Visual Object Tracking on GOT-10k
84.7AOProContEXT
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| ProContEXTPre-training=MAE-ImageNet-1k, Dynamic Template=true, Extra Branch=false2022.10 | 84.7 | — | 74.6 | 72.9 | — | |
| SUMO-LSource=Ours, Model Size=L2026.06 | 83.5 | — | 95.5 | 83.9 | — | |
| OSTrackPre-training=MAE-ImageNet-1k, Dynamic Template=false, Extra Branch=false2022.10 | 83.2 | — | 73.7 | 70.8 | — | |
| ProContEXTPre-training=CLS-ImageNet-1k, Dynamic Template=true, Extra Branch=false2022.10 | 82.7 | — | 72 | 68 | — | |
| SAMURAI-LSource=ArXiv’25, Model Size=L2026.06 | 82.7 | — | 94.5 | 83.4 | — | |
| ProContEXTPre-training=CLS-ImageNet-22k, Dynamic Template=true, Extra Branch=false2022.10 | 82.6 | — | 72.5 | 69.3 | — | |
| SUMO-SSource=Ours, Model Size=S2026.06 | 82.5 | — | 93.2 | 81.2 | — | |
| SUMO-BSource=Ours, Model Size=B2026.06 | 82 | — | 93 | 80.2 | — | |
| RELO-L256Model Scale=Large, Input Resolution=2562026.05 | 81.8 | — | 91.1 | 83.5 | — | |
| SAMURAIYear=20262026.02 | 81.7 | — | — | — | — | |
| SAMURAIYear=20262026.02 | 81.7 | — | — | — | — | |
| SAMURAIYear=2026, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 81.7 | — | — | — | — | |
| SUTrackResolution=384, Model Size=Large2024.12 | 81.5 | — | 89.5 | 83.3 | — | |
| SUTrack-LPublication=[AAAI’25]2026.03 | 81.5 | — | — | — | — | |
| SUTrack-L384Multi Modal=true2026.05 | 81.5 | — | 89.5 | 83.3 | — | |
| ARPTrack-L384Multi Modal=false2026.05 | 81.5 | — | 90.6 | 80.5 | — | |
| ARPTrack-L384Model Scale=Large, Input Resolution=3842026.05 | 81.5 | — | 90.6 | 80.5 | — | |
| ARPTrack-384Semantic Feature=ViT-ARP-L, Training Data of Tracker=Base+VastTrack+K700, Frames=7, Trainable Parameters=405M2026.07 | 81.5 | — | — | 80.5 | — | |
| OneTrackerV2-L384Multi Modal=true2026.05 | 81.3 | — | 91.8 | 83.9 | — | |
| SAM2LongModel=SAM2.1-L2024.10 | 81.1 | — | — | — | — | |
| SUTrackResolution=224, Model Size=Large2024.12 | 81 | — | 90.4 | 82.4 | — | |
| SUTrack-L224Multi Modal=true2026.05 | 81 | — | 90.4 | 82.4 | — | |
| SUTrack-L224Model Scale=Large, Input Resolution=2242026.05 | 81 | — | 90.4 | 82.4 | — | |
| SAM 2Model=SAM2.1-L2024.10 | 80.7 | — | — | — | — | |
| OneTrackerV2-L224Multi Modal=true2026.05 | 80.5 | — | 90.2 | 82.7 | — | |
| RELO-B256Model Scale=Base, Input Resolution=2562026.05 | 80.5 | — | 90.5 | 81.2 | — | |
| MITS2024.03 | 80.4 | — | 89.7 | 75.9 | — | |
| GOT-Edit-378Semantic Feature=DINOv2-L, Geometry Feature=VGGT, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=53M2026.07 | 80.2 | — | — | 79.8 | — | |
| MixFormerPre-training=CLS-ImageNet-22k, Dynamic Template=true, Extra Branch=true2022.10 | 80 | — | 70.7 | 67.8 | — | |
| SPMTrack-L384Multi Modal=false2026.05 | 80 | — | 89.4 | 79.9 | — | |
| MCITrack-384Semantic Feature=Fast-iTPN-L, Training Data of Tracker=Base+VastTrack, Frames=5, Trainable Parameters=287M2026.07 | 80 | — | — | 80.2 | — | |
| MixFormerPre-training=CLS-ImageNet-1k, Dynamic Template=true, Extra Branch=true2022.10 | 79.9 | — | 71.2 | 65.8 | — | |
| GOT-JEPAYear=20252026.02 | 79.6 | — | — | — | — | |
| GOT-JEPAGOT-10k Guidelines=true2026.02 | 79.6 | — | — | — | — | |
| OneTrackerV2-B384Multi Modal=true2026.05 | 79.6 | — | 89.4 | 81.3 | — | |
| GOT-JEPAVariant=Highest-resolution (ViT-L prioritized)2026.07 | 79.6 | — | — | — | — | |
| ARTrackV2Resolution=384, Model Size=Large2024.12 | 79.5 | — | 87.8 | 79.6 | — | |
| ARTrackv2Year=20242026.02 | 79.5 | — | — | — | — | |
| ARTrackv2Year=20242026.02 | 79.5 | — | — | — | — | |
| ARTrackV2-L384Multi Modal=false2026.05 | 79.5 | — | 87.8 | 79.6 | — | |
| ARTrackV2-L384Model Scale=Large, Input Resolution=3842026.05 | 79.5 | — | 87.8 | 79.6 | — | |
| GOT-Edit-378Semantic Feature=DINOv2-L, Geometry Feature=DA3-L, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=28M2026.07 | 79.5 | — | — | 79.6 | — | |
| ARTrackv2Year=2024, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 79.5 | — | — | — | — | |
| SUTrackResolution=384, Model Size=Base2024.12 | 79.3 | — | 88 | 80 | — | |
| SUTrack-BPublication=[AAAI’25]2026.03 | 79.3 | — | — | — | — | |
| SUTrack-B384Multi Modal=true2026.05 | 79.3 | — | 88 | 80 | — | |
| SimTrackPre-training=CLIP-WIT, Dynamic Template=false, Extra Branch=false2022.10 | 78.9 | — | 68.6 | 62.4 | — | |
| ARTrackResolution=384, Model Size=Large2024.12 | 78.5 | — | 87.4 | 77.8 | — | |
| ARTrackModel size=Large2024.03 | 78.5 | — | 87.4 | 77.8 | — | |
| OneTrackerV2-B224Multi Modal=true2026.05 | 78.4 | — | 87.8 | 79.6 | — | |
| ODTrack2024.10 | 78.2 | — | — | — | — | |
| LORAT2024.10 | 78.2 | — | — | — | — | |
| ODTrackResolution=384, Model Size=Large2024.12 | 78.2 | — | 87.2 | 77.3 | — | |
| ODTrack-LPublication=[AAAI’24]2026.03 | 78.2 | — | — | — | — | |
| ODTrack-L384Multi Modal=false2026.05 | 78.2 | — | 87.2 | 77.3 | — | |
| ODTrack-L384Model Scale=Large, Input Resolution=3842026.05 | 78.2 | — | 87.2 | 77.3 | — | |
| STARKPre-training=CLS-ImageNet-1k, Dynamic Template=true, Extra Branch=true2022.10 | 78.1 | — | 68.8 | 64.1 | — | |
| SUTrackResolution=224, Model Size=Base2024.12 | 77.9 | — | 87.5 | 78.5 | — | |
| DeTrackResolution=384, Training Data=GOT-10k only2025.01 | 77.9 | — | 86.5 | 74.9 | — | |
| RTrackerModel size=Large, Backbone=ViT-Large2024.03 | 77.9 | — | 87 | 76.9 | — | |
| MCITrack-B224Evaluation Regime=Non-real-time, Speed (fps) GPU=34, Speed (fps) CPU=2, Speed (fps) AGX=62026.03 | 77.9 | — | 88.2 | 76.8 | — | |
| SUTrack-B224Evaluation Regime=Non-real-time, Speed (fps) GPU=55, Speed (fps) CPU=6, Speed (fps) AGX=132026.03 | 77.9 | — | 87.5 | 78.5 | — | |
| SUTrack-B224Multi Modal=true2026.05 | 77.9 | — | 87.5 | 78.5 | — | |
| MCITrackSource=AAAI25, Supervised=✓2026.05 | 77.9 | — | 88.2 | 76.8 | — | |
| SUTrack-B224Model Scale=Base, Input Resolution=2242026.05 | 77.9 | — | 87.5 | 78.5 | — | |
| DeTrack-384Semantic Feature=Denoising ViT, Training Data of Tracker=Base, Frames=32026.07 | 77.9 | — | — | 74.9 | — | |
| ARPTrack-B256Multi Modal=false2026.05 | 77.7 | — | 87.3 | 74.3 | — | |
| ARPTrackSource=CVPR25, Supervised=✓2026.05 | 77.7 | — | 87.3 | 74.3 | — | |
| ARPTrack-B256Model Scale=Base, Input Resolution=2562026.05 | 77.7 | — | 87.3 | 74.3 | — | |
| LORATResolution=378, Model Size=Large2024.12 | 77.5 | — | 86.2 | 78.1 | — | |
| LoRATYear=20242026.02 | 77.5 | — | — | — | — | |
| LoRATYear=20242026.02 | 77.5 | — | — | — | — | |
| LORAT-LPublication=[ECCV’24]2026.03 | 77.5 | — | — | — | — | |
| LoRAT-L378Multi Modal=false2026.05 | 77.5 | — | 86.2 | 78.1 | — | |
| ARTrackV2Source=CVPR24, Supervised=✓2026.05 | 77.5 | — | 86 | 75.5 | — | |
| DreamTrackSource=CVPR25, Supervised=✓2026.05 | 77.5 | — | 87.1 | 74.2 | — | |
| LoRAT-378Semantic Feature=DINOv2-L, Training Data of Tracker=Base, Frames=3, Trainable Parameters=32M2026.07 | 77.5 | — | — | 78.1 | — | |
| ToMP-378 (Reproduced)Semantic Feature=DINOv2-L, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=25M2026.07 | 77.5 | — | — | 75.8 | — | |
| LoRATYear=2024, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 77.5 | — | — | — | — | |
| HIPTrackSource=CVPR24, Supervised=✓2026.05 | 77.4 | — | 88 | 74.5 | — | |
| DeTrackResolution=256, Training Data=GOT-10k only2025.01 | 77.1 | — | 86.1 | 73.5 | — | |
| ODTrackResolution=384, Model Size=Base2024.12 | 77 | — | 87.9 | 75.1 | — | |
| ODTrack-BPublication=[AAAI’24]2026.03 | 77 | — | — | — | — | |
| ODTrack-B384Multi Modal=false2026.05 | 77 | — | 87.9 | 75.1 | — | |
| ODTrackSource=AAAI24, Supervised=✓2026.05 | 77 | — | 87.9 | 75.1 | — | |
| ODTrack-B384Source=AAAI’24, Resolution=3842026.06 | 77 | — | 87.9 | 75.1 | — | |
| PiVOTYear=20252026.02 | 76.9 | — | — | — | — | |
| PiVOTYear=20252026.02 | 76.9 | — | — | — | — | |
| PiVOT-378Semantic Feature=DINOv2-L, Training Data of Tracker=Base, Frames=3, Trainable Parameters=34M2026.07 | 76.9 | — | — | 75.5 | — | |
| PiVOT-L-27Venue=-2026.07 | 76.9 | — | 87.6 | 75.5 | — | |
| PiVOTYear=2025, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 76.9 | — | — | — | — | |
| TransTPre-training=CLS-ImageNet-1k, Dynamic Template=false, Extra Branch=false2022.10 | 76.8 | — | 67.1 | 60.9 | — | |
| EVPTrack-B384Source=AAAI’24, Resolution=3842026.06 | 76.6 | — | 86.7 | 73.9 | — | |
| SPMTrack-B384Multi Modal=false2026.05 | 76.5 | — | 85.9 | 76.3 | — | |
| GOT-Edit-252Semantic Feature=DINOv2-L, Geometry Feature=DA3-L, Training Data of Tracker=Base+VastTrack, Frames=3, Trainable Parameters=51M2026.07 | 76.4 | — | — | 75.8 | — | |
| LMTrackSource=AAAI25, Supervised=✓2026.05 | 76.3 | — | 87.1 | 73.9 | — | |
| MGTrackYear=20252026.02 | 76.2 | — | — | — | — | |
| MGTrackYear=20252026.02 | 76.2 | — | — | — | — | |
| MGTrackYear=2025, Variant=Highest-resolution (ViT-L prioritized)2026.07 | 76.2 | — | — | — | — | |
| AQATrack-BPublication=[CVPR’24]2026.03 | 76 | — | — | — | — |