It's interesting that it is able to perform so well without using any information as to the relative positions of the cuboids. Temporally, it seems this matters less because of the periodicity of much of the behavior being recognized. Though the results for facial expression recognition look good, I would think lack of positional information could cause problems in this area, because of the complex interactions of all features in the face when displaying emotion. I wonder how much incorporating this in the model would change the results for the data in the paper.