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
论文中msvd的实验结果问题 #2
Comments
我们用Frozen开源的模型,在MSVD上以"Sentence-to-Video"的测评方式得到了zero-shot和fine-tuning的结果。其中arxiv上Frozen的zero-shot结果有误,应该是R@1: 38.7, R@5: 70.1, R@10 80.1, MeanR: 12.7。感谢你的提问,我们会在后续更正Frozen的这一结果,并且开源MSVD数据集上的测评代码。 |
您好,我想确认下论文中关于Frozen的zero-shot的R1=33.7以及fine-tuning的R1=45.6是你们利用Frozen开源模型复现的结果?因为他们的论文中并没有提到33.7是zero-shot or fine-tuning的结果,且paperwithcode网站(https://paperswithcode.com/sota/video-retrieval-on-msvd)上也用33.7作为他们得分的标准和其他fine-tuning的结果进行比较。
…------------------ 原始邮件 ------------------
发件人: "TencentARC/MCQ" ***@***.***>;
发送时间: 2022年4月14日(星期四) 下午2:39
***@***.***>;
***@***.******@***.***>;
主题: Re: [TencentARC/MCQ] 论文中msvd的实验结果问题 (Issue #2)
We use the released model from Frozen (https://github.com/m-bain/frozen-in-time) for zero-shot evaluation on msvd.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
论文表2(a)中msvd检索结果引用了Frozen的,zero-shot为33.7,fine-tuning为45.6。请问这个结果是复现得到还是原论文中的?我在原Frozen论文中只看到了一个33.7的R@1,应该是fine-tuning的结果。
The text was updated successfully, but these errors were encountered: