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

Table 1.

EquiFACS variables (Action Units (AUs), Action Descriptors (ADs), Ear Action Descriptors (EADs) and additional variables) used in [30] after eliminating low frequency and low agreement variables.

More »

Table 1 Expand

Fig 1.

A high-level overview of the pipelines.

More »

Fig 1 Expand

Fig 2.

Examples of horse faces (top) and GrayST stacked frames.

(bottom) for each of the emotional states from left to right: ‘Anticipation’, ‘Baseline’, ‘Disappointment’, ‘Frustration’.

More »

Fig 2 Expand

Table 2.

Performance of the two classifier pipelines using different configurations of classes: Separation into 4 classes, 3 classes unifying Anticipation and Frustration, and just 2 classes of Anticipation and Frustration.

More »

Table 2 Expand

Table 3.

Video emotion classification results.

More »

Table 3 Expand

Fig 3.

Confusion matrix for the video-based pipeline.

More »

Fig 3 Expand

Fig 4.

Confusion matrix for the Equifacs-based pipeline.

More »

Fig 4 Expand

Fig 5.

The EquiFACS-based Decision Tree.

More »

Fig 5 Expand