shuffle-tuple
shuffle-tuple copied to clipboard
Finetune dataset
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 please tell me that do you use the label of test split 1 of UCF101 to fine-tune? If not, then what is the ground-truth? The tuple verification? Thanks a lot!