The goal of research in automatic image popularity assessment (IPA) is to develop computational models that can accurately predict the potential of a social image to go viral on the Internet. Here, we aim to single out the contribution of visual content to image popularity, i.e., intrinsic image popularity. Specifically, we first describe a probabilistic method to generate massive popularity-discriminable image pairs, based on which the first large-scale image database for intrinsic IPA (I2PA) is established. We then develop computational models for I2PA based on deep neural networks, optimizing for ranking consistency with millions of popularity-discriminable image pairs. Experiments on Instagram and other social platforms demonstrate that the optimized model performs favorably against existing methods, exhibits reasonable generalizability on different databases, and even surpasses human-level performance on Instagram. In addition, we conduct a psychophysical experiment to analyze various aspects of human behavior in I2PA.
Cite
@article{arxiv.1907.01985,
title = {Intrinsic Image Popularity Assessment},
author = {Keyan Ding and Kede Ma and Shiqi Wang},
journal= {arXiv preprint arXiv:1907.01985},
year = {2021}
}