RGB-D Object Tracking on VOT-RGBD 2022 (public challenge)
80EAOMDTrack-U
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MDTrack-UTraining Strategy=Unified-Modality Training2026.03 | 80 | 0.835 | 0.951 | |
| MDTrack-STraining Strategy=Modality-Specific Training2026.03 | 79.7 | 0.836 | 0.948 | |
| SDMoEA*-BMethod Type=Multi-modal Tracker, Fine-tuning Protocol=FFT2026.03 | 78.7 | 0.822 | 0.95 | |
| SDMoEA-LMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 78.4 | 0.83 | 0.942 | |
| SDMoEA-BMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 78.3 | 0.819 | 0.949 | |
| FlexTrackMethod Type=Multi-modal Tracker, Fine-tuning Protocol=FFT2026.03 | 78 | 0.838 | 0.931 | |
| UBATrack-384search region size=384x384, template size=192x1922026.01 | 77.8 | 0.825 | 0.937 | |
| SRTrackReference=-, Base Model=SUTrack-B3842025.08 | 77.7 | 0.841 | 0.926 | |
| STTrackTraining Strategy=Modality-Specific Training2026.03 | 77.6 | 0.825 | 0.937 | |
| STTrackMethod Type=Multi-modal Tracker, Fine-tuning Protocol=FFT2026.03 | 77.6 | 0.825 | 0.937 | |
| SDMoEA*-LMethod Type=Multi-modal Tracker, Fine-tuning Protocol=FFT2026.03 | 77.5 | 0.816 | 0.945 | |
| APTrackMethod Type=Multi-modal Tracker, Fine-tuning Protocol=FFT2026.03 | 77.4 | 0.821 | 0.934 | |
| UBATrack-256search region size=256x2562026.01 | 77.2 | 0.814 | 0.932 | |
| SUTrack-L384Model Scale=Large, Resolution=3842024.12 | 76.6 | 0.835 | 0.922 | |
| SUTrack-B384Model Scale=Base, Resolution=3842024.12 | 76.6 | 0.839 | 0.914 | |
| SUTrack-L384Backbone=Large, Resolution=384x3842024.12 | 76.6 | 0.835 | 0.922 | |
| SUTrack-B384Backbone=Base, Resolution=384x3842024.12 | 76.6 | 0.839 | 0.914 | |
| SUTrack-LMethod Type=Multi-modal Tracker, Fine-tuning Protocol=FFT2026.03 | 76.6 | 0.835 | 0.922 | |
| SUTrack-BMethod Type=Multi-modal Tracker, Fine-tuning Protocol=FFT2026.03 | 76.6 | 0.839 | 0.914 | |
| SUTrack-B224Model Scale=Base, Resolution=2242024.12 | 76.5 | 0.828 | 0.918 | |
| SUTrack-B224Backbone=Base, Resolution=224x2242024.12 | 76.5 | 0.828 | 0.918 | |
| SUTrackTraining Strategy=Unified-Modality Training2026.03 | 76.5 | 0.828 | 0.918 | |
| SUTrack-L224Model Scale=Large, Resolution=2242024.12 | 76.4 | 0.834 | 0.919 | |
| SUTrack-L224Backbone=Large, Resolution=224x2242024.12 | 76.4 | 0.834 | 0.919 | |
| SeqTrackv2-B384Backbone=Base, Resolution=3842023.04 | 75.5 | 0.819 | 0.918 | |
| SeqTrackv2-BMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 75.5 | 0.819 | 0.918 | |
| SUTrackReference=AAAI’25, Base Model=SUTrack-B3842025.08 | 75.4 | 0.83 | 0.906 | |
| SeqTrackv2-L256Backbone=Large, Resolution=2562023.04 | 74.9 | 0.813 | 0.918 | |
| SeqTrackv2-L384Backbone=Large, Resolution=3842023.04 | 74.8 | 0.826 | 0.91 | |
| SeqTrackv2-L384Model Scale=Large, Resolution=3842024.12 | 74.8 | 0.826 | 0.91 | |
| SeqTrackv2-L384Backbone=Large, Resolution=384x3842024.12 | 74.8 | 0.826 | 0.91 | |
| SeqTrackv2-LMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 74.8 | 0.826 | 0.91 | |
| SMSTrackType=FFT, Source=ICCV’25, L.P.=98.2M*, FPS=24.12026.04 | 74.8 | 0.822 | 0.897 | |
| SRTrackReference=-, Base Model=DropTrack-B3842025.08 | 74.5 | 0.829 | 0.892 | |
| SeqTrackv2-B256Backbone=Base, Resolution=2562023.04 | 74.4 | 0.815 | 0.91 | |
| SeqTrackv2-B256Model Scale=Base, Resolution=2562024.12 | 74.4 | 0.815 | 0.91 | |
| SeqTrackv2-B256Backbone=Base, Resolution=256x2562024.12 | 74.4 | 0.815 | 0.91 | |
| SeqTrackv2Status=Non-real-time, GPU Speed (fps)=23, CPU Speed (fps)=2, AGX Speed (fps)=52026.03 | 74.4 | 0.815 | — | |
| SRTrackBase Model=OSTrack-B3842025.08 | 74.3 | 0.824 | 0.889 | |
| SRTrackReference=-, Base Model=OSTrack-B2562025.08 | 74.1 | 0.821 | 0.888 | |
| XTrackBase Model=OSTrack-B3842025.08 | 74 | 0.821 | 0.888 | |
| XTrackTraining Strategy=Unified-Modality Training2026.03 | 74 | 0.828 | 0.889 | |
| XTrack-LMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 74 | 0.828 | 0.889 | |
| XTrack-BMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 74 | 0.821 | 0.888 | |
| XTrackType=PEFT, Source=ICCV’25, L.P.=5.4M*, FPS=10.3*2026.04 | 74 | 0.821 | 0.888 | |
| SEATrackSource=Ours, L.P.=0.6M, FPS=63.52026.04 | 73.6 | 0.821 | 0.884 | |
| SDSTrackReference=CVPR’24, Base Model=DropTrack-B3842025.08 | 73 | 0.814 | 0.886 | |
| SDSTrack2024.12 | 72.8 | 0.812 | 0.883 | |
| SDSTrack2024.12 | 72.8 | 0.812 | 0.883 | |
| SDSTrack2026.01 | 72.8 | 0.812 | 0.883 | |
| SDSTrackStatus=Non-real-time, GPU Speed (fps)=42, CPU Speed (fps)=3, AGX Speed (fps)=72026.03 | 72.8 | 0.812 | — | |
| SDSTrackReference=CVPR’24, Base Model=OSTrack-B2562025.08 | 72.8 | 0.812 | 0.883 | |
| SDSTrackTraining Strategy=Modality-Specific Training2026.03 | 72.8 | 0.812 | 0.883 | |
| SDSTrackMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 72.8 | 0.812 | 0.883 | |
| SDSTrackType=PEFT, Source=CVPR’24, L.P.=14.8M, FPS=20.82026.04 | 72.8 | 0.812 | 0.883 | |
| One Tracker2024.03 | 72.7 | 0.819 | 0.872 | |
| OneTracker2024.12 | 72.7 | 0.819 | 0.872 | |
| OneTracker2024.12 | 72.7 | 0.819 | 0.872 | |
| OneTracker2026.01 | 72.7 | 0.819 | 0.872 | |
| OneTrackerStatus=Non-real-time2026.03 | 72.7 | 0.819 | — | |
| OneTrackerBase Model=OSTrack-B3842025.08 | 72.7 | 0.819 | 0.872 | |
| OneTrackerTraining Strategy=Modality-Specific Training2026.03 | 72.7 | 0.819 | 0.872 | |
| OneTrackerMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 72.7 | 0.819 | 0.872 | |
| OneTrackerType=PEFT, Source=CVPR’24, L.P.=2.8M2026.04 | 72.7 | 0.819 | 0.872 | |
| ViPTReference=CVPR’23, Base Model=DropTrack-B3842025.08 | 72.3 | 0.817 | 0.873 | |
| UnTrackReference=CVPR’24, Base Model=DropTrack-B3842025.08 | 72.2 | 0.821 | 0.871 | |
| TABBTrackMethod Type=RGBD Tracker, Fine-tuning Protocol=FFT2026.03 | 72.2 | 0.821 | 0.874 | |
| TABBTrackType=FFT, Source=PR’25, FPS=272026.04 | 72.2 | 0.821 | 0.874 | |
| ViPT2024.03 | 72.1 | 0.815 | 0.871 | |
| Un-Track2023.04 | 72.1 | 0.82 | 0.869 | |
| ViPT2023.04 | 72.1 | 0.815 | 0.871 | |
| Un-Track2024.12 | 72.1 | 0.82 | 0.869 | |
| ViPT2024.12 | 72.1 | 0.815 | 0.871 | |
| Un-Track2024.12 | 72.1 | 0.82 | 0.869 | |
| ViPT2024.12 | 72.1 | 0.815 | 0.871 | |
| Un-Track2026.01 | 72.1 | 0.82 | 0.869 | |
| ViPT2026.01 | 72.1 | 0.815 | 0.871 | |
| Un-TrackStatus=Non-real-time, GPU Speed (fps)=22, CPU Speed (fps)=4, AGX Speed (fps)=52026.03 | 72.1 | 0.82 | — | |
| ViPTStatus=Non-real-time, GPU Speed (fps)=55, CPU Speed (fps)=6, AGX Speed (fps)=132026.03 | 72.1 | 0.815 | — | |
| ViPTReference=CVPR’23, Base Model=OSTrack-B2562025.08 | 72.1 | 0.815 | 0.871 | |
| UnTrackReference=CVPR’24, Base Model=OSTrack-B2562025.08 | 72.1 | 0.82 | 0.869 | |
| ViPTTraining Strategy=Modality-Specific Training2026.03 | 72.1 | 0.815 | 0.871 | |
| Un-TrackTraining Strategy=Modality-Specific Training2026.03 | 72.1 | 0.815 | 0.871 | |
| Un-TrackMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 72.1 | 0.82 | 0.869 | |
| ViPTMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 72.1 | 0.815 | 0.871 | |
| ViPTType=PEFT, Source=CVPR’23, L.P.=0.8M2026.04 | 72.1 | 0.815 | 0.871 | |
| VADTType=PEFT, Source=ICASSP’242026.04 | 72.1 | 0.816 | 0.873 | |
| UnTrackType=PEFT, Source=CVPR’24, L.P.=6.6M, FPS=25.62026.04 | 72.1 | 0.82 | 0.869 | |
| Un-TrackTraining Strategy=Unified-Modality Training2026.03 | 71.8 | 0.82 | 0.864 | |
| RDT-TEFMethod Type=RGBD Tracker, Fine-tuning Protocol=FFT2026.03 | 71 | 0.807 | 0.877 | |
| SBT-RGBD2023.04 | 70.8 | 0.809 | 0.864 | |
| SBT-RGBD2024.12 | 70.8 | 0.809 | 0.864 | |
| SBT-RGBD2026.01 | 70.8 | 0.809 | 0.864 | |
| MixFormer_3DPTMethod Type=RGBD Tracker, Fine-tuning Protocol=PEFT2026.03 | 70 | 0.818 | 0.847 | |
| EMTrackStatus=Real-time, GPU Speed (fps)=109, CPU Speed (fps)=29, AGX Speed (fps)=362026.03 | 69.7 | 0.806 | — | |
| EMTrackMethod Type=Multi-modal Tracker, Fine-tuning Protocol=PEFT2026.03 | 69.7 | 0.806 | 0.844 | |
| DropTrackReference=CVPR’23, Base Model=DropTrack-B3842025.08 | 69.2 | 0.815 | 0.851 | |
| ViPT-TinyStatus=Real-time, GPU Speed (fps)=56, CPU Speed (fps)=22, AGX Speed (fps)=202026.03 | 68.5 | 0.804 | — | |
| UETrack-BStatus=Real-time, GPU Speed (fps)=163, CPU Speed (fps)=56, AGX Speed (fps)=602026.03 | 68.3 | 0.808 | — | |
| SUTrack-T224Model Scale=Tiny, Resolution=2242024.12 | 68.1 | 0.81 | 0.839 |