Classification of emotion from short facial videos without relying on facial expressions

What is it about?

This study classifies emotions remotely, without relying on stereotypical facial expressions or con-tact-based methods, using short facial video data. In this approach, we desire to remotely sense transdermal cardiovascular spatiotemporal facial patterns associated with different emotional states and analyze this data via machine learning.

Featured Image

Why is it important?

Stereotypical facial expressions do not necessarily correspond to actual emotional states and may correspond to communicative intentions.