Detecting Persuasive Atypicality by Modeling Contextual Compatibility

Abstract

We propose a new approach to detect atypicality in persuasive imagery. Unlike atypicality which has been studied in prior work, persuasive atypicality has a particular purpose to convey meaning, and relies on understanding the common-sense spatial relations of objects. We propose a self-supervised attention-based technique which captures contextual compatibility, and models spatial relations in a precise manner. We further experiment with capturing common sense through the semantics of co-occurring object classes. We verify our approach on a dataset of atypicality in visual advertisements, as well as a second dataset capturing atypicality that has no persuasive intent.

Cite

Text

Guo et al. "Detecting Persuasive Atypicality by Modeling Contextual Compatibility." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00101

Markdown

[Guo et al. "Detecting Persuasive Atypicality by Modeling Contextual Compatibility." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/guo2021iccv-detecting/) doi:10.1109/ICCV48922.2021.00101

BibTeX

@inproceedings{guo2021iccv-detecting,
  title     = {{Detecting Persuasive Atypicality by Modeling Contextual Compatibility}},
  author    = {Guo, Meiqi and Hwa, Rebecca and Kovashka, Adriana},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {972-982},
  doi       = {10.1109/ICCV48922.2021.00101},
  url       = {https://mlanthology.org/iccv/2021/guo2021iccv-detecting/}
}