The Gyro-Structure of Some Matrix Manifolds

This supplemental material provides the proofs for the Theorems and Lemmas presented in our paper. For all the datasets, we use interpolation to create sequences of the same length. For SPDNet and SPDNetBN, we compute a covariance matrix to represent an input sequence as in [20]. Our networks are implemented with Tensorflow framework. The number of frames in each sequence is set to 100.