Table 5.

Abbreviations for the summary.

Dimension	Category
Scope	S1: Macro-Facial Expressions
	S2: Micro facial expressions
	S3: Static pose expressions
	S4: Body gesture expressions
Test Environment	TE1: In the wild
	TE2: controlled
Methods	M1: CNN
	M2: Faster R-CNN
	M3: Vision transformers
	M4: Other NNs
Datasets	D1: Created
	D2: Already exists