Vision-Language Tracking on TNL2K (test)
67.9AUCSUTrack
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SUTrackModel Scale=L, Resolution=3842024.12 | 67.9 | — | 72.1 | |
| SUTrack-L384Backbone=Large, Resolution=3842024.12 | 67.9 | — | 72.1 | |
| SUTrackModel Scale=L, Resolution=2242024.12 | 66.7 | — | 70.3 | |
| SUTrack-L224Backbone=Large, Resolution=2242024.12 | 66.7 | — | 70.3 | |
| ATSTrackSource=arXiv 20252026.06 | 66.2 | — | 71.3 | |
| SUTrackModel Scale=B, Resolution=3842024.12 | 65.6 | — | 69.3 | |
| SUTrack-B384Backbone=Base, Resolution=3842024.12 | 65.6 | — | 69.3 | |
| SDTrackSource=ESWA 20262026.06 | 65.6 | — | 70.8 | |
| SemaTrackSource=TVC 20262026.06 | 65.5 | — | 70.2 | |
| ChatTracker-Lvisual tracker=MixFormer2024.11 | 65.4 | 76.5 | 70.2 | |
| ReasoningTrackSource=arXiv 20252026.06 | 65.3 | — | 74.3 | |
| ADTrackSource=AAAI 20262026.06 | 65.3 | — | 70.8 | |
| Open_VLTrackSource=-2026.06 | 65.1 | — | 74.5 | |
| SUTrackModel Scale=B, Resolution=2242024.12 | 65 | — | 67.9 | |
| SUTrack-B224Backbone=Base, Resolution=2242024.12 | 65 | — | 67.9 | |
| DUTrackSource=CVPR 20252026.06 | 64.9 | — | 70.6 | |
| UVLTrack-Bvision-language tracker=true2024.11 | 63.1 | 80.9 | 66.7 | |
| UVLTrackSource=AAAI 20242026.06 | 62.7 | — | 65.4 | |
| SeqTrackv2Model Scale=L, Resolution=3842024.12 | 62.4 | — | 66.1 | |
| SeqTrackv2-L384Backbone=Large, Resolution=3842024.12 | 62.4 | — | 66.1 | |
| RrmTrackSource=TMM 20262026.06 | 62.1 | — | 66 | |
| SUTrackModel Scale=T, Resolution=2242024.12 | 60.9 | — | 62.3 | |
| SUTrack-T224Backbone=Tiny, Resolution=2242024.12 | 60.9 | — | 62.3 | |
| ODTrack-384Source=AAAI 20242026.06 | 60.9 | — | — | |
| ARTrack-3842024.11 | 59.8 | — | — | |
| GLADSource=IJCV 20262026.06 | 59.7 | — | 62.2 | |
| ChatTracker-Bvisual tracker=ARTrack2024.11 | 59.6 | 76.3 | 62.1 | |
| OSDTSource=TCSVT 20242026.06 | 59.3 | — | 61.5 | |
| ABOTrackSource=JVCIR 20262026.06 | 58.9 | — | 60.1 | |
| TemTrackSource=AAAI 20252026.06 | 58.8 | — | — | |
| MMTrackvision-language tracker=true2024.11 | 58.6 | 75.2 | 59.4 | |
| MMTrack-384Source=TCSVT 20232026.06 | 58.6 | — | 59.4 | |
| OneTracker2024.12 | 58 | — | 59.1 | |
| OneTracker2024.12 | 58 | — | 59.1 | |
| F-BDMTrack-3842024.11 | 57.8 | — | 59.4 | |
| SeqTrack-L3842024.11 | 57.8 | — | — | |
| AQATrackSource=CVPR 20242026.06 | 57.8 | — | 59.4 | |
| QueryNLTSource=CVPR 20242026.06 | 57.8 | — | 58.7 | |
| CiteTrackervision-language tracker=true2024.11 | 57.7 | 75.6 | 59.6 | |
| SeqTrackv2Model Scale=B, Resolution=2562024.12 | 57.5 | — | 59.7 | |
| SeqTrackv2-B256Backbone=Base, Resolution=2562024.12 | 57.5 | — | 59.7 | |
| MixformerV2-B2024.11 | 57.4 | — | 58.4 | |
| JointNLTvision-language tracker=true2024.11 | 56.9 | 73.5 | 58.1 | |
| DropTrack2024.11 | 56.9 | — | 57.9 | |
| JointNLT2024.12 | 56.9 | — | 58.1 | |
| JointNLT2024.12 | 56.9 | — | 58.1 | |
| JointNLTSource=CVPR 20232026.06 | 56.9 | — | 58.1 | |
| ATTrackSource=MM 20242026.06 | 56.9 | — | 64.7 | |
| DecoupleTNLvision-language tracker=true2024.11 | 56.7 | — | 55 | |
| DecoupleTNL2024.12 | 56.7 | — | 56 | |
| DecoupleTNL2024.12 | 56.7 | — | 56 | |
| Zhao et al.2024.12 | 56 | — | — | |
| Zhao et al.2024.12 | 56 | — | — | |
| OSTrackSource=ECCV 20222026.06 | 55.9 | — | — | |
| SeqTrackSource=CVPR 20232026.06 | 54.9 | — | — | |
| MATTracker2024.11 | 51.3 | — | — | |
| TDCLSource=ECAI 20242026.06 | 49.6 | — | 56.5 | |
| Li et al.2024.12 | 44 | — | 45 | |
| Li et al.2024.12 | 44 | — | 45 | |
| TNL2K-22024.12 | 42 | — | 42 | |
| TNL2K-22024.12 | 42 | — | 42 | |
| SNLT2024.12 | 27.6 | — | 41.9 | |
| SNLT2024.12 | 27.6 | — | 41.9 | |
| TransVG2024.12 | 26.1 | — | 28.9 | |
| TransVG2024.12 | 26.1 | — | 28.9 | |
| Feng et al.2024.12 | 25 | — | 27 | |
| RTTNLD2024.12 | 25 | — | 27 | |
| Feng et al.2024.12 | 25 | — | 27 | |
| RTTNLD2024.12 | 21 | — | 25 | |
| OneStage-BERT2024.12 | 19.8 | — | — | |
| LBYL-BERT2024.12 | 18.3 | — | — |