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
I was looking at your paper. Could you please explain how to apply VCLR at video level and not on frame level? How do I modify the dataloader to input video clips into the model? Here you are only taking frame level inputs from the segments?
That basically means how do I modify the code for the calculation of L_inter, L_intra, L_segment and L_order for 3D CNNs for pre-training?
Thank you
The text was updated successfully, but these errors were encountered:
Hi @KuangHaofei and @bryanyzhu
I was looking at your paper. Could you please explain how to apply VCLR at video level and not on frame level? How do I modify the dataloader to input video clips into the model? Here you are only taking frame level inputs from the segments?
That basically means how do I modify the code for the calculation of L_inter, L_intra, L_segment and L_order for 3D CNNs for pre-training?
Thank you
The text was updated successfully, but these errors were encountered: