Appendix 1 Positional Encoding

Obviously, the self-attention module is permutation-invariance. Thus it can not "understand" the Before working with our tracker's encoder and decoder network, we need to extend the untied positional encoding to a multi-dimensional version. Together with relative positional bias, for an n-dimensional case, we have: α ij . From Tab. 1, we can observe The result shows our tracker is still competitive. Our tracker obtained the best performance on this benchmark.