ju-chen/Efficient-Prompt

About K700 openset split

Closed this issue · 4 comments

Thanks for your wonderful work~ I want to know the details about your K700 openset split.

Is it right that videos of 400 classes in the original K700 training split are used for openset training, and videos of the other 300 classes in original K700 val splits are used for openset validation?

Or you directly gather all videos of K700 in both training and val list, and pick 400 classes for training and use the left videos of 300 classes for validation?

I have the same question.
Can you please publish the lists for these two sets of classes?

Sorry for the late reply.
We use videos of 400 classes in the original K700 training split for training, and videos of the other 300 classes in original K700 val splits for evaluation.

But which 400? First 400 or random 400?

Please see ./datasplits/Open-set Action Recognition/K700/