GitHub6d
Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis
To this end, we propose 3D Graph ... (3D-GCN), which is designed to extract local 3D features from point clouds across scales, while shift and scale-invariance properties are introduced. Our algorithm ...
IEEE4d
HG-SCC: A Subgraph-Aware Convolutional Few-Shot Classification Method on Heterogeneous Graphs
Heterogeneous graphs (HGs), rich in semantic information, introduce complexities that make few-shot particularly challenging. Addressing this problem, we propose a subgraph-aware convolutional ...
GitHub4d
Ping, but with a graph.
Comes with the following super-powers: ...