search

face-analysis / emonet

Official implementation of the paper "Estimation of continuous valence and arousal levels from faces in naturalistic conditions", Antoine Toisoul, Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulos and Maja Pantic, Nature Machine Intelligence, 2021
https://www.nature.com/articles/s42256-020-00280-0
Other
260 stars 62 forks source link

Training and visualization code #1

Open radekd91 opened 3 years ago

radekd91 commented 3 years ago

Hello,

thank you for sharing this great work.. Do you also plan to release the training code and the visualization code you used to generate the impressively looking results?

Speaking of training ... how does one get access to SEWA these days? The signup form is broken.

Thanks a lot :-)

antoinetlc commented 3 years ago

Hello,

Thank you for your message and sorry for taking so much time to answer. There is no plan to release the training and visualization code at the moment but I can answer specific questions on these if you have any. Regarding the SEWA dataset, I do not have the answer unfortunately. I would recommend you to contact the main SEWA authors directly to see how you can access this dataset.

karthik-kk commented 2 years ago

Hello,

Are there any plans to share the visualization code at this point in time or the near future?

If not, can you please provide some pointers on how to go about developing one? -I would like to know what libraries/frameworks are available to build one/visualize the changes in real-time? -Any boilerplate's that could be made use of -Any other info that could provide some insights.

Thanks!