Tianhong Li

Thanks a lot! I went to that repo and download the toolbox. However, I found the render_body_impl function used in experiments/config/demo_up/write_output different from the actual function in https://github.com/classner/up. How can...

Hi, thanks for your interest! Please refer to this supplementary material -- I submitted with the CVPR camera ready but I don't know why it does not appear online. For...

Hi, thanks for your interest! Please refer to this supplementary material -- I submitted with the CVPR camera ready but I don't know why it does not appear online. For...

Our implementation in Cifar is not based on the moco and imagenet framework, so it could be hard to directly adapt the released code to Cifar. Our implementation in Cifar...

Please see the attachment of the previous email On Fri, Jul 28, 2023 at 3:11 AM Angelina1996 ***@***.***> wrote: > Thanks so much, Tianhong, for your kind help. It makes...

On CIFAR10, since the number of classes is smaller than the output dimension for contrastive loss, the targets can be directly computed without using gradient descent (see section 3.1 of...

Hi, it seems there are some discrepancies between email and the Github reply -- I thought the attachment in the email apply will also appear here. I just uploaded the...

Please check the cifar_dirty sub directory. It should contain every necessary file.

Just uploaded. This file would be also easy to generate, as there is a analytical optimal solution for target positions when the number of classes

Hi, thanks for your interest! Please refer to this supplementary material [here](https://github.com/LTH14/targeted-supcon/blob/master/supp_release.pdf) -- I submitted with the CVPR camera ready but I don't know why it does not appear online....