Table 5. The result of the comparative studies of multilabel models’ performances on CK+ dataset is presented as follows.

Metric with ↑ indicates the higher the metric value, the better the model performance, and metric with ↓ indicates the lower or smaller the value of the metric the better the model’s performance.

ML-Model	Hamming loss ↓	Ranking loss ↓	Average precision ↑	Coverage ↓
RAKELD	0.3904	0.6637	0.2370	4.4435
CC	0.1489	0.6842	0.4234	4.7339
MLkNN	0.1839	0.8345	0.2965	4.7930
MLARAM	0.1951	0.4636	0.4144	3.0748
ML-CNN	0.1487	0.4161	0.5926	2.8120
VGGML-CNN	0.1393	0.3897	0.6002	1.4359