CV-MIM

2000년 도입 · 논문 2편에서 사용

CV-MIM, or Contrastive Cross-View Mutual Information Maximization, is a representation learning method to disentangle pose-dependent as well as view-dependent factors from 2D human poses. The method trains a network using cross-view mutual information maximization, which maximizes mutual information of the same pose performed from different viewpoints in a contrastive learning manner. It further utilizes two regularization terms to ensure disentanglement and smoothness of the learned representations.

출처: Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

소개 논문: Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization