What's the baseline, aka how accurate are humans in detecting sexual orientations from a picture?
-
-
-
Humans are able to predict sexual orientation with modest success, achieving an accuracy measured by the Area Under the Curve (AUC) of AUC=.61 for male images and AUC=.54 for female images.
- 1 more reply
New conversation -
-
-
So, social constructionism shows up in AI too. Interesting.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is nuts. I'm surprised that head pose isn't correlated with sexual orientation.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I think this probably just shows that gay people and straight people take different kinds of pictures for dating sites, which itself is probably dictated by culture. Smiles, facial expressions, eye contact, expressiveness-- all plausibly different b/t gay and straight pics.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
The implication may be that the developmental factors that effect facial bone formation,most likely the fetal hormone environment?, have an impact on brain traits as well. But as always the correlation/causation question would still exist.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Soon to be an iPhone app.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
This Tweet is unavailable.
-
-
Still at best only get it right 68% of the time... Makes you wonder if everyone who says they are gay aren't really just making it up for the money they'll earn scamming people...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.