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 MaximizationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Decoder | 1 | 11.11% |
Domain Generalization | 1 | 11.11% |
Image Classification | 1 | 11.11% |
Object Detection | 1 | 11.11% |
Self-Supervised Image Classification | 1 | 11.11% |
Self-Supervised Learning | 1 | 11.11% |
Semantic Segmentation | 1 | 11.11% |
Action Recognition | 1 | 11.11% |
Disentanglement | 1 | 11.11% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |