I would strongly disagree, moderators apart from filtering nudity also apply a lot of business rules while filtering content even the report says that the best recall is around 90% which leaves a fair bit of stuff that still needs to pass human evaluation. May be that's why folks like youtube employee ten of thousands of moderator in countries like India or philipines.
This makes me think, if filtering nudity etc is possible via APIs and can be deployed on a scale then why the hell do I still see embarrassing pictures popping up in my FB timeline from some arcane pages which I might have liked somewhile ago. Can't FB just flag or remove porn images automatically?
There still seems to be 10% gap between these ML APIs to miss-classify images, might be a case where they have been trained very conservatively to filter out even a little bit show of skin.
Wonder how others are moderating their UGC images? (Seems social networks like FB don't do any moderation, have been embarrassed many times when an explicit image shows up on my wall :P )
5 comments
[ 4.1 ms ] story [ 21.7 ms ] thread