Action Prediction on ProcTHOR single-object (IID)
97AccuracyCDE (ViT-CLIP)
Evaluation Results
| Method | Links | |
|---|---|---|
| CDE (ViT-CLIP)Backbone=ViT, Pre-training=CLIP2025.08 | 97 | |
| Vanilla-RBackbone=ResNet-182025.08 | 96 | |
| SMS-RBackbone=ResNet-182025.08 | 96 | |
| CDE (ViT-DINO)Backbone=ViT, Pre-training=DINO2025.08 | 96 | |
| CDE (ViT-MAE)Backbone=ViT, Pre-training=MAE2025.08 | 96 | |
| Vanilla-VBackbone=ViT-DINO2025.08 | 95 | |
| ICM-RBackbone=ResNet-182025.08 | 95 | |
| ICM-VBackbone=ViT-DINO2025.08 | 95 | |
| SMS-VBackbone=ViT-DINO2025.08 | 95 |