Datasets
Code
This is an alpha version of the nod shake detector trained on SSPNet data. The detector includes the Viola & Jones face detector and will work fine for most near-frontal-view and profile faces. The detector outputs a .CSV file with its prediction for each frame (1 for nod, 2 for shake, 0 for otherwise) and also whether the face was detected by Viola & Jones at that frame (1 for yes, 0 for no).
More information about the point detector can be found in: H. Gunes and M. Pantic, "Dimensional Emotion Prediction from Spontaneous Head Gestures for Interaction with Sensitive Artificial Listeners", in Proc. Int'l Conf. on Intelligent Virtual Agents (IVA'10), pp. 371-377, 2010. We kindly request you to cite this work if you decide to use the point detector for research purposes.
The Matlab implementation was written by Konstantinos Bousmalis based on code written by Hatice Gunes. The code has been compiled on a Windows machine, hence this downloadable version of our detector will work only on a Windows machine. You will need Matlab Component Runtime installed at your computer for the program to run.