Image Captioning on R S1 0.2
0.7348BLEU-1VIT + GPT (SOLI-par)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VIT + GPT (SOLI-par)Architecture=VIT + GPT, SOLI approach=SOLI-par2025.12 | 0.7348 | 0.6462 | 0.5641 | |
| VIT + GPT (SOLI-half)Architecture=VIT + GPT, SOLI approach=SOLI-half2025.12 | 0.7197 | 0.6286 | 0.5625 | |
| ResNet+Att-LSTM-GloVe (SOLI-par)Architecture=ResNet+Att-LSTM-GloVe, SOLI approach=SOLI-par2025.12 | 0.5857 | 0.2196 | 0.2317 | |
| ResNet+Att-LSTM-GloVe (SOLI-half)Architecture=ResNet+Att-LSTM-GloVe, SOLI approach=SOLI-half2025.12 | 0.5777 | 0.2011 | 0.2152 |