Questions about preprocess for downstream tasks

[dreamerlin]

Thanks for your great work.

I would like to use your repo (https://github.com/EGO4D/episodic-memory) for downstream tasks. So, I want to ask some questions about the pre-process for these tasks. Should I also resize and chunk the clips (provided by the official Ego4d) same as the EgoVLP?

[QinghongLin]

Hi!
If you want to use the checkpoint to extract features for NLQ, yes, please try to chunk and resize them as 256 (short size).
btw, you can directly download the nlq & mq features have provided in the repo.

[dreamerlin]

Seemingly no need to chunk