Representation Learning

Contrastive Cross-View Mutual Information Maximization

Introduced by Zhao et al. in Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

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.

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

Papers


Paper Code Results Date Stars

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories