eddie-hwang/nslp-g

This is repository for NSLP-G.

nslp-g's Issues

Release of the model weights

Hi,

Your work has a really interesting idea, thanks for releasing the complete code!
Could you share the model weights, please?

Thanks in advance,

When will the code will be released?

Hi,
thank you for you work!

When is the code will be release?

Best regards,

Data Pre-Processing

Hello Hwang,
you mentioned that the data classes are implemented in scripts/data.py, but I can not find the data.py file.
Also, I am currently trying 3D Pose Estimator(https://github.com/gopeith/SignLanguageProcessing) to lift up 2D into 3D keypoints of Pose and Facial keypoints, but the results are not good. It would be great if you can share the information how you pre-processed the data. If it is possible, please send me an Email about the information. [email protected]
Thanks,

PHOENIX14T

Hello, Eddie,
I noticed you used the same method with the paper "Progressive Transformer for end-to-end sign language production" to get the 3d skeletal joint coordinates, I also followed this method and generated the coordinates data (360 coordinates including face and body). But the quality of the extracted 3D coordinates is not that good. Can you share your pre-processed PHOENIX14T data with me? I would appreciate it if you could share the pre-processed PHOENIX14T data. Here is my email address: [email protected]. Thank you very much.

When the complete code will be released?

Thanks for your contribution, great paper!

I just saw that the VAE part of the code was recently released, when the complete code will be released?

Thanks in advance,

Ask about Sanders's model

Dear author，

Hi, you implemented Saunders' model using the new framework, so do you know why the video is not generated when his model is set with text? Only gloss mode generates videos......

I hope you can help me with this problem. Thank you very much.