List your company

Image Captioning on NWPU RESISC45 Captions

88.9BLEU-1Ours
73.92477.81281.785.588Dec 29, 2025

Evaluation results

MethodLinks
OursVisual Encoder=CLIP-Cap-4, Text Decoder=LlamaV22025.1288.9—79.145.868.9206.181.274.833.4
RS-CapRetVisual Encoder=CLIP-Cap-4, Text Decoder=LlamaV2, Finetuned=false2025.1287.1—77.543.965191.978.671.332
RS-CapRetVisual Encoder=CLIP-Cap-4, Text Decoder=LlamaV2, Finetuned=true2025.1287.1—77.643.665.6192.978.771.731.1
MLCA-NETVisual Encoder=VGG16, Text Decoder=LSTM2025.1274.5—60.133.747.8116.462.454.128.5