Image Guided Story Ending Generation On Lsmdc
Métriques
BLEU-1
BLEU-2
BLEU-3
BLEU-4
CIDEr
METEOR
ROUGE-L
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | BLEU-1 | BLEU-2 | BLEU-3 | BLEU-4 | CIDEr | METEOR | ROUGE-L | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|---|
| Seq2Seq | 14.21 | 4.56 | 1.70 | 0.70 | 8.69 | 11.01 | 19.69 | Effective Approaches to Attention-based Neural Machine Translation | |
| MMT | 18.52 | 5.99 | 2.51 | 1.13 | 12.41 | 12.87 | 20.99 | MMT: Image-guided Story Ending Generation with Multimodal Memory Transformer | |
| Transformer | 15.35 | 4.49 | 1.82 | 0.76 | 9.32 | 11.43 | 19.16 | Attention Is All You Need | |
| MGCL | 15.89 | 4.76 | 1.57 | 0.00 | 9.16 | 11.61 | 20.30 | - | - |
0 of 4 row(s) selected.