Visual Object Tracking on TrackingNet (test)
92.1Normalized Precision (Pnorm)MCITrack-L384
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MCITrack-L384Input Resolution=384x3842024.12 | 92.1 | 87.9 | 89.2 | — | |
| SUTrackModel scale=Large, Input resolution=3842024.12 | 91.7 | 87.7 | 88.7 | — | |
| ETCTrack-B384Resolution=3842026.05 | 91.7 | 87.3 | 88.2 | — | |
| SAMOSA2026.05 | 91.43 | — | 88.31 | 85.55 | |
| SAM2Long2026.05 | 91.41 | — | 88.42 | 85.42 | |
| SAM 2.12026.05 | 91.4 | — | 88.37 | 85.41 | |
| HiM2SAM2026.05 | 91.4 | — | 88.25 | 85.4 | |
| SAMITE2026.05 | 91.38 | — | 88.08 | 85.22 | |
| SAMURAI2026.05 | 91.34 | — | 88.33 | 85.39 | |
| MCITrack-L224Input Resolution=224x2242024.12 | 91.3 | 86.9 | 87.4 | — | |
| SAM2.1++2026.05 | 91.25 | — | 87.76 | 84.78 | |
| SeC2026.05 | 91.23 | — | 88.05 | 85.27 | |
| ODTrack-L2024.01 | 91 | 86.1 | 86.7 | — | |
| ODTrack-L384Input Resolution=384x3842024.12 | 91 | 86.1 | 86.7 | — | |
| ODTrackModel scale=Large, Input resolution=3842024.12 | 91 | 86.1 | 86.7 | — | |
| MCITrack-B224†Resolution=2242026.05 | 91 | 86.4 | 86.3 | — | |
| ODTrack-L2026.05 | 91 | — | 86.7 | 86.1 | |
| SAM 22026.05 | 90.99 | — | 87.8 | 84.94 | |
| MCITrack-B224Input Resolution=224x2242024.12 | 90.9 | 86.3 | 86.1 | — | |
| SUTrackModel scale=Large, Input resolution=2242024.12 | 90.9 | 86.5 | 86.7 | — | |
| SUTrackModel scale=Base, Input resolution=3842024.12 | 90.7 | 86.5 | 86.8 | — | |
| ETCTrack-B224Resolution=2242026.05 | 90.6 | 86 | 85.6 | — | |
| DreamTrack-B384Resolution=3842026.05 | 90.6 | 86.5 | 85.9 | — | |
| ARTrackV2-L384Input Resolution=384x3842024.12 | 90.4 | 86.1 | 86.2 | — | |
| ARTrackV2Model scale=Large, Input resolution=3842024.12 | 90.4 | 86.1 | 86.2 | — | |
| ARTrackV2-L3842026.05 | 90.4 | — | 86.2 | 86.1 | |
| MixViT-L (ConvMAE)Backbone=MixViT-L, Pre-training=ConvMAE2023.02 | 90.3 | 86.1 | 86 | — | |
| ChatTracker-Lvisual tracker=MixFormer2024.11 | 90.3 | 86.1 | 86 | — | |
| SUTrackModel scale=Base, Input resolution=2242024.12 | 90.3 | 85.7 | 85.1 | — | |
| MixViT-LBackbone=MixViT-L, Pre-training=MAE2023.02 | 90.2 | 85.4 | 85.7 | — | |
| MCITrack-S224Input Resolution=224x2242024.12 | 90.2 | 85.6 | 85.2 | — | |
| MixViT-L384Input Resolution=384x3842024.12 | 90.2 | 85.4 | 85.7 | — | |
| MixViTModel scale=Large, Input resolution=3842024.12 | 90.2 | 85.4 | 85.7 | — | |
| SPMTrack-B384Resolution=3842026.05 | 90.2 | 86.1 | 85.6 | — | |
| ODTrack-B2024.01 | 90.1 | 85.1 | 84.9 | — | |
| ODTrack-B384Input Resolution=384x3842024.12 | 90.1 | 85.1 | 84.9 | — | |
| ODTrackModel scale=Base, Input resolution=3842024.12 | 90.1 | 85.1 | 84.9 | — | |
| ETCTrack-S224Resolution=2242026.05 | 90.1 | 85.4 | 84.8 | — | |
| ODTrack-B384Resolution=3842026.05 | 90.1 | 85.1 | 84.9 | — | |
| PiVOT-L-272024.09 | 90 | — | 85.3 | 85.3 | |
| DreamTrack-B256Resolution=2562026.05 | 90 | 85.8 | 85.3 | — | |
| ARPTrack-B256Resolution=2562026.05 | 90 | 85.5 | 85.3 | — | |
| SeqTrack-L384Architecture Category=Seq2Seq, Backbone=ViT-Large, Input Resolution=384x3842023.04 | 89.8 | 85.5 | 85.8 | — | |
| SeqTrack-L3842024.11 | 89.8 | 85.5 | 85.8 | — | |
| SeqTrack-L384Input Resolution=384x3842024.12 | 89.8 | 85.5 | 85.8 | — | |
| ARTrackV2Input resolution=3842024.12 | 89.8 | 85.7 | 85.5 | — | |
| SeqTrackModel scale=Large, Input resolution=3842024.12 | 89.8 | 85.5 | 85.8 | — | |
| SeqTrack-LVenue=CVPR232024.09 | 89.8 | — | 85.8 | 85.5 | |
| ARTrackV2-B384Resolution=3842026.05 | 89.8 | 85.7 | 85.5 | — | |
| SeqTrack-L3842026.05 | 89.8 | — | 85.8 | 85.5 | |
| LoRAT-L378Input Resolution=378x3782024.12 | 89.7 | 85.6 | 85.4 | — | |
| LORATModel scale=Large, Input resolution=3782024.12 | 89.7 | 85.6 | 85.4 | — | |
| LoRAT-L3782026.05 | 89.7 | — | 85.4 | 85.6 | |
| RFGM-B256Search Resolution=256x256, Backbone=ViT-B2024.02 | 89.6 | 84.7 | 83.6 | — | |
| RGFM-B2562024.11 | 89.6 | 84.7 | 83.6 | — | |
| ARTrack-L384Input Resolution=384x3842024.12 | 89.6 | 85.6 | 86 | — | |
| ARTrackModel scale=Large, Input resolution=3842024.12 | 89.6 | 85.6 | 86 | — | |
| SeqTrack-L256Architecture Category=Seq2Seq, Backbone=ViT-Large, Input Resolution=256x2562023.04 | 89.5 | 85 | 84.9 | — | |
| MCITrack-T224Input Resolution=224x2242024.12 | 89.4 | 84.8 | 83.7 | — | |
| TATrack-LPublished=Ours2023.02 | 89.3 | 85 | 84.5 | — | |
| AQATrack-384Resolution=3842024.03 | 89.3 | 84.8 | 85.3 | — | |
| ARTrackV2-256Input Resolution=256x2562024.12 | 89.3 | 84.9 | 84.5 | — | |
| TATrack-L384Input Resolution=384x3842024.12 | 89.3 | 85 | 84.5 | — | |
| TATrackModel scale=Large, Input resolution=3842024.12 | 89.3 | 85 | 84.5 | — | |
| ETCTrack-T224Resolution=2242026.05 | 89.3 | 84.6 | 83.2 | — | |
| ARTrackV2-B256Resolution=2562026.05 | 89.3 | 84.9 | 84.5 | — | |
| TemTrack-B384Resolution=3842026.05 | 89.3 | 85 | 84.8 | — | |
| PiVOT-L-222024.09 | 89.2 | — | 83.9 | 84.3 | |
| MixViT (ConvMAE)Backbone=MixViT, Pre-training=ConvMAE2023.02 | 89.1 | 84.5 | 83.7 | — | |
| ARTrack2024.01 | 89.1 | 85.1 | 84.8 | — | |
| ARTrack2024.03 | 89.1 | 85.1 | 83.6 | — | |
| ARTrack-3842024.11 | 89.1 | 85.1 | 84.8 | — | |
| CTTrack-L320Input Resolution=320x3202024.12 | 89.1 | 84.9 | 83.5 | — | |
| ARTrackInput resolution=3842024.12 | 89.1 | 85.1 | 84.8 | — | |
| CTTrackModel scale=Large, Input resolution=3202024.12 | 89.1 | 84.9 | 83.5 | — | |
| CTTrack-LVenue=AAAI232024.09 | 89.1 | — | 83.5 | 84.9 | |
| HIPTrack-B384Resolution=3842026.05 | 89.1 | 84.5 | 83.8 | — | |
| HIPTrack2026.05 | 89.1 | — | 83.8 | 84.5 | |
| F-BDMTrack-3842024.11 | 89 | 84.5 | 84 | — | |
| ROMTrack-384Input Resolution=384x3842024.12 | 89 | 84.1 | 83.7 | — | |
| CiteTracker-384Input Resolution=384x3842024.12 | 89 | 84.5 | 84.2 | — | |
| ROMTrackInput resolution=3842024.12 | 89 | 84.1 | 83.7 | — | |
| CiteTrackerInput resolution=3842024.12 | 89 | 84.5 | 84.2 | — | |
| ROMTrack-384Venue=ICCV232024.09 | 89 | — | 83.7 | 84.1 | |
| F-BDMTrack-384Resolution=3842026.05 | 89 | 84.5 | 84 | — | |
| ROMTrack3842026.05 | 89 | — | 83.7 | 84.1 | |
| MixCvT-LBackbone=MixCvT-L, Pre-training=ImageNet-22k2023.02 | 88.9 | 83.9 | 83.1 | — | |
| Mixformer-LArchitecture Category=Corner Prediction, Backbone=ViT-Large2023.04 | 88.9 | 83.9 | 83.1 | — | |
| MITS2024.11 | 88.9 | 83.4 | 84.6 | — | |
| DropTrack2024.11 | 88.9 | 84.1 | — | — | |
| GRMModel scale=Large, Input resolution=3202024.12 | 88.9 | 84.4 | 84 | — | |
| MixformerModel scale=Large, Input resolution=3202024.12 | 88.9 | 83.9 | 83.1 | — | |
| MixFormer-LVenue=CVPR222024.09 | 88.9 | — | 83.1 | 83.9 | |
| DropTrack2023.04 | 88.9 | 84.1 | — | — | |
| SeqTrack2024.01 | 88.8 | 83.9 | 83.6 | — | |
| SeqTrack-B384Architecture Category=Seq2Seq, Backbone=ViT-Base, Input Resolution=384x3842023.04 | 88.8 | 83.9 | 83.6 | — | |
| SeqTrack2024.03 | 88.8 | 83.9 | 82.6 | — | |
| SeqTrackModel scale=Base, Input resolution=3842024.12 | 88.8 | 83.9 | 83.6 | — | |
| TemTrack-B256Resolution=2562026.05 | 88.8 | 84.3 | 83.5 | — | |
| GRM2023.03 | 88.7 | 84 | 83.3 | — |