Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The HRNet architecture.

The multi-resolution stage modules are marked with blue color areas. The remained three stages module consists of parallel multi-resolution subnetworks with multi-resolution information interactions.

More »

Fig 1 Expand

Fig 2.

The channel attention mechanism.

The top block (a) is ECA block, which consists of average pooling, a fast 1D convolution of size k and a sigmoid activation. The bottom block (b) is SE block, which consists of average pooling, two fully-connected (FC) layers and a sigmoid activation.

More »

Fig 2 Expand

Fig 3.

The DE-HRNet structure.

The dySample and the Detail Enhancement Module (DEM) are applied to the HRNet [5,9], further implementation details are provided in Section 3.1.

More »

Fig 3 Expand

Fig 4.

The structure of Detail Enhancement Module.

The module is designed based on SE block. Additionally, the global average pooling and dropout [25] technology are located before and after the SE block, respectively. Dashed lines denote selective identity mappings.

More »

Fig 4 Expand

Table 1.

Comparisons on the COCO validation set. #Params and FLOPS are calculated only for the method.

More »

Table 1 Expand

Table 2.

Comparisons on the COCO test-dev set. The bottom-up methods use multi-scale testing.

More »

Table 2 Expand

Table 3.

Comparisons of PCK@0.5 score on the MPII valid set.

More »

Table 3 Expand

Table 4.

Ablation study of DE-HRNet’s components on the MPII valid set.

More »

Table 4 Expand

Table 5.

The ECA block and SE block components on the MPII valid set.

More »

Table 5 Expand