Abduallah Mohamed

@suke27 I garee with you, But I think it should be: alpha*(1.0-ms_ssim_loss)+(1-alpha)*L1_loss

Same

Hi, This means you predicted bad parameters that could not construct a correct covariance matrix. Try adjusting the learning rate. On Thu, Jun 15, 2023 at 7:08 AM Jasmine ***@***.***>...

Hi, Please see our work "Social-Implicit" for better visualization. Some frames without pedestrians were omitted.

Thanks! 1- Manually annotated. See the ETH-UCY datasets source paper about this. 2- As you said using Homography matrix. You can find it within the datasets source as in (1)

Hi Wang, Thanks for reaching out. Relative position is a form of normalization for the data. Other methods are relative change w.r.t initial point, middle or last observed point. Also,...

There is no issue in using FD (computation cost?) The step_rel amplifies noise too. Probably, changing the "normalization" method can enhance the results, by how much % vs current results...

Thanks for asking. This data loader is taken from Social-GAN. 1- Relative to the first position, they are also delta between position aka speed 2- This is a very old...

I'm not sure about windows as I never used it before for development.

Hi, Please check the visualization section https://github.com/abduallahmohamed/Skeleton-Graph#visualization