Abstract. We propose Neural Graph Matching (NGM) Networks, a
novel framework that can learn to recognize a previous unseen 3D action
class with only a few examples. We achieve this by leveraging the inherent
structure of 3D data through a graphical representation. This allows
us to modularize our model and lead to strong data-efficiency in fewshot learning. More specifically, NGM Networks jointly learn a graph
generator and a graph matching metric function in an end-to-end fashion
to directly optimize the few-shot learning objective. We evaluate NGM
on two 3D action recognition datasets, CAD-120 and PiGraphs, and
show that learning to generate and match graphs both lead to significant
improvement of few-shot 3D action recognition over the holistic baselines.