Appendix for Unsupervised Motion Representation Learning with Capsule Autoencoders

We show in the table below the notations grouped by the modules. The values used in our implementation are shown if applicable. The necessity of a two-layer hierarchy is briefly discussed in Section 3.3. In short, it is difficult for a single-layer hierarchy to capture long-time dependencies and variations. This section describes an empirical study where we compare MCAE with its single-layer correspondence.