Please use this identifier to cite or link to this item:
Title: Decomposing generation networks with structure prediction for recipe generation
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). Decomposing generation networks with structure prediction for recipe generation. Pattern Recognition, 126, 108578-.
Project: AISG-GC-2019-003 
RG28/18 (S) 
RG22/19 (S) 
Journal: Pattern Recognition 
Abstract: Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality. Different from the image captioning task, where the captions usually have one sentence, cooking instructions contain multiple sentences and have obvious structures. To help the model capture the recipe structure and avoid missing some cooking details, we propose a novel framework: Decomposing Generation Networks (DGN) with structure prediction, to get more structured and complete recipe generation outputs. Specifically, we split each cooking instruction into several phases, and assign different sub-generators to each phase. Our approach includes two novel ideas: (i) learning the recipe structures with the global structure prediction component and (ii) producing recipe phases in the sub-generator output component based on the predicted structure. Extensive experiments on the challenging large-scale Recipe1M dataset validate the effectiveness of our proposed model, which improves the performance over the state-of-the-art results.
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2022.108578
Schools: School of Computer Science and Engineering 
Research Centres: Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) 
Rights: © 2022 Elsevier Ltd. All rights reserved. This paper was published in Pattern Recognition and is made available with permission of Elsevier Ltd.
Fulltext Permission: embargo_20240707
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
  Until 2024-07-07
3.72 MBAdobe PDFUnder embargo until Jul 07, 2024

Page view(s)

Updated on Feb 23, 2024

Google ScholarTM




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