Image Captioning 벤치마크
Image Captioning on MS-COCO
| Rank | Model | BLEU-1 | BLEU-4 | CIDEr | METEOR | SPICE | Test ROGUE-L | Paper | Code | Year |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | NeuSyRE | 79.1 | 37.6 | 131.4 | 28.5 | 23.8 | 57.7 | NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment | jaleedkhan/neusire | 2023 |
| 2 | FLAT 자동 추출 | – | 40.5 | – | – | – | – | FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation | 2026 | |
| 3 | RORPCap 자동 추출 | – | – | 120.5 | – | – | – | RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning | 2025 |