[interfixus]

It seems determined to put visible toes on everybody, no matter that they're wearing socks.

Is this a bug or a feature?

[RodgerTheGreat]

I'm going to guess they start with a generic human model that includes all limbs and extremities and then the "machine learning" process attempts to fit that model to the silhouettes extracted from the video.

[stochastic_monk]

Which implies that the technique uses domain knowledge of people to make assumptions about their morphology.