Learning structural representations for recipe generation and food retrieval
Publication Type
Journal Article
Publication Date
3-2023
Abstract
Food is significant to human daily life. In this paper, we are interested in learning structural representations for lengthy recipes, that can benefit the recipe generation and food cross-modal retrieval tasks. Different from the common vision-language data, here the food images contain mixed ingredients and target recipes are lengthy paragraphs, where we do not have annotations on structure information. To address the above limitations, we propose a novel method to unsupervisedly learn the sentence-level tree structures for the cooking recipes. Our approach brings together several novel ideas in a systematic framework: (1) exploiting an unsupervised learning approach to obtain the sentence-level tree structure labels before training; (2) generating trees of target recipes from images with the supervision of tree structure labels learned from (1); and (3) integrating the learned tree structures into the recipe generation and food cross-modal retrieval procedure. Our proposed model can produce good-quality sentence-level tree structures and coherent recipes. We achieve the state-of-the-art recipe generation and food cross-modal retrieval performance on the benchmark Recipe1M dataset.
Discipline
Databases and Information Systems | Food Science
Research Areas
Data Science and Engineering
Publication
IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume
45
Issue
3
First Page
3363
Last Page
3377
ISSN
0162-8828
Identifier
10.1109/TPAMI.2022.3181294
Publisher
Institute of Electrical and Electronics Engineers
Citation
WANG, Hao; LIN, Guosheng; HOI, Steven C. H.; and MIAO, Chunyan.
Learning structural representations for recipe generation and food retrieval. (2023). IEEE Transactions on Pattern Analysis and Machine Intelligence. 45, (3), 3363-3377.
Available at: https://ink.library.smu.edu.sg/sis_research/9336
Copyright Owner and License
Authors
Additional URL
https://doi.org/10.1109/TPAMI.2022.3181294