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
It seems that the defaut configurations is spitting a video in to clips that contain only one frame. So I think heatmap information from previous frame (whether of ground truth or prediction) is not used. If then, how can I set up config to achieve reported result in the paper?
The text was updated successfully, but these errors were encountered:
It seems that the defaut configurations is spitting a video in to clips that contain only one frame. So I think heatmap information from previous frame (whether of ground truth or prediction) is not used. If then, how can I set up config to achieve reported result in the paper?
The text was updated successfully, but these errors were encountered: