CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval

TL;DR

This paper introduces a novel cross-modal hierarchical embedding framework for food retrieval that models complex relationships between images and recipe texts, enabling automatic identification of key recipe components and improving retrieval accuracy.

Contribution

The work presents a new hierarchical embedding model using tree-structured LSTMs for food image-recipe association, capturing complex relationships without explicit supervision.

Findings

Effective identification of main ingredients and actions in recipes

Improved cross-modal retrieval performance

Learned meaningful food recipe representations

Abstract

Despite the abundance of multi-modal data, such as image-text pairs, there has been little effort in understanding the individual entities and their different roles in the construction of these data instances. In this work, we endeavour to discover the entities and their corresponding importance in cooking recipes automaticall} as a visual-linguistic association problem. More specifically, we introduce a novel cross-modal learning framework to jointly model the latent representations of images and text in the food image-recipe association and retrieval tasks. This model allows one to discover complex functional and hierarchical relationships between images and text, and among textual parts of a recipe including title, ingredients and cooking instructions. Our experiments show that by making use of efficient tree-structured Long Short-Term Memory as the text encoder in our computational cross-modal retrieval framework, we are not only able to identify the main ingredients and cooking actions in the recipe descriptions without explicit supervision, but we can also learn more meaningful feature representations of food recipes, appropriate for challenging cross-modal retrieval and recipe adaption tasks.