?
Determines the standard deviation of the Gaussian distribution for sampled latent codes. Values greater than 1 will increase the variance of gestures, but might add some artifacts.
JSON Data
Raw Typing Data JSON
The models shown here come from our papers on generating typing with GAN:
WordGesture-GAN: Modeling Word-Gesture Movement with Generative Adversarial Network Jeremy Chu, Dongsheng An, Yan Ma, Wenzhe Cui, Shumin Zhai, Xianfeng David Gu, Xiaojun Bi (2023)
"WordGesture-GAN: Modeling Word-Gesture Movement with Generative Adversarial Network".
In Proceedings of CHI 2023 - the SIGCHI Conference on Human Factors in Computing Systems.
Article No.: 287. Pages 1-15.
TouchType-GAN: Modeling Touch Typing with Generative Adversarial Network Jeremy Chu, Yan Ma, Shumin Zhai, Xianfeng David Gu, and Xiaojun Bi. 2023.
"TouchType-GAN: Modeling Touch Typing with Generative Adversarial Network".
In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST '23).
Article No.: 29. Pages 1–13.