Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The overall network architecture of HFE-Net.

More »

Fig 1 Expand

Fig 2.

EfficientNetV2 [42] network architecture.

More »

Fig 2 Expand

Fig 3.

(a) shows the working principle of self-attention mechanism, (b) shows the working principle of Multi-head Self-attention mechanism.

More »

Fig 3 Expand

Table 1.

Distribution of data in the FER2013 dataset.

More »

Table 1 Expand

Table 2.

Distribution of data in the FERPlus dataset.

More »

Table 2 Expand

Table 3.

Distribution of data in the RAF-DB dataset.

More »

Table 3 Expand

Table 4.

Distribution of data in the Affectnet dataset.

More »

Table 4 Expand

Table 5.

Multilayer perceptron, Multi-head Self-attention and Feature Fusion Device ablation experiments on four FER datasets.

More »

Table 5 Expand

Table 6.

Comparison of experimental results on the FER2013 dataset.

More »

Table 6 Expand

Table 7.

Comparison of experimental results on the FERPlus dataset.

More »

Table 7 Expand

Table 8.

Comparison of experimental results on the RAF-DB dataset.

More »

Table 8 Expand

Table 9.

Comparison of experimental results on the Affectnet dataset.

More »

Table 9 Expand

Fig 4.

Confusion matrix of Effv2-s (baseline) on three datasets.

More »

Fig 4 Expand

Fig 5.

Confusion matrix of the proposed model on three datasets.

More »

Fig 5 Expand