Deep High-Resolution Representation Learning for Human Pose Estimation
这篇论文给出HRnet,思路关键是保留不同scale的feature map,并在前传过程中让他们交换信息。

From here you can search these documents. Enter your search terms below.
| Keys | Action |
|---|---|
| ? | Open this help |
| n | Next page |
| p | Previous page |
| s | Search |