Giters

salesforce / ALPRO

Align and Prompt: Video-and-Language Pre-training with Entity Prompts

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

MSR-VTT dataset split

chaochen99 opened this issue · comments

commented

Hi,
Thanks for sharing the code!

I saw "use 7k videos for training and report results on the 1k test split" in your paper. When I downloaded the MSR-VTT dataset, there are only 7K train sets and 3K test sets, but no val dataset. Could you share the code for dividing the dataset to avoid discrepancies in results?

Looking forward to your reply.

commented

Once you downloaded and unzipped the data.zip, you will be able to find the annotations by split in e.g. msrvtt_ret directory. This partition follows the common partition protocol in previous works. Thanks.