Levon Dang

among human 3.6m 7 subjects, the subject 5 is used to test, the others are used to train

Since the 3D coordinate error of your model has a large performance gain of other baselines, i am so interested with the reason inside.

And why the performance gain of eular error is not that large, compared with 3D coordinate error?

+1

+1

I guess they are [1 2 3 6 7 8 12 13 14 15 17 18 19 25 26 27]

same error. Do you solved it?

> Hello, author. I tried to reproduce your code, but the results of the experiments are quite different from the results given in the paper. Can you explain the construction...

+1

me too