Search Results for author:
Found 2 papers, 0 papers with code
Light-weighted Saliency Detection with Distinctively Lower Memory Cost and Model Size
The runtime memory cost of our approach is 42 to 99 times fewer comparing with the previous DNNs based methods.
Learning Saliency Prediction From Sparse Fixation Pixel Map
In this work, we propose a first-of-its-kind approach of learning saliency prediction from sparse fixation pixel map, and a novel loss function for training from such sparse fixation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
