Why Does a Visual Question Have Different Answers?

Abstract

Visual question answering is the task of returning the answer to a question about an image. A challenge is that different people often provide different answers to the same visual question. To our knowledge, this is the first work that aims to understand why. We propose a taxonomy of nine plausible reasons, and create two labelled datasets consisting of 45,000 visual questions indicating which reasons led to answer differences. We then propose a novel problem of predicting directly from a visual question which reasons will cause answer differences as well as a novel algorithm for this purpose. Experiments demonstrate the advantage of our approach over several related baselines on two diverse datasets. We publicly share the datasets and code at https://vizwiz.org.

Cite

Text

Bhattacharya et al. "Why Does a Visual Question Have Different Answers?." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00437

Markdown

[Bhattacharya et al. "Why Does a Visual Question Have Different Answers?." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/bhattacharya2019iccv-visual/) doi:10.1109/ICCV.2019.00437

BibTeX

@inproceedings{bhattacharya2019iccv-visual,
  title     = {{Why Does a Visual Question Have Different Answers?}},
  author    = {Bhattacharya, Nilavra and Li, Qing and Gurari, Danna},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00437},
  url       = {https://mlanthology.org/iccv/2019/bhattacharya2019iccv-visual/}
}