In traditional computer vision and computer graphics, the pose matrix is a 4x4 matrix of the form
r11 r12 r12 t1
r21 r22 r22 t2
r31 r32 r32 t3
0 0 0 1
and is a transformation to change viewpoints from one frame to another.
In the Matrix Capsules with EM Routing paper they say that the 'pose' of various sub-objects of an object are encoded by each capsule lower layer. But from the procedure described in the paper, I understand that the pose matrix they talk about doesn't conform to the definition of the pose matrix. There isn't any restriction on keeping the form of the pose matrix shown above.
Therefore, my first question is that is it right to use the word pose to describe the 4x4 matrix of each capsule?
My next question is that since the claim is that the capsules learn the pose matrices of the sub-objects of an object, does it mean they learn the viewpoint transformations of the sub-objects since the pose matrix is actually a transformation?