Recipe1M: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images
By Amaia Salvador, Nick Hynes, Yusuf Aytar, Javier Marín, Ferda Ofli, Ingmar Weber, Antonio Torralba. arXiv.org, 2018
386 citations recorded by the source corpus.
In this paper, we introduce Recipe1M+, a new large-scale, structured corpus of over one million cooking recipes and 13 million food images. As the largest publicly available collection of recipe data, Recipe1M+ affords the ability to train high-capacity modelson aligned, multimodal data. Using these data, we train a neural network to learn a joint embedding of recipes and images that yields impressive results on an image-recipe retrieval task. Moreover, 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 postulate that these embeddings will provide a basis for further exploration of the Recipe1M+ dataset and food and cooking in general. Code, data and models are publicly available.
Subfields: Biomedical Engineering, Food Science, Public Health, Environmental and Occupational Health
View Paper: https://www.semanticscholar.org/paper/048d133e2ec513ce385c8e736df715d8ff496e17
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
- Mingmin Zhao
- Antonio Torralba
- Adriana Romero
- Dina Katabi
- Yonglong Tian
- Amaia Salvador
- Michal Drozdzal
- Mohammad Abu Alsheikh
In Food Science
Citations in the corpus
- Milvus: A Purpose-Built Vector Data Management System (2021, methodology): “per entity, we then use another dataset called Recipe1M [50, 56] that includes more than one million cooking recipes and food images.”
- Deep Learning on Small Datasets without Pre-Training using Cosine Loss (2019, background): “It furthermore enjoys popularity in the area of cross-modal embeddings, where different representations of the same entity, such as images and text, should be close together in a joint embedding space [39, 35].”
- Inverse Cooking: Recipe Generation From Food Images (2018, methodology): “The average number of ingredients per sample in Recipe1M is 7.99 ± 3.21 after pre-processing.”
- Through-Wall Human Pose Estimation Using Radio Signals (2018, background): “In terms of modeling, our work is related to cross-modal and multi-modal learning that explores matching different modalities or delivering complementary information across modalities [8, 11, 36, 34].”
- RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation (2020, background): “One of the results was the publication of the Recipe1M+ (Salvador et al., 2017) (Marin et al., 2019) dataset containing both recipes and images.”