1 code implementation • ACMMM 2022 • Ali Ak, Andreas Pastor, Patrick Le Callet
This first JND point provides an intrinsic quantification of the visible distortions within the multimedia content.
1 code implementation • 13 Oct 2021 • Suiyi Ling, Andreas Pastor, Junle Wang, Patrick Le Callet
In this paper, we thus propose (1) a re-adapted multi-task attention network to predict both the mean opinion score and the standard deviation in an end-to-end manner; (2) a brand-new confidence interval ranking loss that encourages the model to focus on image-pairs that are less certain about the difference of their aesthetic scores.
no code implementations • 27 Jan 2021 • Zhenyu Lei, Yejing Xie, Suiyi Ling, Andreas Pastor, Junle Wang, Patrick Le Callet
Our inclination is to seek and learn the correlations between different aesthetic relevant dimensions to further boost the generalization performance in predicting all the aesthetic dimensions.