When I started to look into the deep High-Resolution Net paper, I came to know about the HigherHRNet and the Bottom Up HRNet as well. But I can't find any metrics or proof on which is better for a single person pose estimation task. I would like to know which of these three is the most accurate. Help me out here.
-
$\begingroup$ Can you please edit your post to provide the link to the paper that talks about these models? $\endgroup$ – nbro♦ Oct 30 '20 at 19:21
-
$\begingroup$ Wait, what is the "High-Resolution Net" paper, what is the "HigherHRNet" paper and what is the "Bottom Up HRNet" paper? $\endgroup$ – nbro♦ Oct 31 '20 at 17:33