| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| VideoAttentionTarget | L2 Distance0.051 | 38 | 2mo ago | ||
| GazeFollowing | OmniGF | Minimum Distance0.04 | 35 | 2mo ago | |
| GazeFollow (test) | ViTGaze | AUC0.949 | 24 | 5mo ago | |
| VideoAttentionTarget (test) | ViTGaze | AUC0.938 | 20 | 5mo ago | |
| ChildPlay | OmniGF | Distance0.09 | 17 | 2mo ago | |
| VAT (test) | Distance Error0.108 | 11 | 5mo ago | ||
| GazeFollow Inconsistent | Ours (ViT-L) | AUC93.71 | 9 | 2mo ago | |
| GazeFollow Consistent | Ours (ViT-L) | AUC0.9719 | 9 | 2mo ago | |
| VideoAttentionTarget (VAT) Inconsistent | AUC0.9078 | 9 | 2mo ago | ||
| VideoAttentionTarget (VAT) Consistent | HCLoRA | AUC0.959 | 9 | 2mo ago | |
| GOO Real | PaGE ViT-H+ Teacher | AUC93 | 7 | 19d ago | |
| VSGaze | MTGS | Distance0.111 | 6 | 5mo ago | |
| UCO-LAEO | Gupta | Distance Error0.03 | 6 | 5mo ago | |
| VideoCoAtt | MTGS-noSoc | Distance Error0.111 | 6 | 5mo ago | |
| VAT | MTGS | Distance Error0.116 | 6 | 5mo ago | |
| Zhang | PaGE ViT-B Distill | Accuracy76.29 | 5 | 19d ago | |
| DL Gaze (randomly selected 15,000 pictures) | HGTTR | AUC0.912 | 4 | 5mo ago |
