Improving saliency models' predictions of the next fixation with humans' intrinsic cost of gaze shifts

arXiv:2207.04250v3 Announce Type: replace
Abstract: The human prioritization of image regions can be modeled in a time invariant fashion with saliency maps or sequentially with scanpath models. However, while both types of models have steadily improved on several benchmarks and datasets, there is still a considerable gap in predicting human gaze. Here, we leverage two recent developments to reduce this gap: theoretical analyses establishing a principled framework for predicting the next gaze target and the empirical measurement of the human …

abstract arxiv benchmarks cost cs.cv datasets fashion human humans image intrinsic maps next predictions type types