Image Captioning On Nocaps Out Of Domain
Métriques
CIDEr
SPICE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | CIDEr | SPICE | Paper Title | Repository |
|---|---|---|---|---|
| ClipCap (Transformer) | 49.14 | 9.57 | ClipCap: CLIP Prefix for Image Captioning | |
| CS395T | 21.3 | 7.2 | - | - |
| ClipCap (MLP + GPT2 tuning) | 49.35 | 9.7 | ClipCap: CLIP Prefix for Image Captioning | |
| ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS | 72.13 | 11.53 | - | - |
| UpDown | 30.09 | 8.08 | - | - |
| area_attention | 26.55 | 7.72 | - | - |
| Neural Baby Talk + CBS | 58.48 | 8.77 | - | - |
| nocaps_training | 30.09 | 8.08 | - | - |
| Microsoft Cognitive Services team | 110.14 | 13.74 | VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning | - |
| vinvl_yuan_cbs | 71.43 | 10.57 | - | - |
| Neural Baby Talk | 48.73 | 8.2 | - | - |
| firethehole | 88.54 | 13.87 | - | - |
| UpDown-C | 70.21 | 10.15 | - | - |
| FudanWYZ | 103.75 | 13.75 | - | - |
| evertyhing | 85.18 | 11.18 | - | - |
| Xinyi | 68.92 | 10.05 | - | - |
| IEDA-LAB | 87.51 | 12.52 | - | - |
| MD | 77.39 | 11.59 | - | - |
| coco_all_19 | 23.07 | 7.4 | - | - |
| cxy_nocaps_training | 68.5 | 10.01 | - | - |
0 of 40 row(s) selected.