Image Captioning On Coco
Metrics
BLEU-4
CIDEr
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | BLEU-4 | CIDEr |
|---|---|---|
| unimo-towards-unified-modal-understanding-and | 39.6 | 127.7 |
| retrieval-augmented-multimodal-language | - | 20.2 |
| analog-bits-generating-discrete-data-using | 34.7 | 115 |
| retrieval-augmented-multimodal-language | - | 103 |
| retrieval-augmented-multimodal-language | - | 38.7 |
| retrieval-augmented-multimodal-language | - | 48 |
| Model 7 | 39.9 | 131.0 |
| retrieval-augmented-multimodal-language | - | 83.9 |
| retrieval-augmented-multimodal-language | - | 55.8 |
| reflective-decoding-network-for-image | - | 125.2 |
| expansionnet-v2-block-static-expansion-in | - | 143.7 |
| retrieval-augmented-multimodal-language | - | 71.9 |
| retrieval-augmented-multimodal-language | - | 89.1 |
| m2-meshed-memory-transformer-for-image | - | 131.2 |
| retrieval-augmented-multimodal-language | - | 85 |
| cutmix-regularization-strategy-to-train | 24.9 | 77.6 |
| lyrics-boosting-fine-grained-language-vision | - | 121.1 |