Compare and Contrast: Learning Prominent Visual Differences

@article{Chen2018CompareAC,
  title={Compare and Contrast: Learning Prominent Visual Differences},
  author={S. Chen and K. Grauman},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={1267-1276}
}
  • S. Chen, K. Grauman
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • Relative attribute models can compare images in terms of all detected properties or attributes, exhaustively predicting which image is fancier, more natural, and so on without any regard to ordering. However, when humans compare images, certain differences will naturally stick out and come to mind first. These most noticeable differences, or prominent differences, are likely to be described first. In addition, many differences, although present, may not be mentioned at all. In this work, we… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 53 REFERENCES
    Just Noticeable Differences in Visual Attributes
    33
    Deep Relative Attributes
    53
    Fine-Grained Visual Comparisons with Local Learning
    243
    Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
    63
    Relative Parts: Distinctive Parts for Learning Relative Attributes
    43
    Relative attributes
    809
    Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing
    24
    Attribute2Image: Conditional Image Generation from Visual Attributes
    492
    Attribute and simile classifiers for face verification
    1343
    High level describable attributes for predicting aesthetics and interestingness
    393