Abstract: Learning to build 3D scene graphs is essential for real-world perception in a structured and rich fashion. However, previous 3D scene graph generation methods utilize a fully supervised ...
Abstract: Due to the homophily assumption in graph convolution networks (GCNs), a common consensus in the graph node classification task is that graph neural networks (GNNs) perform well on homophilic ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results