Daochang Liu

icon indicating a website link https://finspire13.github.io/ icon indicating an email [email protected]

icon location Beijing icon location Researcher@USYD

Results 3 comments of Daochang Liu

Cue Generation and Dataset

Thanks for bring this to my attention. Please find the new link: https://drive.google.com/file/d/1URJGJGEp1VgtKVMM3gPkie6x69uuE3eZ/view?usp=share_link

Request for pre processing code release

Hi mustafa, thank you for the question. The ResNet features are extracted using the pre-trained ResNet-101 in torchvision. And the augmentation is just the TenCrop transform in torchvision. I don't...

Model weights

Hi, thanks for interest. Here is the [trained model](https://drive.google.com/file/d/1NRGTH2A6jJ-PZ9xpIOtD32suJfsI4Xt6/view?usp=sharing) for setting 'SS-full'.