Recipe Generation On Foodcom
評価指標
BLEU-1
BLEU-4
BPE Perplexity
D-1
D-2
Rouge-L
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | BLEU-1 | BLEU-4 | BPE Perplexity | D-1 | D-2 | Rouge-L | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| LLaVA-Chef | 29 | 6 | 2.6 | 0 | 0 | 18.4 | LLaVA-Chef: A Multi-modal Generative Model for Food Recipes | - |
| Prior Name | 28.046 | 3.211 | 9.516 | 0.233 | 2.08 | 24.794 | Generating Personalized Recipes from Historical User Preferences | - |
0 of 2 row(s) selected.