Open ee2110 opened 7 months ago
Thank you for your interest in our work and for your kind words!
We used train/test sets from COIN (https://github.com/salesforce/paprika/blob/cbefd714f3368733b1dc4dc3f2ee1e2ba69f57ed/datasets/coin.py#L32) and created train/test sets for CrossTask on our own using random splits (https://github.com/salesforce/paprika/blob/cbefd714f3368733b1dc4dc3f2ee1e2ba69f57ed/datasets/cross_task.py#L12).
Yes, downstream models were trained on the train set of the downstream datasets before evaluating them on the downstream test set.
We used the pre-trained model to extract features of the video segments that contain steps. These features served as the input to the downstream models (https://github.com/salesforce/paprika/blob/cbefd714f3368733b1dc4dc3f2ee1e2ba69f57ed/datasets/cross_task.py#L201).
Hi, thank you for the great work and interesting ideas!
Hope to get more information about these, I enjoyed reading your work.
Below is the screenshot of a diagram taken from the paper
Thank you.