Please use this identifier to cite or link to this item:
Title: Learning structural representations for recipe generation and food retrieval
Authors: Wang, Hao
Lin, Guosheng
Hoi, Steven C. H.
Miao, Chunyan
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: Wang, H., Lin, G., Hoi, S. C. H. & Miao, C. (2022). Learning structural representations for recipe generation and food retrieval. IEEE Transactions On Pattern Analysis and Machine Intelligence.
Project: AISG-GC-2019-003
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
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.
ISSN: 0162-8828
DOI: 10.1109/TPAMI.2022.3181294
Rights: © 2022 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Page view(s)

Updated on Dec 3, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.