una-dinosauria/human-motion-prediction

Understanding the structure of H3.6M dataset

KavinduZoysa opened this issue · 4 comments

Hi Una-dinosauria,

First of all, I need to thank you for making this fantastic paper and code available publicly and it is really helpful for my academics.

I have a very basic question. Can you please explain the structure of the dataset and what is the meaning of 99 numbers in each row? In the site, they are describing 96 data, but in H3.6M dataset there are 99 data in each raw.

IIRC, the first three numbers are the global translation. The rest are (99-3)/3 = 32 articulations that define the joint angles of the human body.

You may want to look at #21 (comment) to get see how you can visualize the data. Following the visualization code should make it clear what the data means.

Cheers,

Hi Una-dinosauria,

Thank you for pointing me towards the correct reference. Could you please tell me what are the independent joints out of 32 joints?

Thank you,
Kavindu

Hi!

No, sorry I can't do that. You can use our code to visualize and perhaps some more code to measure standard deviations so you can find out.

Cheers,

Thank you for the support.