About the accurate correspondences between different parsing labels and indexes in your provided parsing data about pise HOT 3 CLOSED

Hi.
After checking the organization of the data, the correspondences are ['0': background, '1': hat, '2': hair, '3':upper clothes, '4': lower part of the body, '5': lower part of the body, '6': skin, '7' face]. This will be corrected in the next version of our paper.
BTW, how to re-organize the labels to the limited categories of parsing (for efficiency) is worth discussing. The pose can help distinguish the legs and the arms, so I think it may be more reasonable. Therefore, in my opinion, if the labels are reasonable, you can re-organize it as you like to deal with.

from pise.

Thanks for your reply. However, to be more precise, I think '4' should be 'Shoes(including socks)', while '5' should be 'lower clothes(e.g. pants, shorts)'. Regarding them all as 'lower part of the body' may be not reasonable.

from pise.

Yeap, 4 is represented as shoes (and socks). It is a typo error in the previous reply.

from pise.