CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation. (arXiv:2208.12448v1 [cs.CV])

In 3D action recognition, there exists rich complementary information between
skeleton modalities. Nevertheless, how to model and utilize this information
remains a challenging problem for self-supervised 3D action representation
learning. In this work, we formulate the cross-modal interaction as a
bidirectional knowledge distillation problem. Different from classic
distillation solutions that transfer the knowledge of a fixed and pre-trained
teacher to the student, in this work, the knowledge is continuously updated and
bidirectionally distilled between modalities. To this end, we propose …

3d arxiv cv distillation learning representation representation learning