Learning Cross-Modal Embeddings for Cooking Recipes and Food Images

@article{Salvador2017LearningCE,
  title={Learning Cross-Modal Embeddings for Cooking Recipes and Food Images},
  author={Amaia Salvador and Nicholas Hynes and Yusuf Aytar and Javier Mar{\'i}n and Ferda Ofli and Ingmar Weber and Antonio Torralba},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={3068-3076}
}
  • Amaia Salvador, Nicholas Hynes, +4 authors Antonio Torralba
  • Published in
    IEEE Conference on Computer…
    2017
  • Computer Science
  • In this paper, we introduce Recipe1M, a new large-scale, structured corpus of over 1m cooking recipes and 800k food images. [...] Key Method Using these data, we train a neural network to find a joint embedding of recipes and images that yields impressive results on an image-recipe retrieval task. Additionally, we demonstrate that regularization via the addition of a high-level classification objective both improves retrieval performance to rival that of humans and enables semantic vector arithmetic. We…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 115 CITATIONS, ESTIMATED 77% COVERAGE

    Inverse Cooking: Recipe Generation From Food Images

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS

    CookGAN: Meal Image Synthesis from Ingredients

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model

    VIEW 11 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A Survey of Automatic Methods for Nutritional Assessment

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A Survey on Food Computing

    VIEW 8 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Deep Cooking: Predicting Relative Food Ingredient Amounts from Images

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 30 Highly Influenced Citations

    • Averaged 31 Citations per year from 2017 through 2019

    • 15% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 44 REFERENCES

    Efficient Estimation of Word Representations in Vector Space

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Im2Calories: Towards an Automated Mobile Vision Food Diary

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Cross-Modal Scene Networks

    VIEW 1 EXCERPT

    Finding Beans in Burgers: Deep Semantic-Visual Embedding with Localization

    VIEW 1 EXCERPT

    Places: A 10 Million Image Database for Scene Recognition

    VIEW 2 EXCERPTS