Recipe recognition with large multimodal food dataset

By Devinder Kumar, Nicolas Thomé, Matthieu Cord, Frédéric Precioso. 2015

259 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Douwe Kiela
2. Mohit Bansal
3. Yejin Choi
4. Samuel R. Bowman
5. Jianfeng Gao
6. Jason Aaron Edward Weston
7. Antonio Torralba
8. Luke S. Zettlemoyer

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Trevor Darrell
4. Andrew Zisserman
5. Cordelia Schmid
6. Jitendra Malik
7. Mohit Bansal
8. Antonio Torralba

In Multimodal Learning

1. Antonio Torralba
2. Adriana Romero
3. Michal Drozdzal
4. Amaia Salvador
5. Yusuf Aytar
6. Joey Tianyi Zhou
7. Davide Testuggine
8. Xavier Giró-i-Nieto

Citations in the corpus

• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes (2020, methodology): “Other datasets using internet data include Food101 [80], where the goal is to predict the dish of recipes and images; various versions of Yelp reviews [52]; Walmart and Ferramenta product classification [90, 21]; social media name tagging (Twitter and Snapchat) [49]; social media target-oriented sent”
• Deep-based Ingredient Recognition for Cooking Recipe Retrieval (2016, methodology): “One of best the performances on UEC Food-100 dataset is achieved by fusion of DCNN features with RootHOG and color moment [15], and similarly for UPMC Food-101 dataset by fusion of textual and deep features [34].”
• Inverse Cooking: Recipe Generation From Food Images (2018, background): “Traditionally, the image-to-recipe problem has been formulated as a retrieval task [54, 3, 4, 45], where a recipe is retrieved from a fixed dataset based on the image similarity score in an embedding space.”
• Recipe1M: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images (2018, background): “For instance, Wang et al. [22] released a multimodal food dataset which has 101k images divided equally among 101 food categories; the recipes for each are however raw HTML.”
• Trusted Multi-View Classification With Dynamic Evidential Fusion (2022, background): “Each sample is provided with both an image and text view [108].”
• Learning Cross-Modal Embeddings for Cooking Recipes and Food Images (2017, background): “The first of which [23] has 101k images divided equally among 101 categories; the recipes for each are however raw HTML.”