Appendixfor"3DSiameseVoxel-to-BEVTrackerfor SparsePointClouds "

B, we provide specific network architecture and more details about the target center parameterization for the voxel-to-BEV target localization network. Then, we present the 2D network to aggregate features in the BEV space. After that, we introduce the center network for target localization. Note that the last 2D convolution is the transposed convolution. To obtain the target center in the BEV space, we perform target center parameterization.