Neural Graph Matching Networks for Fewshot 3D Action Recognition
ECCV, pp. 673-689, 2018.
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 few-shot...More
PPT (Upload PPT)