Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

When will the ground truth answers be made public? #1

Open
yuanliping opened this issue Dec 9, 2024 · 3 comments
Open

When will the ground truth answers be made public? #1

yuanliping opened this issue Dec 9, 2024 · 3 comments

Comments

@yuanliping
Copy link

When will the ground truth answers be made public?

@keshik6
Copy link
Owner

keshik6 commented Dec 12, 2024

We won't be releasing the ground truth answers (both test and dev sets). You can submit your results to the evaluation server (will be available soon) to benchmark your methods on HourVideo. We provide ground truth annotations for 2 sample videos here.

Thanks.

@helloYwen123
Copy link

We won't be releasing the ground truth answers (both test and dev sets). You can submit your results to the evaluation server (will be available soon) to benchmark your methods on HourVideo. We provide ground truth annotations for 2 sample videos here.

Thanks.

:) I understand the need for anonymity in the test set, but why is the dev set also not released? Two sample videos are far from sufficient for proper development and tuning. Without the dev ground truth, the dataset is nearly unusable for meaningful experimentation. Could you clarify the reasoning behind keeping both dev and test sets anonymous?

@Wiselnn570
Copy link

We won't be releasing the ground truth answers (both test and dev sets). You can submit your results to the evaluation server (will be available soon) to benchmark your methods on HourVideo. We provide ground truth annotations for 2 sample videos here.
Thanks.

:) I understand the need for anonymity in the test set, but why is the dev set also not released? Two sample videos are far from sufficient for proper development and tuning. Without the dev ground truth, the dataset is nearly unusable for meaningful experimentation. Could you clarify the reasoning behind keeping both dev and test sets anonymous?

same concern

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants