Visual Object Tracking on LaSOT (test)
76.6AUCMCITrack-L384
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| MCITrack-L384Backbone=Fast-iTPN-L, Input Resolution=384x384, Params (M)=287, FLOPs (G)=370, Speed (fps)=52024.12 | 76.6 | — | 86.1 | 85 | — | — | — | — | |
| MCITrack-L224Backbone=Fast-iTPN-L, Input Resolution=224x224, Params (M)=287, FLOPs (G)=123, Speed (fps)=162024.12 | 76.1 | — | 86.1 | 84.1 | — | — | — | — | |
| ETCTrack-B384Resolution=3842026.05 | 75.9 | — | 85.9 | 84 | — | — | — | — | |
| MCITrack-B224Backbone=Fast-iTPN-B, Input Resolution=224x224, Params (M)=88, FLOPs (G)=38, Speed (fps)=352024.12 | 75.3 | — | 85.6 | 83.3 | — | — | — | — | |
| SUTrackModel scale=Large, Input resolution=3842024.12 | 75.2 | — | 84.9 | 83.2 | — | — | — | — | |
| LORAT2024.11 | 75.1 | — | — | — | — | — | — | — | |
| SAM2.1++2024.11 | 75.1 | — | — | — | — | — | — | — | |
| LoRAT-L378Backbone=Large, Input Resolution=378x3782024.12 | 75.1 | — | 84.1 | 82 | — | — | — | — | |
| LORATModel scale=Large, Input resolution=3782024.12 | 75.1 | — | 84.1 | 82 | — | — | — | — | |
| DreamTrack-B384Resolution=3842026.05 | 75 | — | 84.2 | 81.7 | — | — | — | — | |
| ETCTrack-B224Resolution=2242026.05 | 74.9 | — | 85.1 | 82.7 | — | — | — | — | |
| SPMTrack-B384Resolution=3842026.05 | 74.9 | — | 84 | 81.7 | — | — | — | — | |
| SUTrackModel scale=Base, Input resolution=3842024.12 | 74.4 | — | 83.9 | 81.9 | — | — | — | — | |
| ChatTracker-Lvisual tracker=MixFormer, MLLM=GPT4V-preview1106, GVLM=GroundingDINO-T2024.11 | 74.1 | — | 83.8 | 81.2 | — | — | — | — | |
| ODTrack-L2024.01 | 74 | — | 84.2 | 82.3 | — | — | — | — | |
| ODTrack2024.11 | 74 | — | — | — | — | — | — | — | |
| ODTrack-L384Backbone=Large, Input Resolution=384x3842024.12 | 74 | — | 84.2 | 82.3 | — | — | — | — | |
| ODTrackModel scale=Large, Input resolution=3842024.12 | 74 | — | 84.2 | 82.3 | — | — | — | — | |
| MCITrack-B224†Resolution=224, Evaluation=Locally trained2026.05 | 74 | — | 83.6 | 81.4 | — | — | — | — | |
| MCITrack-S224Backbone=Fast-iTPN-S, Input Resolution=224x224, Params (M)=45, FLOPs (G)=19, Speed (fps)=402024.12 | 73.8 | — | 84.2 | 81.7 | — | — | — | — | |
| DreamTrack-B256Resolution=2562026.05 | 73.8 | — | 83.4 | 80.6 | — | — | — | — | |
| ARTrackV2-L384Backbone=Large, Input Resolution=384x3842024.12 | 73.6 | — | 82.8 | 81.1 | — | — | — | — | |
| ARTrackV2Model scale=Large, Input resolution=3842024.12 | 73.6 | — | 82.8 | 81.1 | — | — | — | — | |
| SUTrackModel scale=Large, Input resolution=2242024.12 | 73.5 | — | 83.3 | 80.9 | — | — | — | — | |
| ETCTrack-S224Resolution=2242026.05 | 73.4 | — | 83.5 | 81.1 | — | — | — | — | |
| MixViT-L (ConvMAE)Backbone=MixViT-L, Pre-training=ConvMAE2023.02 | 73.3 | — | 82.8 | 80.3 | — | — | — | — | |
| ODTrack-B2024.01 | 73.2 | — | 83.2 | 80.6 | — | — | — | — | |
| ODTrack-B384Input Resolution=384x3842024.12 | 73.2 | — | 83.2 | 80.6 | — | — | — | — | |
| SUTrackModel scale=Base, Input resolution=2242024.12 | 73.2 | — | 83.4 | 80.5 | — | — | — | — | |
| ODTrackModel scale=Base, Input resolution=3842024.12 | 73.2 | — | 80.6 | 83.2 | — | — | — | — | |
| ODTrack-B384Resolution=3842026.05 | 73.2 | — | 83.2 | 80.6 | — | — | — | — | |
| ARTrack-L384Backbone=Large, Input Resolution=384x3842024.12 | 73.1 | — | 82.2 | 80.3 | — | — | — | — | |
| ARTrackModel scale=Large, Input resolution=3842024.12 | 73.1 | — | 82.2 | 80.3 | — | — | — | — | |
| TemTrack-B384Resolution=3842026.05 | 73.1 | — | 83 | 80.7 | — | — | — | — | |
| ARTrackV2Input resolution=3842024.12 | 73 | — | 81.9 | 78.6 | — | — | — | — | |
| ARTrackV2-B384Resolution=3842026.05 | 73 | — | 82 | 79.6 | — | — | — | — | |
| LORATModel scale=Base, Input resolution=3782024.12 | 72.9 | — | 81.9 | 79.1 | — | — | — | — | |
| LoRAT-B378Resolution=3782026.05 | 72.9 | — | 81.9 | 79.1 | — | — | — | — | |
| AQATrack-384Source=Ours, Input Resolution=384x3842024.03 | 72.7 | — | 82.9 | 80.2 | — | — | — | — | |
| HIPTrack-B384Resolution=3842026.05 | 72.7 | — | 82.9 | 79.5 | — | — | — | — | |
| ARTrack2024.01 | 72.6 | — | 81.7 | 79.1 | — | — | — | — | |
| ARTrack-384Source=CVPR23, Input Resolution=384x3842024.03 | 72.6 | — | 81.7 | 79.1 | — | — | — | — | |
| ARTrack-384Source=CVPR 20232024.11 | 72.6 | — | 81.7 | 79.1 | — | — | — | — | |
| ARTrackInput resolution=3842024.12 | 72.6 | — | 81.7 | 79.1 | — | — | — | — | |
| ARPTrack-B256Resolution=2562026.05 | 72.6 | — | 81.4 | 78.5 | — | — | — | — | |
| SeqTrack2024.11 | 72.5 | — | — | — | — | — | — | — | |
| SeqTrack-L384Source=CVPR 20232024.11 | 72.5 | — | 81.5 | 79.3 | — | — | — | — | |
| SeqTrack-L384Backbone=Large, Input Resolution=384x3842024.12 | 72.5 | — | 81.5 | 79.3 | — | — | — | — | |
| SeqTrackModel scale=Large, Input resolution=3842024.12 | 72.5 | — | 81.5 | 79.3 | — | — | — | — | |
| MixViT-LBackbone=MixViT-L, Pre-training=MAE2023.02 | 72.4 | — | 82.2 | 80.1 | — | — | — | — | |
| MixViT2024.11 | 72.4 | — | — | — | — | — | — | — | |
| MixViT-L384Backbone=Large, Input Resolution=384x3842024.12 | 72.4 | — | 82.2 | 80.1 | — | — | — | — | |
| MixViTModel scale=Large, Input resolution=3842024.12 | 72.4 | — | 82.2 | 80.1 | — | — | — | — | |
| UNINEXTModel scale=Large2024.12 | 72.4 | — | 80.7 | 78.9 | — | — | — | — | |
| DiffusionTrack2024.11 | 72.3 | — | — | — | — | — | — | — | |
| F-BDMTrack-384Source=ICCV23, Input Resolution=384x3842024.03 | 72 | — | 81.5 | 77.7 | — | — | — | — | |
| F-BDMTrack-384Source=ICCV 20232024.11 | 72 | — | 81.5 | 77.7 | — | — | — | — | |
| MITSSource=ICCV 20232024.11 | 72 | — | 80.1 | 78.5 | — | — | — | — | |
| TemTrack-B256Resolution=2562026.05 | 72 | — | 82.1 | 79.1 | — | — | — | — | |
| F-BDMTrack-384Resolution=3842026.05 | 72 | — | 81.5 | 77.7 | — | — | — | — | |
| DropTrack2024.11 | 71.8 | — | — | — | — | — | — | — | |
| DropTrackSource=CVPR 20232024.11 | 71.8 | — | 81.8 | 78.1 | — | — | — | — | |
| DropTrackInput resolution=2242024.12 | 71.8 | — | 81.8 | 78.1 | — | — | — | — | |
| ETCTrack-T224Resolution=2242026.05 | 71.8 | — | 82.1 | 78.9 | — | — | — | — | |
| ChatTracker-Bvisual tracker=ARTrack, MLLM=GPT4V-preview1106, GVLM=GroundingDINO-T, integration=UVLTrack-B in place of STM and FVM2024.11 | 71.7 | — | 80.9 | 77.5 | — | — | — | — | |
| MCITrack-T224Backbone=Fast-iTPN-T, Input Resolution=224x224, Params (M)=32, FLOPs (G)=13, Speed (fps)=512024.12 | 71.7 | — | 81.5 | 78.2 | — | — | — | — | |
| LoRAT-B224Input Resolution=224x2242024.12 | 71.7 | — | 80.9 | 77.3 | — | — | — | — | |
| ARTrackV2-256Input Resolution=256x2562024.12 | 71.6 | — | 80.2 | 77.2 | — | — | — | — | |
| ARTrackV2-B256Resolution=2562026.05 | 71.6 | — | 80.2 | 77.2 | — | — | — | — | |
| SeqTrack2024.01 | 71.5 | — | 81.1 | 77.8 | — | — | — | — | |
| SeqTrack-B384Source=CVPR23, Input Resolution=384x3842024.03 | 71.5 | — | 81.1 | 77.8 | — | — | — | — | |
| SeqTrackModel scale=Base, Input resolution=3842024.12 | 71.5 | — | 81.1 | 77.8 | — | — | — | — | |
| AQATrack-256Source=Ours, Input Resolution=256x2562024.03 | 71.4 | — | 81.9 | 78.6 | — | — | — | — | |
| ROMTrack-384Source=ICCV23, Input Resolution=384x3842024.03 | 71.4 | — | 81.4 | 78.2 | — | — | — | — | |
| ROMTrack2024.11 | 71.4 | — | — | — | — | — | — | — | |
| AQATrack-256Input Resolution=256x2562024.12 | 71.4 | — | 81.9 | 78.6 | — | — | — | — | |
| ROMTrack-384Input Resolution=384x3842024.12 | 71.4 | — | 81.4 | 78.2 | — | — | — | — | |
| AQATrackInput resolution=2562024.12 | 71.4 | — | 82 | 78.6 | — | — | — | — | |
| ROMTrackInput resolution=3842024.12 | 71.4 | — | 81.4 | 78.2 | — | — | — | — | |
| GRMModel scale=Large, Input resolution=3202024.12 | 71.4 | — | 81.2 | 77.9 | — | — | — | — | |
| SwinTrack-B-384Resolution=3842023.02 | 71.3 | — | — | 76.5 | — | — | — | — | |
| SwinTrack-384Search Resolution=384x3842024.02 | 71.3 | — | — | 76.5 | — | — | — | — | |
| SwinTrack-384Input Resolution=384x3842024.12 | 71.3 | — | — | 76.5 | — | — | — | — | |
| SwinTrack2024.12 | 71.3 | — | 76.5 | — | — | — | — | — | |
| DecoupleTNLvision-language tracker=true, Source=ICCV 20232024.11 | 71.2 | — | — | 75.3 | — | — | — | — | |
| OSTrack-384Resolution=3842023.02 | 71.1 | — | 81.1 | 77.6 | — | — | — | — | |
| TATrack-LPublished=Ours2023.02 | 71.1 | — | 79.1 | 76.1 | — | — | — | — | |
| OSTrack2024.01 | 71.1 | — | 81.1 | 77.6 | — | — | — | — | |
| OSTrack-384Search Resolution=384x3842024.02 | 71.1 | — | 81.1 | 77.6 | — | — | — | — | |
| OSTrack-384Source=ECCV22, Input Resolution=384x3842024.03 | 71.1 | — | 81.1 | 77.6 | — | — | — | — | |
| OSTrack2024.11 | 71.1 | — | — | — | — | — | — | — | |
| TATrack-L384Backbone=Large, Input Resolution=384x3842024.12 | 71.1 | — | 79.1 | 76.1 | — | — | — | — | |
| OSTrackInput resolution=3842024.12 | 71.1 | — | 81.1 | 77.6 | — | — | — | — | |
| TATrackModel scale=Large, Input resolution=3842024.12 | 71.1 | — | 79.1 | 76.1 | — | — | — | — | |
| OSTrack-384Resolution=3842026.05 | 71.1 | — | 81.1 | 77.6 | — | — | — | — | |
| MixformerV2-BSource=NeurIPS 20232024.11 | 70.6 | — | 80.8 | 76.2 | — | — | — | — | |
| SimTrack-LBackbone=ViT-Large2023.02 | 70.5 | — | 79.7 | — | — | — | — | — | |
| One Tracker2024.03 | 70.5 | — | 79.9 | 76.5 | — | — | — | — | |
| SimTrackSearch Resolution=< 300x3002024.02 | 70.5 | — | 79.7 | — | — | — | — | — | |
| OneTrackerInput resolution=3842024.12 | 70.5 | — | 79.9 | 76.5 | — | — | — | — |