HIGHLIGHTS
SUMMARY
This culture-specific dataset has been used to train a Generative Adversarial Network (GAN), capable of generating 2D samples, which are then fed to a Neural_Network to map the 2-Dimensional generated poses to a 3D space, and finally to the robot`s joints. Given the absence of culture-dependent approaches for gesture generation in the Literature, and considering the main aim of this work, i.e., proposing and evaluating an integrated methodology to generate gestures perceived as culturally International Journal of Social Robotics 14:1493-1506 competent, this approach has not been compared . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.