TL;DR研究如何将针对 RGB 视频训练的行动识别网络适应于识别 3D 人体姿势序列这样的另一个模态,提出了一种基于互相学习的小型学生网络集成和交叉模态知识蒸馏的方法,使得几乎达到了使用完全监督训练的学生网络的精度。
Abstract
In this work, we address the problem how a network for action recognition
that has been trained on a modality like RGB videos can be adapted to recognize
actions for another modality like sequences of 3D human poses. To this end, we
extract the knowledge of the trained teacher network