no code implementations • 15 Jan 2019 • Shanghua Xiao
The runtime memory cost of our approach is 42 to 99 times fewer comparing with the previous DNNs based methods.
no code implementations • 3 Sep 2018 • Shanghua Xiao
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.