — | |
| ARTrack256Input Resolution=2562026.04 | 57.5 | — | — | — | — | |
| SeqTrackerV2-B224FPS=402026.05 | 57.5 | 59.7 | — | — | — | |
| JointNLTInitialize=NL+BB2023.03 | 56.9 | 58.1 | — | — | — | |
| JointNLTReference Setting=NL+BBOX2024.01 | 56.9 | 58.1 | — | — | — | |
| SeqTrackBackbone=Large, Resolution=2562023.04 | 56.9 | — | — | — | — | |
| DropTrack-B384TU=false2023.04 | 56.9 | 57.9 | — | — | — | |
| DropTrack384Input Resolution=3842026.04 | 56.9 | — | — | — | — | |
| JointNLTType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 56.9 | 58.1 | 73.6 | — | — | |
| ATTrackerType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 56.9 | 64.7 | 75 | — | — | |
| SeqTrack-L256Model Scale=Large, Input Resolution=2562026.05 | 56.9 | — | — | — | — | |
| DTLLMType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 56.6 | 56.9 | — | — | — | |
| DiffusionTrack-B256 (2)TU=false2023.04 | 56.5 | 57.3 | — | — | — | |
| SeqTrack-B256Train=Frame, Temp.=22025.05 | 56.5 | 58.6 | 74.2 | — | — | |
| SeqTrackVariant=Base2024.01 | 56.4 | — | — | — | — | |
| SeqTrackBackbone=Base, Resolution=3842023.04 | 56.4 | — | — | — | — | |
| SeqTrack-B384TU=true2023.04 | 56.4 | — | — | — | — | |
| SeqTrack-B384Model Variant=B, Input Resolution=3842026.04 | 56.4 | — | — | — | — | |
| UNINEXTBackbone=ResNet-502023.03 | 56 | 57.5 | — | — | — | |
| OSTrackResolution=3842022.03 | 55.9 | — | — | — | — | |
| OSTrack-384Initialize=BB2023.03 | 55.9 | — | — | — | — | |
| OSTrackBackbone=ViT-B2023.03 | 55.9 | — | — | — | — | |
| OSTrack2024.01 | 55.9 | — | — | — | — | |
| OSTrack-384Variant Type=Performance-oriented2024.01 | 55.9 | — | — | — | — | |
| OSTrack2023.04 | 55.9 | — | — | — | — | |
| SwinTrack-384TU=false2023.04 | 55.9 | 57.1 | — | — | — | |
| OSTrack-384TU=false2023.04 | 55.9 | 56.7 | — | — | — | |
| OSTrack2026.05 | 55.9 | — | — | — | — | |
| OSTrack-B256 + MPTTrain=Frame, Temp.=12025.05 | 55.8 | 56.5 | 72.7 | — | — | |
| UVLTrack-BReference Setting=NL2024.01 | 55.7 | 57.2 | — | — | — | |
| UVLTrackType=Vision-Language, Supervised=Yes, Initialize=NL2026.05 | 55.7 | 57.2 | — | — | — | |
| SimTrack-L/14Variant Type=Performance-oriented2024.01 | 55.6 | 55.7 | — | — | — | |
| SimTrack2023.04 | 55.6 | — | — | — | — | |
| SimTrack-LTU=false2023.04 | 55.6 | 55.7 | — | — | — | |
| OSTrack-B256Train=Frame, Temp.=12025.05 | 55.6 | 56.1 | 72.1 | — | — | |
| Sim-L14Train=Frame, Temp.=12025.05 | 55.6 | 55.7 | — | — | — | |
| SimTrack2026.05 | 55.6 | — | — | — | — | |
| SVLTrack-V384Type=Vision-only, Supervised=Init.BBox, Initialize=BBox, Resolution=3842026.05 | 55.5 | 57.8 | 73.1 | — | — | |
| PNTrack-384Supervision type=Self Supervised Tracking, Input resolution=3842026.05 | 55.3 | — | — | — | — | |
| SeqTrackBackbone=Base, Resolution=2562023.04 | 54.9 | — | — | — | — | |
| SimTrackBackbone=ViT-B2023.03 | 54.8 | 53.8 | — | — | — | |
| SimTrack-B/16Variant Type=Basic2024.01 | 54.8 | 53.8 | — | — | — | |
| Sim-B16Train=Frame, Temp.=12025.05 | 54.8 | 53.8 | — | — | — | |
| VLTTTType=Vision-Language, Supervised=Yes, Initialize=NL+BBox2026.05 | 54.7 | 55.3 | 71.8 | — | — | |
| JointNLTInitialize=NL2023.03 | 54.6 | 55 | — | — | — | |
| JointNLTReference Setting=NL2024.01 | 54.6 | 55 | — | — | — | |
| JointNLTType=Vision-Language, Supervised=Yes, Initialize=NL2026.05 | 54.6 | 55 | — | — | — | |
| OSTrackResolution=2562022.03 | 54.3 | — | — | — | — | |
| OSTrack-256Variant Type=Basic2024.01 | 54.3 | — | — | — | — |