Identifying Real and Posed Smiles from Observers' Galvanic Skin Response
and Blood Volume Pulse
Abstract
The smiles stimuli were collected from the UvA-NEMO dataset. A total of
60 videos were randomly selected for this experiment. We created four
categories out of these 60 videos, namely PV (paired videos), PI (paired
images), SV (single video), and SI (single image). When the same person
was viewed by observers in both real and posed smile videos, we report
this as “paired videos”, otherwise we use the term “single video”.