Short-Term Object Interaction Anticipation on Ego4D
33.8mAP (Noun)DINOv3
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DINOv3Encoder=ViT-7B, Protocol=Attentive-based predicted head2026.03 | 33.8 | 50.2 | 40.9 | 23.8 | 14.2 | 19.8 | 11.5 | 7.33 | 5.82 | 17.4 | 10.3 | 5.68 | |
| DINOv3Encoder=ViT-H+, Protocol=Attentive-based predicted head2026.03 | 32.4 | 48.9 | 40.2 | 23.4 | 13.6 | 19.4 | 10.8 | 6.71 | 5.45 | 17.2 | 9.53 | 5.2 | |
| V-JEPA 2.1Encoder=ViT-G, Protocol=Attentive-based predicted head2026.03 | 30.9 | 50.7 | 39.3 | 25.8 | 20.2 | 20.3 | 15.1 | 10.8 | 8.2 | 17.2 | 12.8 | 7.71 | |
| DINOv2Encoder=ViT-g, Protocol=Attentive-based predicted head2026.03 | 30.6 | 47.8 | 38.1 | 23.6 | 14.1 | 19.1 | 10.9 | 7.29 | 5.73 | 16.8 | 9.37 | 5.44 | |
| STAformer2026.03 | 29.4 | 38.3 | 28.3 | 16.6 | 12.27 | 12.8 | 8.89 | 5.47 | 4.06 | 15.3 | 9.94 | 5.67 | |
| V-JEPA 2.1Encoder=ViT-g, Protocol=Attentive-based predicted head2026.03 | 28.7 | 47.3 | 36.5 | 23.6 | 18.1 | 18.2 | 13.5 | 9.55 | 7.21 | 15.5 | 11.4 | 6.75 | |
| DINOv2Encoder=ViT-L, Protocol=Attentive-based predicted head2026.03 | 28.3 | 45.1 | 37.8 | 21.9 | 14.4 | 17.6 | 10.6 | 7.27 | 5.25 | 15.2 | 9.22 | 5.25 | |
| V-JEPA 2Encoder=ViT-g, Protocol=Attentive-based predicted head2026.03 | 27.2 | 45.7 | 34.4 | 22.2 | 16.7 | 16.9 | 12.1 | 8.56 | 6.26 | 14.9 | 10.4 | 6.02 | |
| StillFast2026.03 | 20.2 | — | — | — | — | — | — | — | — | 10.3 | 7.17 | 3.96 | |
| GANO2026.03 | — | 45.3 | 27 | 12.2 | 16.6 | 6.54 | 9 | 4.18 | 2.47 | — | — | — |