search

cvlab-stonybrook / Scanpath_Prediction

Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning (CVPR2020)
MIT License
97 stars 22 forks source link

How to generate a scanpth for an image. #25

Open TianheWu opened 1 year ago

TianheWu commented 1 year ago

I have an image and I want to use your pretrained model to generate the scanpath coordinates for this image. How should I do. Thanks! Please help me!

ouyangzhibo commented 1 year ago

Sorry for the late reply. To generate a scanpath for a new image (not in COCO-Search18), you would need to first compute the DCBs (see https://github.com/cvlab-stonybrook/Scanpath_Prediction/blob/master/extract_DCBs_demo.py). Then you can follow this issue for the rest.