Search Results for author:
Found 3 papers, 2 papers with code
From Just Noticeable Differences to Image Quality
This first JND point provides an intrinsic quantification of the visible distortions within the multimedia content.
Considering user agreement in learning to predict the aesthetic quality
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.
Multi-Modal Aesthetic Assessment for MObile Gaming Image
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
