You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, Can you please clarify the experimental setup?
In your paper, it mentions that 'For the comparison with the previous approaches, we used both single and interacting hand (SH+IH) images of the H+M split. For ablation studies, we used SH+IH images of the H split. And in table 5, it provide the comparision in both single and interacting hand (SH+IH) images of the H+M split :
But when envaluated in SH+IH and H+M split , the model get the results with given checkpoint like here:
When envlauted in SH+IH and only H split by uncomment the code here , the model get the reults like here :
It seems that the latter is closer to the results mentioned in the article. But it does not use M split.
Looking forward your reply! Thank you.
The text was updated successfully, but these errors were encountered:
Hi, Can you please clarify the experimental setup?
In your paper, it mentions that 'For the comparison with the previous approaches, we used both single and interacting hand (SH+IH) images of the H+M split. For ablation studies, we used SH+IH images of the H split. And in table 5, it provide the comparision in both single and interacting hand (SH+IH) images of the H+M split :
But when envaluated in SH+IH and H+M split , the model get the results with given checkpoint like here:
When envlauted in SH+IH and only H split by uncomment the code here , the model get the reults like here :
It seems that the latter is closer to the results mentioned in the article. But it does not use M split.
Looking forward your reply! Thank you.
The text was updated successfully, but these errors were encountered: