ARKit to FACS cheat sheet

If you or your team are using open-source face tracking kits, figuring out what’s what can be challenging. Navigate the ambiguity with the FACS Translation Sheet!

Bypassing VR Headset Occlusion in Face Tracking – PREVIEW

There is a superstition among engineers and researchers that you cannot track facial landmarks (features like the eyebrows, eyes, and mouth) when they fall outside the camera view. This belief is not entirely true. You can still track facial movements despite occlusion, and here’s how!

nasolabial furrow deepener vs. upper lip raiser

Because of its name, upper lip raiser is considered the go-to action for lifting the top lip and tends to get overused in art and tech, acting as a replacement for nasolabial furrow deepener or a shortcut for showing teeth during smiling. Despite its name, upper lip raiser is not the only lip-raising action! In fact, applying upper lip raiser to contexts better suited for nasolabial furrow deepener can be detrimental to the essence of a target expression.

faces you don’t want to see during UX research – especially for VR

Faces of discomfort often followed headset adjustment – or predicted upcoming adjustments. Bored faces and faces on the contempt spectrum tended to be predictive of undesirable experiences later disclosed during the post-demo interviews. These expressions were not just useful for predicting events. They also served as points for further investigation.

bias in emotion tracking

We seem to subscribe to the popular oversimplification that machines are less biased than humans; however, if you are familiar with the ways in which machines are trained to read and focus on different aspects of data, you will know: It’s just not that simple.