We consider three heterogeneous Graph Neural Network (GNN) backbones, i.e., GCN, GAT, and GPR-GNN . Each of the GNN backbones has very different message propagation mechanisms. For each client, we ...
Abstract: This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results