Jiangliu Wang

Hello, Imisra. In your paper, you said that the pretrain dataset is the training split 1 of UCF101, and the fine-tune dataset is **test split 1 of UCF101**. Could you...

Finetune process

3

Hello HsinYing, nice work! I am wondering how do you finetune the unsupervised UCF101 dataset. In your paper, you report mean classification accuracy over the 3 splits of UCF101 dataset....

Dataset with RGB frames

1

Hi Okan, Interesting work! I am quite curious about the reason why you only collect the depth and infrared frames. I believe that RGB frame is more widely used in...

ucf101 train from scratch

5

Use the train_c3d_ucf101.py to train the ucf101 dataset from scratch, I can only get ~30% acc, which is much more lower than the reported ~45% accuracy. Can anyone get higher...

Hi, thanks for sharing the code. I am wondering which part of your code indicates that the algorithm is curriculum learning as I didn't manage to find it. Could you...