Single Object Tracking on TrackingNet
91.9PnormSENTRY-S2-L
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SENTRY-S2-LMethod Type=Zero-shot Method, Model Scale=L2026.06 | 91.9 | 85.7 | 88.9 | — | |
| SENTRY-D4S-LMethod Type=Zero-shot Method, Model Scale=L2026.06 | 91.5 | 85.9 | 87.9 | — | |
| SAM2-LMethod Type=Zero-shot Method, Model Scale=L2026.06 | 91.3 | 85.3 | 88.2 | — | |
| SENTRY-SR-LMethod Type=Zero-shot Method, Model Scale=L2026.06 | 91.1 | 85.8 | 88.1 | — | |
| ODTrack-LSize=Large2023.03 | 91 | 86.1 | 86.7 | — | |
| SPMTrack-LSource=CVPR252026.04 | 91 | — | — | 86.9 | |
| DAM4SAM-LMethod Type=Zero-shot Method, Model Scale=L2026.06 | 90.9 | 85.3 | 87.4 | — | |
| DTPTrackSource=Ours, Backbone scale=L, Input resolution=3782026.04 | 90.8 | — | — | 86.9 | |
| DreamTrackResolution=3842025.10 | 90.6 | — | 85.9 | 86.5 | |
| ARTrackV2-LSize=Large2023.03 | 90.4 | 86.1 | 86.2 | — | |
| ARTrackV2Source=CVPR24, Backbone scale=L, Input resolution=3842026.04 | 90.4 | — | — | 86.1 | |
| SUTrackResolution=2242025.10 | 90.3 | — | 85.1 | 85.7 | |
| LoRATSource=ECCV24, Backbone scale=g, Input resolution=3782026.04 | 90.2 | — | — | 86 | |
| SPMTrack-BMethod Type=Vision-Based, Model Scale=B2026.06 | 90.2 | 86.1 | 85.6 | — | |
| DTPTrackSource=Ours, Backbone scale=B, Input resolution=2242026.04 | 90.1 | — | — | 85.6 | |
| ODTrack-BSource=AAAI242026.04 | 90.1 | — | — | 85.1 | |
| SAM 2++2025.10 | 90.1 | — | 87.3 | 86 | |
| DreamTrackResolution=2562025.10 | 90 | — | 85.3 | 85.8 | |
| ARPTrack256Method Type=Vision-Based, Input Resolution=2562026.06 | 90 | 85.5 | 85.3 | — | |
| ARTrackV2Source=CVPR24, Backbone scale=B, Input resolution=3842026.04 | 89.8 | — | — | 85.7 | |
| ARTrack-V2Resolution=3842025.10 | 89.8 | — | 85.5 | 85.7 | |
| LoRATSource=ECCV24, Backbone scale=L, Input resolution=3782026.04 | 89.7 | — | — | 85.6 | |
| CLDTrackerMethod Type=VLM2026.06 | 89.7 | 85.1 | 84.9 | — | |
| ARTrack-LSize=Large2023.03 | 89.6 | 85.6 | 86 | — | |
| ARTrackSource=CVPR23, Backbone scale=L, Input resolution=3842026.04 | 89.6 | — | — | 85.6 | |
| SeqTrack-LSize=Large2023.03 | 89.5 | 85 | 84.9 | — | |
| LoRAT-LSize=Large2023.03 | 89.5 | 85 | 84.4 | — | |
| TATrack-LSize=Large2023.03 | 89.3 | 85 | 84.5 | — | |
| AQATrackSource=CVPR24, Input resolution=3842026.04 | 89.3 | — | — | 84.8 | |
| HIPTrackResolution=3842025.10 | 89.2 | — | 83.7 | 84.5 | |
| HIPTrackSource=CVPR242026.04 | 89.1 | — | — | 84.5 | |
| HIPTrackMethod Type=Vision-Based2026.06 | 89.1 | 84.5 | 83.8 | — | |
| ROMTrackSource=ICCV23, Input resolution=3842026.04 | 89 | — | — | 84.1 | |
| SeqTrackResolution=3842025.10 | 89 | — | 83.7 | 84 | |
| MixFormer-LSize=Large2023.03 | 88.9 | — | 83.1 | — | |
| OmniVid2023.03 | 88.9 | 83.8 | 83.2 | — | |
| DropTrack2023.03 | 88.9 | 84.1 | — | — | |
| GRM-LSize=Large2023.03 | 88.9 | 84.4 | 84 | — | |
| DropTrackSource=CVPR23, Input resolution=3842026.04 | 88.9 | — | — | 84.1 | |
| SeqTrackSource=CVPR23, Backbone scale=B, Input resolution=3842026.04 | 88.8 | — | — | 83.9 | |
| ARTrackResolution=2562025.10 | 88.8 | — | 83.5 | 84.4 | |
| ARTrack-V2Resolution=2562025.10 | 88.8 | — | 83.4 | 84.2 | |
| GRMSource=CVPR232026.04 | 88.7 | — | — | 84 | |
| MixViTConvMAEResolution=2882025.10 | 88.6 | — | 82.8 | 83.7 | |
| AQATrack256Method Type=Vision-Based, Input Resolution=2562026.06 | 88.6 | 83.8 | 83.1 | — | |
| OSTrackSource=ECCV22, Input resolution=3842026.04 | 88.5 | — | — | 83.9 | |
| OSTrackResolution=3842025.10 | 88.5 | — | 83.2 | 83.8 | |
| DropTrackResolution=3842025.10 | 88.5 | — | 83.1 | 83.8 | |
| GRMResolution=2562025.10 | 88.5 | — | 83.1 | 83.8 | |
| ROMTrackResolution=3842025.10 | 88.5 | — | 83.1 | 83.8 | |
| LoRATResolution=3782025.10 | 88.5 | — | 83.2 | 84.3 | |
| LoRATSource=ECCV24, Backbone scale=B, Input resolution=3782026.04 | 88.4 | — | — | 84.2 | |
| ROMTrackResolution=2562025.10 | 88.4 | — | 82.8 | 83.7 | |
| TATrack-BSource=AAAI232026.04 | 88.3 | — | — | 83.5 | |
| SeqTrackResolution=2562025.10 | 88.3 | — | 82.3 | 83.2 | |
| UNINEXT-LBackbone=Swin-Large2023.03 | 88.2 | 85.1 | 84.7 | — | |
| DiffusionTrackMethod Type=Vision-Based2026.06 | 88.2 | 83.8 | 82.1 | — | |
| SAMURAI-LMethod Type=Zero-shot Method, Model Scale=L2026.06 | 88.2 | 85.3 | 85 | — | |
| HIPTrack-LSize=Large2023.03 | 88 | 77.4 | 74.5 | — | |
| LoRATResolution=2242025.10 | 88 | — | 82.2 | 83.6 | |
| AiATrack2023.03 | 87.8 | — | 80.4 | — | |
| OSTrack2023.03 | 87.8 | — | 82 | — | |
| AiATrackSource=ECCV222026.04 | 87.8 | — | — | 82.7 | |
| OSTrackResolution=2562025.10 | 87.8 | — | 81.9 | 83.1 | |
| SimTrack-LSize=Large2023.03 | 87.4 | — | — | — | |
| SimTrackSource=ECCV222026.04 | 87.4 | — | — | 83.4 | |
| STARK2023.03 | 86.9 | 82 | — | — | |
| TransT2023.03 | 86.7 | 81.4 | 80.3 | — | |
| OmniTracker-LBackbone=Swin-Large2023.03 | 86.7 | 83.4 | 82.3 | — | |
| SimTrackResolution=2242025.10 | 86.7 | — | 80.2 | 82.3 | |
| UNINEXT-L-noObjPreBackbone=Swin-Large, Pre-training=without Objects365, Box De-noising=disabled2023.03 | 86.6 | 83.2 | 82.3 | — | |
| Unicorn-LBackbone=Swin-Large2023.03 | 86.4 | 83 | 82.2 | — | |
| Siam R-CNN2023.03 | 85.4 | 81.2 | 80 | — | |
| TrDiMP2023.03 | 83.3 | 78.4 | 73.1 | — | |
| OmniTracker-TBackbone=Swin-Tiny2023.03 | 82.5 | 80.2 | 77.7 | — | |
| UNINEXT-T-noObjPreBackbone=Swin-Tiny, Pre-training=without Objects3652023.03 | 82.1 | 79.7 | 77.5 | — | |
| Unicorn-TBackbone=Swin-Tiny2023.03 | 82 | 79 | 77.4 | — | |
| PrDiMP2023.03 | 81.6 | 75.8 | 70.4 | — | |
| DiMP2023.03 | 80.1 | 74 | 68.7 | — | |
| SiamPRN++2023.03 | 80 | 73.3 | 69.4 | — | |
| KYS2023.03 | 80 | 74 | 68.8 | — | |
| ATOM2023.03 | 77.1 | 70.3 | 64.8 | — | |
| D3S2023.03 | 76.8 | 72.8 | 66.4 | — | |
| SiamFC2023.03 | 66.3 | 57.1 | 53.3 | — | |
| AutoMatch2023.03 | — | 76 | 72.6 | — | |
| LoRATv2Source=NIPS25, Backbone scale=B, Input resolution=2242026.04 | — | — | — | 84.1 | |
| LoRATv2Source=NIPS25, Backbone scale=L, Input resolution=3782026.04 | — | — | — | 85.7 | |
| SAMURAI2025.10 | — | — | — | 85.3 | |
| SwinTrack2023.03 | — | 81.1 | 78.4 | — | |
| UTT2023.03 | — | 79.7 | 77 | — | |
| UVLTrack-BMethod Type=VLM, Model Scale=B2026.06 | — | 83.4 | 82.1 | — |