Human Judgment Classification On Pascal 50S
Metrics
Mean Accuracy
Results
Performance results of various models on this benchmark
Model Name | Mean Accuracy | Paper Title | Repository |
|---|---|---|---|
| RefCLIP-S | 83.1 | CLIPScore: A Reference-free Evaluation Metric for Image Captioning | - |
| MID | 85.2 | Mutual Information Divergence: A Unified Metric for Multimodal Generative Models | - |
| CLIP-S | 80.7 | CLIPScore: A Reference-free Evaluation Metric for Image Captioning | - |
0 of 3 row(s) selected.