Comment by tyre

I think their model should take a second pass on the words and probabilities, independent of the video.

Look at their example:

  Animal: 97.76%
  Tiger: 90.11%
  Terrestrial animal: 68.17%

So we are 90% sure it is a tiger but only 68% sure it is a land animal? I don't think that makes sense.

It could be that this is a weakness of seeding AI data with human inputs. I can believe that 90% of people who saw the video would agree that it is a tiger, while fewer would agree it is a terrestrial animal, because they don't know what terrestrial means.