search

hyf015 / egocentric-gaze-prediction

Code for the paper "Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition"
62 stars 18 forks source link

computeAAEAUC #20

Closed kylemin closed 5 years ago

kylemin commented 5 years ago

In the function of computeAAEAUC, why it is necessary to subtract 112 from each indices of x and y?

r1 = np.array([predicted[0]-112, predicted[1]-112, d])
r2 = np.array([i-112, j-112, d])
hyf015 commented 5 years ago

By this means we move the viewpoint to be the center of the image.