Table 4 Comparison scores of our method and other state-of-the-art methods on the Sydney-Captions dataset.

SAT

0.7391

0.6402

0.5623

0.5248

0.3493

0.6721

2.2015

SM-Att

0.7430

0.6535

0.5859

0.5181

0.3641

0.6772

2.3402

Struc-Att

0.7795

0.7019

0.6392

0.5861

0.3954

0.7299

2.3791

MLCA-Net

0.8310

0.7420

0.6590

0.5800

0.3900

0.7110

2.3240

MC-Net

0.8340

0.7500

0.6780

0.6070

0.4060

0.7390

2.5640

VRTMM

0.7443

0.6723

0.6172

0.5699

0.3748

0.6698

2.5285

GLCM

0.8041

0.7305

0.6745

0.6259

0.4421

0.6965

2.4337

P-to-H

0.8373

0.7771

0.7198

0.6659

0.4548

0.7860

3.0369

DiffNet

0.8011

0.7283

0.6598

0.5981

0.4216

0.7490

2.7442

Ours

0.7815

0.6994

0.6257

0.5569

0.4000

0.7167

2.4808