Relational Captioning On Relational
Métriques
Image-Level Recall
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Image-Level Recall | Paper Title | Repository |
|---|---|---|---|
| MTTSNet | 34.27 | Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning | |
| MTTSNet (extended) | 45.96 | Dense Relational Image Captioning via Multi-task Triple-Stream Networks |
0 of 2 row(s) selected.