Table 2 Experimental results of image models.
From: T-ECBM: a deep learning-based text-image multimodal model for tourist attraction recommendation
Model | Number of parameters | Top-1 accuracy (%) | Top-5 accuracy (%) | F1-score (%) |
|---|---|---|---|---|
GoogLeNet_CA | 6,058,580 | 83.13 ± 1.76 | 95.43 ± 0.94 | 82.75 ± 1.75 |
ResNet-152_CA | 58,864,278 | 82.29 ± 0.85 | 94.11 ± 0.93 | 81.90 ± 0.85 |
DenseNet-121_CA | 7,240,380 | 83.16 ± 0.87 | 96.20 ± 0.36 | 82.78 ± 0.87 |
EfficientNet_CA | 4,230,440 | 83.68 ± 1.13 | 97.07 ± 0.71 | 83.28 ± 1.12 |
