marcellacornia / sam

Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model. IEEE Transactions on Image Processing (2018)
https://ieeexplore.ieee.org/document/8400593
MIT License
205 stars 76 forks source link

How to learn the prior maps in your method? #42

Open Andantino97 opened 3 years ago

Andantino97 commented 3 years ago

Hi, Thanks for your excellent work, here I wanna know about the prior map.

However, rather than knowing how to use the prior maps, I'd like to know more about how you get the prior maps. What does the learn mean in learned priors? Is there another network to learn to generate the prior maps? Or is there any ground truth to train the network to produce the prior maps?

Looking forward to your reply!