Realtime_Multi-Person_Pose_Estimation
Realtime_Multi-Person_Pose_Estimation copied to clipboard
The detail of 'refine the results by applying a single person CPM'
Thanks for the great work! I am interested in the detail of ' If we refine the results of our method by applying a single person CPM on each rescaled region of the estimated persons parsed by our method, we gain an 2.6% overall AP increase.' But i can't find more information to implement it. Can you offer more detail or related code about it or has anyone done this? Thanks very much!
@mingmingDiii Did you get it?