Visual Object Tracking on LaSoText
64.1AUCEdgeDAM
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| EdgeDAM2026.03 | 64.1 | — | — | — | |
| SAM2LongModel=SAM2.1-L2024.10 | 60.9 | — | — | — | |
| SAM2.1++2026.03 | 60.9 | — | — | — | |
| RELO-L256Model Scale=Large, Input Resolution=2562026.05 | 57.5 | 69.1 | 66.7 | — | |
| SAM 2Model=SAM2.1-L2024.10 | 56.9 | — | — | — | |
| SAM2.12026.03 | 56.9 | — | — | — | |
| LORAT2024.10 | 56.6 | — | — | — | |
| Alpha-RefineResolution=2882025.01 | 56.6 | — | — | — | |
| LORAT2026.03 | 56.6 | — | — | — | |
| MCITrack-B224Evaluation Regime=Non-real-time, Speed (fps) GPU=34, Speed (fps) CPU=2, Speed (fps) AGX=62026.03 | 54.6 | 65.7 | 62.1 | — | |
| MCITrackSource=AAAI25, Supervised=✓2026.05 | 54.6 | 65.7 | 62.1 | — | |
| RELO-B256Model Scale=Base, Input Resolution=2562026.05 | 54.2 | 65.4 | 62.2 | — | |
| ARPTrack-L384Model Scale=Large, Input Resolution=3842026.05 | 54.2 | 64.4 | 61.2 | — | |
| SUTrack-L224Model Scale=Large, Input Resolution=2242026.05 | 54 | 65.3 | 61.7 | — | |
| ODTrack2024.10 | 53.9 | — | — | — | |
| ODTrack-L2024.01 | 53.9 | 65.4 | 61.7 | — | |
| ODTrack2026.03 | 53.9 | — | — | — | |
| ODTrack-L384Model Scale=Large, Input Resolution=3842026.05 | 53.9 | 65.4 | 61.7 | — | |
| DeTrackResolution=3842025.01 | 53.6 | 64.4 | 60.4 | — | |
| ARTrackV2-L384Model Scale=Large, Input Resolution=3842026.05 | 53.4 | 63.7 | 60.2 | — | |
| SUTrack-B224Evaluation Regime=Non-real-time, Speed (fps) GPU=55, Speed (fps) CPU=6, Speed (fps) AGX=132026.03 | 53.1 | 64.2 | 60.5 | — | |
| LoRAT-B378Source=ECCV24, Supervised=✓2026.05 | 53.1 | 64.8 | 60.6 | — | |
| DreamTrackSource=CVPR25, Supervised=✓2026.05 | 53.1 | 64.1 | 59.8 | — | |
| SUTrack-B224Model Scale=Base, Input Resolution=2242026.05 | 53.1 | 64.2 | 60.5 | — | |
| ARTrackV2Source=CVPR24, Supervised=✓2026.05 | 52.9 | 63.4 | 59.1 | — | |
| LoRAT-L224Model Scale=Large, Input Resolution=2242026.05 | 52.8 | 64.7 | 60 | — | |
| DropTrack2024.10 | 52.7 | — | — | — | |
| DropTrack-B384TU=false2023.04 | 52.7 | 63.9 | 60.2 | — | |
| DropTrack2026.03 | 52.7 | — | — | — | |
| AQATrackSource=CVPR24, Supervised=✓2026.05 | 52.7 | 64.2 | 60.8 | — | |
| ODTrack-B2024.01 | 52.4 | 63.9 | 60.1 | — | |
| ODTrackSource=AAAI24, Supervised=✓2026.05 | 52.4 | 63.9 | 60.1 | — | |
| ARPTrackSource=CVPR25, Supervised=✓2026.05 | 52 | 62.9 | 58.7 | — | |
| ARPTrack-B256Model Scale=Base, Input Resolution=2562026.05 | 52 | 62.9 | 58.7 | — | |
| ARTrack2024.01 | 51.9 | 62 | 58.5 | — | |
| ARTrackResolution=3842025.01 | 51.9 | 62 | 58.5 | — | |
| ARTrack-B384TU=true2023.04 | 51.9 | 62 | 58.5 | — | |
| ARTrackSource=CVPR23, Supervised=✓2026.05 | 51.9 | 62 | 58.5 | — | |
| SMTrack-M384Architecture=SSM-based, Resolution=3842026.02 | 51.6 | 62.1 | 59 | — | |
| ROMTrack2024.10 | 51.3 | — | — | — | |
| ROMTrack-384Architecture=Transformer-based, Resolution=3842026.02 | 51.3 | 62.4 | 58.6 | — | |
| ROMTrack2026.03 | 51.3 | — | — | — | |
| UVLTrack-LVariant Type=Performance-oriented2024.01 | 51.2 | — | 59 | — | |
| F-BDMTrackResolution=3842025.01 | 50.8 | 61.3 | 57.8 | — | |
| SeqTrack2024.10 | 50.7 | — | — | — | |
| SeqTrack2026.03 | 50.7 | — | — | — | |
| MixFormerV2-BEvaluation Regime=Non-real-time, Speed (fps) GPU=116, Speed (fps) CPU=11, Speed (fps) AGX=162026.03 | 50.6 | — | 56.9 | — | |
| OSTrack2024.10 | 50.5 | — | — | — | |
| OSTrack-384Input Resolution=384x3842022.03 | 50.5 | 61.3 | 57.6 | — | |
| OSTrack2024.01 | 50.5 | 61.3 | 57.6 | — | |
| SeqTrack2024.01 | 50.5 | 61.6 | 57.5 | — | |
| OSTrack-384Variant Type=Performance-oriented2024.01 | 50.5 | — | 57.6 | — | |
| OSTrackResolution=3842025.01 | 50.5 | 61.3 | 57.6 | — | |
| SeqTrackResolution=3842025.01 | 50.5 | 61.6 | 57.5 | — | |
| SeqTrack-B384TU=true2023.04 | 50.5 | 61.6 | 57.5 | — | |
| OSTrack-384TU=false2023.04 | 50.5 | 61.3 | 57.6 | — | |
| SeqTrack-B384Architecture=Transformer-based, Resolution=3842026.02 | 50.5 | 61.6 | 57.5 | — | |
| OSTrack-384Architecture=Transformer-based, Resolution=3842026.02 | 50.5 | 61.3 | 57.6 | — | |
| OSTrack2026.03 | 50.5 | — | — | — | |
| OSTrackSource=ECCV22, Supervised=✓2026.05 | 50.5 | 61.3 | 57.6 | — | |
| SeqTrackSource=CVPR23, Supervised=✓2026.05 | 50.5 | 61.6 | 57.5 | — | |
| SUTrack-T224Resolution=224x224, Speed (fps) CPU=23, Speed (fps) AGX=342024.12 | 50.2 | 61.1 | 57 | — | |
| SeqTrackResolution=2562025.01 | 49.5 | 60.8 | 56.3 | — | |
| SeqTrack-B256Architecture=Transformer-based, Resolution=2562026.02 | 49.5 | 60.8 | 56.3 | — | |
| SeqTrack-B256Evaluation Regime=Non-real-time, Speed (fps) GPU=31, Speed (fps) CPU=2, Speed (fps) AGX=62026.03 | 49.5 | 60.8 | 56.3 | — | |
| SeqTrack-B256Model Scale=Base, Input Resolution=2562026.05 | 49.5 | 60.8 | 56.3 | — | |
| UVLTrack-BVariant Type=Basic2024.01 | 49.2 | — | 55.8 | — | |
| SwinTrackResolution=3842025.01 | 49.1 | 55.6 | — | — | |
| SwinTrack-384TU=false2023.04 | 49.1 | — | 55.6 | — | |
| PNTrack-384Source=Ours, Supervised=Init.BBox2026.05 | 49.1 | 61.2 | 55.1 | — | |
| SwinTrack-B384Model Scale=Base, Input Resolution=3842026.05 | 49.1 | — | 55.6 | — | |
| LMTrackSource=AAAI25, Supervised=✓2026.05 | 49 | 59.6 | 55.8 | — | |
| SMTrack-M256Architecture=SSM-based, Resolution=2562026.02 | 48.9 | 59.7 | 55.1 | — | |
| ROMTrackArchitecture=Transformer-based2026.02 | 48.9 | 59.3 | 55 | — | |
| SSTrack-384Source=AAAI25, Supervised=Init.BBox2026.05 | 48.5 | 60.9 | 54.5 | — | |
| SMTrack-S256Architecture=SSM-based, Resolution=2562026.02 | 48.4 | 59.8 | 54.7 | — | |
| UETrack-BEvaluation Regime=Real-time, Speed (fps) GPU=163, Speed (fps) CPU=56, Speed (fps) AGX=602026.03 | 48.4 | 59 | 54.5 | — | |
| KeepTrack2024.10 | 48.2 | — | — | — | |
| KeepTrack2022.03 | 48.2 | — | — | — | |
| KeepTrackResolution=3522025.01 | 48.2 | — | — | — | |
| KeepTrackTU=true2023.04 | 48.2 | — | — | — | |
| KeepTrackArchitecture=CNN-based2026.02 | 48.2 | — | — | — | |
| KeepTrack2026.03 | 48.2 | — | — | — | |
| F-BDMTrackResolution=2562025.01 | 47.9 | 57.9 | 54 | — | |
| DeTrackResolution=2562025.01 | 47.9 | 56.6 | 52.1 | — | |
| UETrack-SEvaluation Regime=Real-time, Speed (fps) GPU=183, Speed (fps) CPU=68, Speed (fps) AGX=672026.03 | 47.9 | 58.4 | 53.9 | — | |
| AiATrack2024.01 | 47.7 | 55.6 | 55.4 | — | |
| AiATrackVariant Type=Basic2024.01 | 47.7 | — | 55.4 | — | |
| AiATrackResolution=3202025.01 | 47.7 | 55.6 | 55.4 | — | |
| SwinTrack-BModel Variant=Base2022.03 | 47.6 | 58.2 | 54.1 | — | |
| SwinTrackResolution=2242025.01 | 47.6 | 53.9 | — | — | |
| OSTrack-256Input Resolution=256x2562022.03 | 47.4 | 57.3 | 53.3 | — | |
| OSTrack-256Variant Type=Basic2024.01 | 47.4 | — | 53.3 | — | |
| OSTrackResolution=2562025.01 | 47.4 | 57.3 | 53.3 | — | |
| OSTrack-256Architecture=Transformer-based, Resolution=2562026.02 | 47.4 | 57.3 | 53.3 | — | |
| OSTrack-256Evaluation Regime=Non-real-time, Speed (fps) GPU=105, Speed (fps) CPU=11, Speed (fps) AGX=192026.03 | 47.4 | 57.3 | 53.3 | — | |
| OSTrack-B256Model Scale=Base, Input Resolution=2562026.05 | 47.4 | 57.3 | 53.3 | — | |
| PNTrack-256Source=Ours, Supervised=Init.BBox2026.05 | 47 | 58.8 | 53.1 | — | |
| AiATrackTU=true2023.04 | 46.8 | 54.4 | 54.2 | — | |
| ARTrackResolution=2562025.01 | 46.4 | 56.5 | 52.3 | — |