OpenGVLab/EgoVideo

code for NLQ fusion

Yisen-Feng opened this issue · 2 comments

Yisen-Feng commented

Hi,

Thank you for releasing the features. I was unable to find the code to fuse the features. I'm interested in reproducing the results of the paper on the NLQ dataset. Can you share these codes?
image

cg1177 commented

Hello, this fusion method is to concatenate all features along channel dimension and modify the input channels of the first projector.

Yisen-Feng commented

Hello, this fusion method is to concatenate all features along channel dimension and modify the input channels of the first projector.

thanks for your reply