English

Learning Program Representations for Food Images and Cooking Recipes

Computer Vision and Pattern Recognition 2022-03-31 v1

Abstract

In this paper, we are interested in modeling a how-to instructional procedure, such as a cooking recipe, with a meaningful and rich high-level representation. Specifically, we propose to represent cooking recipes and food images as cooking programs. Programs provide a structured representation of the task, capturing cooking semantics and sequential relationships of actions in the form of a graph. This allows them to be easily manipulated by users and executed by agents. To this end, we build a model that is trained to learn a joint embedding between recipes and food images via self-supervision and jointly generate a program from this embedding as a sequence. To validate our idea, we crowdsource programs for cooking recipes and show that: (a) projecting the image-recipe embeddings into programs leads to better cross-modal retrieval results; (b) generating programs from images leads to better recognition results compared to predicting raw cooking instructions; and (c) we can generate food images by manipulating programs via optimizing the latent code of a GAN. Code, data, and models are available online.

Keywords

Cite

@article{arxiv.2203.16071,
  title  = {Learning Program Representations for Food Images and Cooking Recipes},
  author = {Dim P. Papadopoulos and Enrique Mora and Nadiia Chepurko and Kuan Wei Huang and Ferda Ofli and Antonio Torralba},
  journal= {arXiv preprint arXiv:2203.16071},
  year   = {2022}
}

Comments

CVPR 2022 oral

R2 v1 2026-06-24T10:31:19.704Z