Learning from web recipe-image pairs for food recognition: Problem, baselines and performance
Cross-modal recipe retrieval has recently been explored for food recognition and understanding. Text-rich recipe provides not only visual content information (e.g., ingredients, dish presentation) but also procedure of food preparation (cutting and cooking styles). The paired data is leveraged to tr...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7246 https://ink.library.smu.edu.sg/context/sis_research/article/8249/viewcontent/tmm2021_zhu_ngo_chan.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8249 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-82492024-07-12T10:04:58Z Learning from web recipe-image pairs for food recognition: Problem, baselines and performance ZHU, Bin NGO, Chong-wah CHAN, Wing-Kwong Cross-modal recipe retrieval has recently been explored for food recognition and understanding. Text-rich recipe provides not only visual content information (e.g., ingredients, dish presentation) but also procedure of food preparation (cutting and cooking styles). The paired data is leveraged to train deep models to retrieve recipes for food images. Most recipes on the Web include sample pictures as the references. The paired multimedia data is not noise-free, due to errors such as pairing of images containing partially prepared dishes with recipes. The content of recipes and food images are not always consistent due to free-style writing and preparation of food in different environments. As a consequence, the effectiveness of learning cross-modal deep models from such noisy web data is questionable. This paper conducts an empirical study to provide insights whether the features learnt with noisy pair data are resilient and could capture the modality correspondence between visual and text. 2022-01-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7246 info:doi/10.1109/TMM.2021.3123474 https://ink.library.smu.edu.sg/context/sis_research/article/8249/viewcontent/tmm2021_zhu_ngo_chan.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Image recognition;Training;Generative adversarial networks;Feature extraction;Visualization;Data models;Context modeling;Food recognition;image-to-recipe retrieval;image-to-image retrieval Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Image recognition;Training;Generative adversarial networks;Feature extraction;Visualization;Data models;Context modeling;Food recognition;image-to-recipe retrieval;image-to-image retrieval Databases and Information Systems |
spellingShingle |
Image recognition;Training;Generative adversarial networks;Feature extraction;Visualization;Data models;Context modeling;Food recognition;image-to-recipe retrieval;image-to-image retrieval Databases and Information Systems ZHU, Bin NGO, Chong-wah CHAN, Wing-Kwong Learning from web recipe-image pairs for food recognition: Problem, baselines and performance |
description |
Cross-modal recipe retrieval has recently been explored for food recognition and understanding. Text-rich recipe provides not only visual content information (e.g., ingredients, dish presentation) but also procedure of food preparation (cutting and cooking styles). The paired data is leveraged to train deep models to retrieve recipes for food images. Most recipes on the Web include sample pictures as the references. The paired multimedia data is not noise-free, due to errors such as pairing of images containing partially prepared dishes with recipes. The content of recipes and food images are not always consistent due to free-style writing and preparation of food in different environments. As a consequence, the effectiveness of learning cross-modal deep models from such noisy web data is questionable. This paper conducts an empirical study to provide insights whether the features learnt with noisy pair data are resilient and could capture the modality correspondence between visual and text. |
format |
text |
author |
ZHU, Bin NGO, Chong-wah CHAN, Wing-Kwong |
author_facet |
ZHU, Bin NGO, Chong-wah CHAN, Wing-Kwong |
author_sort |
ZHU, Bin |
title |
Learning from web recipe-image pairs for food recognition: Problem, baselines and performance |
title_short |
Learning from web recipe-image pairs for food recognition: Problem, baselines and performance |
title_full |
Learning from web recipe-image pairs for food recognition: Problem, baselines and performance |
title_fullStr |
Learning from web recipe-image pairs for food recognition: Problem, baselines and performance |
title_full_unstemmed |
Learning from web recipe-image pairs for food recognition: Problem, baselines and performance |
title_sort |
learning from web recipe-image pairs for food recognition: problem, baselines and performance |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2022 |
url |
https://ink.library.smu.edu.sg/sis_research/7246 https://ink.library.smu.edu.sg/context/sis_research/article/8249/viewcontent/tmm2021_zhu_ngo_chan.pdf |
_version_ |
1814047649620295680 |