makarandtapaswi / ballclustering_iccv2019 Goto Github PK

Please can I give the model images instead of videos ?

Thanks for sharing your work. Do you have any plan to release the training code?

Hello, the link in your previous work of the link to the original face tracks cannot be opened. Is the link invalid now,?
Thanks a lot.

Thanks for sharing your work. Do you have any plan to release your feature extracting network? otherwise, the checkpoint of VGG Face SE-ResNet50-256 features can not be used.
Thanks!

Can you release the training code and loss functions? Otherwise we cannot reproduce the results from paper. Thanks.

Hello, Thanks for your work.

I see that on the Test Data you do L2 Norm to the features is that correct? Wouldn't that throw off the threshold value since it was learned on an unnormalized d^2 euclidean space instead of normalized cosine space?

Also, I was trying to implement the BallClustering loss myself. Is it the same to assume its similar to CenterLoss but instead of the loss being the distances to the Centroid we use the 2 d^2 euclidean constrains to calculate loss? As parameters for the loss I have the centroids (num_classes, num_features) and b_hat (scalar value). It doesn't seem to produce better results than Softmax + Triplet on my datasets can you help me out figuring out what's missing or share your BallClustering Loss to compare with my implementation?

In the paper, you mention the Loss is simply L = alpha * Lsim + Ldis but no mention of Softmax. Is it safe to assume it's both Softmax + BallClustering on just 1 loss?

Thanks.

Hello, when can I open source?