Dynamic Keypoint Head is an output head for pose estimation that are conditioned on each instance (person), and can encode the instance concept in the dynamically-generated weights of their filters. They are used in the FCPose architecture.
The Figure shows the core idea. $F$ denotes a level of feature maps. "Rel. Coord." means the relative coordinates, denoting the relative offsets from the locations of $F$ to the location where the filters are generated. Refer to the text for details. $f_{\theta_{i}}$ is the dynamically-generated keypoint head for the $i$-th person instance. Note that each person instance has its own keypoint head.
Source: FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware ConvolutionsPaper | Code | Results | Date | Stars |
---|