Please use this identifier to cite or link to this item:
Title: Mixed-dish Recognition with Contextual Relation Networks
Authors: Lixi Deng
Jingjing Chen 
Qianru Sun 
Xiangnan He 
Sheng Tang 
Zhaoyan Ming 
Yongdong Zhang
Tat-Seng Chua 
Keywords: Context modeling
Food recognition
Multiple dish detection
Issue Date: 21-Oct-2019
Citation: Lixi Deng, Jingjing Chen, Qianru Sun, Xiangnan He, Sheng Tang, Zhaoyan Ming, Yongdong Zhang, Tat-Seng Chua (2019-10-21). Mixed-dish Recognition with Contextual Relation Networks. ACM MM 2019 : 112-120. ScholarBank@NUS Repository.
Abstract: Mixed dish is a food category that contains different dishes mixed in one plate, and is popular in Eastern and Southeast Asia. Recognizing individual dishes in a mixed dish image is important for health related applications, e.g. calculating the nutrition values. However, most existing methods that focus on single dish classification are not applicable to mixed-dish recognition. The new challenge in recognizing mixed-dish images are the complex ingredient combination and severe overlap among different dishes. In order to tackle these problems, we propose a novel approach called contextual relation networks (CR-Nets) that encodes the implicit and explicit contextual relations among multiple dishes using region-level features and label-level co-occurrence, respectively. This is inspired by the intuition that people are likely to choose dishes with common eating habits, e.g., with multiple nutrition but without repeating ingredients. In addition, we collect a large-scale dataset of mixed-dish images that contain 9, 254 mixed-dish images from 6 school canteens in Singapore. Extensive experiments on both our dataset and a smaller-scale public dataset validate that our CR-Nets can achieve top performance for localizing the dishes and recognizing their food categories. © 2019 Association for Computing Machinery.
Source Title: ACM MM 2019
ISBN: 9781450368896
DOI: 10.1145/3343031.3351147
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
3343031.3351147.pdf3.46 MBAdobe PDF




checked on Sep 19, 2020

Page view(s)

checked on Sep 17, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.