Table 2 Comparison scores of our method and other state-of-the-art methods on the RSICD.

From: Feature refinement and rethinking attention for remote sensing image captioning

Methods

BLEU1

BLEU2

BLEU3

BLEU4

METEOR

ROUGE_L

CIDEr

SAT

0.6707

0.5438

0.4550

0.3870

0.3203

0.5724

2.4686

SM-Att

0.6699

0.5523

0.4703

0.4068

0.3255

0.5802

2.5738

Struc-Att

0.7016

0.5614

0.4648

0.3934

0.3291

0.5706

1.7031

MLCA-Net

0.7570

0.6340

0.5390

0.4610

0.3510

0.6460

2.3560

MC-Net

0.7280

0.6060

0.5110

0.4330

0.3600

0.6410

2.4540

VRTMM

0.7813

0.6721

0.5645

0.5123

0.3737

0.6713

2.7150

GLCM

0.7767

0.6492

0.5642

0.4937

0.3627

0.6769

2.5491

P-to-H

0.7581

0.6416

0.5585

0.4923

0.3550

0.6523

2.5814

DiffNet

0.7858

0.6807

0.5928

0.5202

0.3947

0.7018

2.9074

Ours

0.7836

0.6679

0.5774

0.5042

0.3672

0.6730

2.8436

  1. Significant values are given in bold.