I have a video recording of a person in a sitting position (the camera was place in front of the person). The recording lasts for around 60 minutes. At the beginning and end of the recordings (around 10 min each) there is a second person in the video and the faces might not always be visible because the persons have been talking. We are only interested in the 60 minutes and not in this part in the beginning and end.
Would the result of Affectiva be different when I cut the 10 minutes at the beginning and end? Of course the easier solution would be to just run it over the whole recording without trimming…
No, shouldn't be our SDK gives a prediction of the emotional/expression state per frame basis.