Object Tracking on TrackingNet
89Precision (P)OneTrackerV2-L384
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| OneTrackerV2-L384Multi Modal=true2026.05 | 89 | 88.6 | 92.5 | — | — | |
| SUTrackResolution=384, Model Size=Large2024.12 | 88.7 | 87.7 | 91.7 | — | — | |
| SUTrack-L384Multi Modal=true2026.05 | 88.7 | 87.7 | 91.7 | — | — | |
| OneTrackerV2-L224Multi Modal=true2026.05 | 88.3 | 87.5 | 91.6 | — | — | |
| RELO-L256Model Scale=Large, Input Resolution=2562026.05 | 88 | 87.3 | 91.6 | — | — | |
| OneTrackerV2-B384Multi Modal=true2026.05 | 87.6 | 87.2 | 91.1 | — | — | |
| ARPTrack-L384Multi Modal=false2026.05 | 87.4 | 86.6 | 91.1 | — | — | |
| ARPTrack-L384Model Scale=Large, Input Resolution=3842026.05 | 87.4 | 86.6 | 91.1 | — | — | |
| SPMTrack-L384Multi Modal=false2026.05 | 87.2 | 86.9 | 91 | — | — | |
| SUTrackResolution=384, Model Size=Base2024.12 | 86.8 | 86.5 | 90.7 | — | — | |
| SUTrack-B384Multi Modal=true2026.05 | 86.8 | 86.5 | 90.7 | — | — | |
| SUTrackResolution=224, Model Size=Large2024.12 | 86.7 | 86.5 | 90.9 | — | — | |
| ODTrackResolution=384, Model Size=Large2024.12 | 86.7 | 86.1 | 91 | — | — | |
| ODTrack-L384Train=Seq, Temp.=32025.05 | 86.7 | 86.1 | 91 | — | — | |
| SUTrack-L224Multi Modal=true2026.05 | 86.7 | 86.5 | 90.9 | — | — | |
| ODTrack-L384Multi Modal=false2026.05 | 86.7 | 86.1 | 91 | — | — | |
| ODTrack-L384Model Scale=Large, Input Resolution=3842026.05 | 86.7 | 86.1 | 91 | — | — | |
| SUTrack-L224Model Scale=Large, Input Resolution=2242026.05 | 86.7 | 86.5 | 90.9 | — | — | |
| SimTrackBackbone=ViT-B2023.03 | 86.5 | 82.3 | — | — | — | |
| UNINEXTBackbone=ViT-H2023.03 | 86.4 | 85.4 | 89 | — | — | |
| ARTrackV2Resolution=384, Model Size=Large2024.12 | 86.2 | 86.1 | 90.4 | — | — | |
| SeqTrack-L384 + MPTTrain=Frame, Temp.=22025.05 | 86.2 | 85.8 | 90.1 | — | — | |
| ARTrackV2-L384Train=Seq, Temp.=22025.05 | 86.2 | 86.1 | 90.4 | — | — | |
| OneTrackerV2-B224Multi Modal=true2026.05 | 86.2 | 86.3 | 90.6 | — | — | |
| ARTrackV2-L384Multi Modal=false2026.05 | 86.2 | 86.1 | 90.4 | — | — | |
| RELO-B256Model Scale=Base, Input Resolution=2562026.05 | 86.2 | 86.4 | 90.7 | — | — | |
| ARTrackV2-L384Model Scale=Large, Input Resolution=3842026.05 | 86.2 | 86.1 | 90.4 | — | — | |
| MCITrack-B224Evaluation Regime=Non-real-time, Speed (fps) GPU=34, Speed (fps) CPU=2, Speed (fps) AGX=62026.03 | 86.1 | 86.3 | 90.9 | — | — | |
| MCITrackSource=AAAI25, Supervised=✓2026.05 | 86.1 | 86.3 | 90.9 | — | — | |
| ARTrackResolution=384, Model Size=Large2024.12 | 86 | 85.6 | 89.6 | — | — | |
| MixViT-L (ConvMAE)Train=Frame, Temp.=22025.05 | 86 | 86.1 | 90.3 | — | — | |
| SeqTrack-L384Train=Frame, Temp.=22025.05 | 85.9 | 85.6 | 90 | — | — | |
| SeqTrackResolution=384, Model Size=Large2024.12 | 85.8 | 85.5 | 89.8 | — | — | |
| ARTrack-L384Train=Seq, Temp.=12025.05 | 85.8 | 85.4 | 90.2 | — | — | |
| MixViTResolution=384, Model Size=Large2024.12 | 85.7 | 85.4 | 90.2 | — | — | |
| SPMTrack-B384Multi Modal=false2026.05 | 85.6 | 86.1 | 90.2 | — | — | |
| ARTrackV2Source=CVPR24, Supervised=✓2026.05 | 85.5 | 85.7 | 89.8 | — | — | |
| LORATResolution=378, Model Size=Large2024.12 | 85.4 | 85.6 | 89.7 | — | — | |
| LoRAT-L378Multi Modal=false2026.05 | 85.4 | 85.6 | 89.7 | — | — | |
| ARPTrack-B256Multi Modal=false2026.05 | 85.3 | 85.5 | 90 | — | — | |
| ARPTrackSource=CVPR25, Supervised=✓2026.05 | 85.3 | 85.5 | 90 | — | — | |
| DreamTrackSource=CVPR25, Supervised=✓2026.05 | 85.3 | 85.8 | 90 | — | — | |
| ARPTrack-B256Model Scale=Base, Input Resolution=2562026.05 | 85.3 | 85.5 | 90 | — | — | |
| SUTrackResolution=224, Model Size=Base2024.12 | 85.1 | 85.7 | 90.3 | — | — | |
| SUTrack-B224Evaluation Regime=Non-real-time, Speed (fps) GPU=55, Speed (fps) CPU=6, Speed (fps) AGX=132026.03 | 85.1 | 85.7 | 90.3 | — | — | |
| SUTrack-B224Multi Modal=true2026.05 | 85.1 | 85.7 | 90.3 | — | — | |
| SUTrack-B224Model Scale=Base, Input Resolution=2242026.05 | 85.1 | 85.7 | 90.3 | — | — | |
| SMTrack-M384Architecture=SSM-based, Resolution=3842026.02 | 85 | 85.2 | 90 | — | — | |
| ODTrackResolution=384, Model Size=Base2024.12 | 84.9 | 85.1 | 90.1 | — | — | |
| ODTrack-B384Train=Seq, Temp.=32025.05 | 84.9 | 85.1 | 90.1 | — | — | |
| ODTrack-B384Multi Modal=false2026.05 | 84.9 | 85.1 | 90.1 | — | — | |
| ODTrackSource=AAAI24, Supervised=✓2026.05 | 84.9 | 85.1 | 90.1 | — | — | |
| ARTrackSource=CVPR23, Supervised=✓2026.05 | 84.8 | 85.1 | 89.1 | — | — | |
| UNINEXTBackbone=ConvNeXt-L2023.03 | 84.7 | 85.1 | 88.2 | — | — | |
| UNINEXT2024.03 | 84.7 | — | 88.2 | 85.1 | — | |
| ARTrackV2Resolution=256, Model Size=Base2024.12 | 84.5 | 84.9 | 89.3 | — | — | |
| TATrackResolution=384, Model Size=Large2024.12 | 84.5 | 85 | 89.3 | — | — | |
| ARTrackV2-B256Train=Seq, Temp.=22025.05 | 84.5 | 84.9 | 89.3 | — | — | |
| ARTrackV2-256Multi Modal=false2026.05 | 84.5 | 84.9 | 89.3 | — | — | |
| LoRAT-L224Model Scale=Large, Input Resolution=2242026.05 | 84.4 | 85 | 89.5 | — | — | |
| AQATrackSource=CVPR24, Supervised=✓2026.05 | 84.3 | 84.8 | 89.3 | — | — | |
| CiteTrackerResolution=384, Model Size=Base2024.12 | 84.2 | 84.5 | 89 | — | — | |
| GRMResolution=320, Model Size=Large2024.12 | 84 | 84.4 | 88.9 | — | — | |
| ProContEXTPre-training=MAE-ImageNet-1k, Dynamic Template=true, Extra Branch=false2022.10 | 83.8 | 84.6 | — | — | 89.2 | |
| OSTrack-B384 + MPTTrain=Frame, Temp.=12025.05 | 83.8 | 84.6 | 89.1 | — | — | |
| HIPTrackSource=CVPR24, Supervised=✓2026.05 | 83.8 | 84.5 | 89.1 | — | — | |
| ROMTrack-384Architecture=Transformer-based, Resolution=3842026.02 | 83.7 | 84.1 | 89 | — | — | |
| MixViT (ConvMAE)Train=Frame, Temp.=22025.05 | 83.7 | 84.5 | 89.1 | — | — | |
| ROMTrack-B384Train=Frame, Temp.=22025.05 | 83.7 | 84.1 | 89 | — | — | |
| SeqTrackBackbone=ViT-B2023.03 | 83.6 | 83.9 | 88.8 | — | — | |
| RFGM-B256Search Resolution=256x2562024.02 | 83.6 | 84.7 | 89.6 | — | — | |
| SeqTrack-BResolution=384x384, GPU Speed (fps)=15, Temporal Context=true2024.05 | 83.6 | — | — | 83.9 | — | |
| SeqTrack-B384Architecture=Transformer-based, Resolution=3842026.02 | 83.6 | 83.9 | 88.8 | — | — | |
| SeqTrackSource=CVPR23, Supervised=✓2026.05 | 83.6 | 83.9 | 88.8 | — | — | |
| MixViTResolution=288, Model Size=Base2024.12 | 83.5 | 83.5 | 88.3 | — | — | |
| CTTrackResolution=320, Model Size=Large2024.12 | 83.5 | 84.9 | 89.1 | — | — | |
| ARTrack2024.03 | 83.5 | — | 88.7 | 84.2 | — | |
| ARTrack-256Evaluation Regime=Non-real-time, Speed (fps) GPU=39, Speed (fps) CPU=3, Speed (fps) AGX=62026.03 | 83.5 | 84.2 | 88.7 | — | — | |
| ARTrack-B256Train=Seq, Temp.=12025.05 | 83.5 | 84.2 | 88.7 | — | — | |
| ARTrack-B256Model Scale=Base, Input Resolution=2562026.05 | 83.5 | 84.2 | 88.7 | — | — | |
| UNINEXTBackbone=ResNet-502023.03 | 83.3 | 83.2 | 86.9 | — | — | |
| OSTrack-384Input Resolution=384x3842022.03 | 83.2 | 83.9 | 88.5 | — | — | |
| OSTrackPre-training=MAE [17]2021.12 | 83.2 | — | — | 83.9 | — | |
| OSTrackPre-training=MAE-ImageNet-1k, Dynamic Template=false, Extra Branch=false2022.10 | 83.2 | 83.9 | — | — | 88.5 | |
| OSTrackBackbone=ViT-B2023.03 | 83.2 | 83.9 | 88.5 | — | — | |
| OSTrack-384Variant Type=Performance-oriented2024.01 | 83.2 | 83.9 | — | — | — | |
| OSTrack-384Search Resolution=384x3842024.02 | 83.2 | 83.9 | 88.5 | — | — | |
| OSTrack-CE-384Resolution=384x384, GPU Speed (fps)=812024.05 | 83.2 | — | — | 83.9 | — | |
| OSTrack-384Architecture=Transformer-based, Resolution=3842026.02 | 83.2 | 83.9 | 88.5 | — | — | |
| OmniViD2024.03 | 83.2 | — | 88.9 | 83.8 | — | |
| ARTrack-B256 + MPTTrain=Frame, Temp.=12025.05 | 83.2 | 84.2 | 88.9 | — | — | |
| OSTrackSource=ECCV22, Supervised=✓2026.05 | 83.2 | 83.9 | 88.5 | — | — | |
| MixFormer-LPre-trained=ImageNet-22k, Backbone=Large2022.03 | 83.1 | 83.9 | 88.9 | — | — | |
| MixFormerPre-training=ImageNet-22k2021.12 | 83.1 | — | — | 83.9 | — | |
| MixFormer-LVariant Type=Performance-oriented2024.01 | 83.1 | 83.9 | — | — | — | |
| Mixformer-LSearch Resolution=> 300x3002024.02 | 83.1 | 83.9 | 88.9 | — | — | |
| AQATrackResolution=256, Model Size=Base2024.12 | 83.1 | 83.8 | 88.6 | — | — | |
| VideoTrackResolution=256, Model Size=Base2024.12 | 83.1 | 83.8 | 88.7 | — | — | |
| VideoTrackArchitecture=Transformer-based2026.02 | 83.1 | 83.8 | 88.7 | — | — | |
| MixFormer-LTrain=Frame, Temp.=22025.05 | 83.1 | 83.9 | 88.9 | — | — |