Homographic Matrix for UCY used in Y-Net

Question

Homographic Matrix for UCY used in Y-Net

Closed this issue 3 years ago · 6 comments

Hi, I am building the dataset for UCY and ETH dataset. To conduct a fair experiment, can you provide the homographic matrix used for UCY? Also, do you use same scene images among uni_examples and UNIV (student00*) as well as among Zara * datasets? Thanks.

Answer 1 · 2021-10-29T00:05:35.000Z

Hi, thanks for your interest in our work. Here are the homography matrices:

https://drive.google.com/drive/folders/1ycxLUluANUXSHNmJQ8w4Nx8nVQXiB2F3.

For univ, we use the same scene images but for zara1,2 there is a very slight difference between the reference images.

Answer 2 · 2021-12-16T19:04:21.000Z

@HRHLALALA Hi, I was wondering if you got similar results as the paper for Y-Net on ETH and UCY dataset. Thanks.

Answer 3 · 2021-12-17T00:49:24.000Z

@HRHLALALA Hi, I was wondering if you got similar results as the paper for Y-Net on ETH and UCY dataset. Thanks.

I am currently using the dataset from Social GAN to train but unfortunately not yet got the results. I will let you know when the results come out.

Answer 4 · 2021-12-17T03:22:55.000Z

Thanks for the quick response!
I see, FYI I've trained a new model using the dataset from Social GAN and for the ETH split I've got

ADE: 0.58 (paper: 0.28)
FDE: 0.84 (paper: 0.33)

This is unfortunately very different from the original numbers in the paper. It would be great if you can check it with yours once you have it.
Thanks.

Answer 5 · 2022-06-25T07:32:31.000Z

Thanks for the quick response! I see, FYI I've trained a new model using the dataset from Social GAN and for the ETH split I've got
ADE: 0.58 (paper: 0.28)
FDE: 0.84 (paper: 0.33)
This is unfortunately very different from the original numbers in the paper. It would be great if you can check it with yours once you have it. Thanks.

Hi @sff1019, I know it may be a little bit outdated, but I am wondering if you have achieved similar numbers on the Social GAN split for the ETH dataset? Any comments would be highly appreciated!

Answer 6 · 2024-02-16T01:55:57.000Z

Thanks for the quick response! I see, FYI I've trained a new model using the dataset from Social GAN and for the ETH split I've got
ADE: 0.58 (paper: 0.28)
FDE: 0.84 (paper: 0.33)
This is unfortunately very different from the original numbers in the paper. It would be great if you can check it with yours once you have it. Thanks.

Hi:
@sff1019,Could you tell me How to implement YNet?What changes have you made based on SDD? Thank you for you help1