Closed ttgeng233 closed 2 years ago
Hi, since our method are not designed for multi-label datasets, you may need a little bit tweak to our current models.
Current cls head uses Focal loss, which already supports multi-label groundtruths. However, current regression head is class-agnostic, , you may need to design a class-aware regression head and modify the code.
Thank you very much, is there noting to do with NMS? if some modifications are needed during inference?
Hi, I think our current code already supports multi-class NMS. However, our code can not handle the case that multiple actions with same labels occurs at same time.
Closed due to inactivity.
Thanks for your great work! The datasets that used here are all single-label datasets where there is just one action per time-step? Can this model be used on multi-label datasets (i. e., MultiTHUMOS, Charades) by replacing loss functions or just replacing nms with multi-class nms.