Anonyme

Results 3 comments of Anonyme

Why use " labels.append(np.ones(dists.size(0)))" in training? and

Hi, thank you for you nice job! I feel puzzled why there is only the 'triplet_loss' but no 'CrossEntropyLoss' during training. It seems that 'model.module.forward_classifier' here not be used to...

Codes for weakly supervised action segmentation

> Hi, > > Thanks for the very refreshing paper! It seems that this repository only contains codes for TSC. I am wondering if you have plans to release the...

Question about sparsity and pruning of the model

> Hi, Meteor, > > I am very glad that you are interested in this paper. Your questions are very representative! > > For the first question, yes. There are...