Image Captioning on UCM
0.918BLEU-1Ours
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| OursVisual Encoder=CLIP-Cap-4, Text Decoder=LlamaV22025.12 | 0.918 | 0.868 | 0.829 | 0.798 | 0.489 | 0.832 | 3.701 | 0.547 | |
| SkyEyeGPTVisual Encoder=EVA-G, Text Decoder=LlamaV2-Chat2025.12 | 0.907 | 0.857 | 0.816 | 0.784 | 0.462 | 0.795 | 2.368 | — | |
| RSGPTVisual Encoder=EVA-G, Text Decoder=Vicuna2025.12 | 0.861 | 0.791 | 0.723 | 0.657 | 0.422 | 0.783 | 3.332 | — | |
| RS-CapRetVisual Encoder=CLIP-Cap-4, Text Decoder=LlamaV2, Finetuned=true2025.12 | 0.843 | 0.779 | 0.722 | 0.67 | 0.472 | 0.817 | 3.548 | 0.525 | |
| RS-CapRetVisual Encoder=CLIP-Cap-4, Text Decoder=LlamaV2, Finetuned=false2025.12 | 0.833 | 0.76 | 0.699 | 0.645 | 0.447 | 0.786 | 3.429 | 0.525 | |
| MLCA-NETVisual Encoder=VGG16, Text Decoder=LSTM2025.12 | 0.826 | 0.77 | 0.717 | 0.668 | 0.435 | 0.772 | 3.24 | 0.473 |