| news-classification-on-n15news | Multimodal(ViT+BERT, Input: Image + Body) | #1 | Accuracy: 0.9249 |
| news-classification-on-n15news | BERT (Input: Body) | #2 | Accuracy: 0.9203 |
| news-classification-on-n15news | Multimodal(ViT+BERT, Input: Image + Abstract) | #3 | Accuracy: 0.8610 |
| news-classification-on-n15news | BERT (Input: Abstract) | #4 | Accuracy: 0.8471 |
| news-classification-on-n15news | Multimodal(ViT+BERT, Input: Image + Headline) - Dot | #5 | Accuracy: 0.8202 |
| news-classification-on-n15news | Multimodal(ViT+BERT, Input: Image + Caption) - Concatenate | #6 | Accuracy: 0.7951 |
| news-classification-on-n15news | BERT (Input: Caption) | #7 | Accuracy: 0.7792 |
| news-classification-on-n15news | BERT (Input: Headline) | #8 | Accuracy: 0.7727 |
| news-classification-on-n15news | ViT (Input: Image) | #9 | Accuracy: 0.6065 |