Image Captioning On Conceptual Captions
Metrics
CIDEr
ROUGE-L
SPICE
Results
Performance results of various models on this benchmark
Model Name | CIDEr | ROUGE-L | SPICE | Paper Title | Repository |
|---|---|---|---|---|---|
| ClipCap (Transformer) | 71.82 | 25.12 | 16.07 | ClipCap: CLIP Prefix for Image Captioning | |
| ClipCap (MLP + GPT2 tuning) | 87.26 | 26.71 | 18.5 | ClipCap: CLIP Prefix for Image Captioning |
0 of 2 row(s) selected.