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

What is the value of the variance of 2D Gaussian? #5

Closed kazucmpt closed 5 years ago

kazucmpt commented 5 years ago

The ground truth gaze image is generated from the gaze data by pointing a 2d Gaussian at the gaze position. Put the ground truth gaze maps into path/to/gt/images.

I want to generate the ground truth gaze map, so I need the value of the variance of 2d Gaussian. I could not find that in your paper. Would you tell us that value?

Thank you.

hyf015 commented 5 years ago

For 1280x720 image I used a variance of 70.

kazucmpt commented 5 years ago

Thank you.

So after you generate the ground truth gaze images whose size are 1280×720, you resized the images 224×224 ?

hyf015 commented 5 years ago

Yes, you are right.

kazucmpt notifications@github.com于2018年9月27日 周四下午8:57写道：

Thank you.

So after you generate the ground truth gaze images whose size are 1280720, you resized the images 224244 ?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/hyf015/egocentric-gaze-prediction/issues/5#issuecomment-425062860, or mute the thread https://github.com/notifications/unsubscribe-auth/AVSGeG2wbKBUGqjGnfOiTIv7w5vkgi32ks5ufL0cgaJpZM4W24hL .

kazucmpt commented 5 years ago

I understood well. Thank you very much.