This comment thread is peak derangement. They chose anime girls because that's where we have the most comprehensive close-to-homogenous visual data available. Nothing more, nothing less.
To call this comment deranged is to misrepresent the context entirely, and also be extremely naive about the selection of videos for the paper. Yes it's possibly a bit snarky, but quite funny too. It's certainly what I was thinking when I looked at the results: this paper is written in field which doesn't have many women in it! I think it's highly likely this will get more exposure because of the choice of examples. Yes they have a robot too — but there aren't any "normal looking" people doing dances.
What do you mean there are not any normal looking people doing dances? The individuals shown on the page might be considered attractive by some but they are not abnormal for that.
