Complex Reasoning on Natural Scenes Dataset (NSD) (test)
65.41BLEU-1Neuro-Vision to Language
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Neuro-Vision to Languagenumber_of_models=1, ViT3D=true2024.04 | 65.41 | 59.61 | 50.68 | 38.46 | 34.46 | 62.6 | 217.83 | 60.29 | 80.96 | |
| Neuro-Vision to Languagenumber_of_models=1, ViT3D=false2024.04 | 60.36 | 47.81 | 39.76 | 30.57 | 24.37 | 45.39 | 150.67 | 52.13 | 73.26 |