{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T02:09:09Z","timestamp":1768442949256,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61525206,61572472,61871004"],"award-info":[{"award-number":["61525206,61572472,61871004"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["NExT++ project"],"award-info":[{"award-number":["NExT++ project"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351147","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"112-120","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Mixed-dish Recognition with Contextual Relation Networks"],"prefix":"10.1145","author":[{"given":"Lixi","family":"Deng","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianru","family":"Sun","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyan","family":"Ming","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tat Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2831627"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.117"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.83"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70742-6_37"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 25th ACM international conference on Multimedia. ACM, 1771--1779","author":"Ngo Chong-Wah","year":"2017","unstructured":"Jing-jing Chen, Chong-Wah Ngo , and Tat-Seng Chua . 2017 . Cross-modal recipe retrieval with rich food attributes . In Proceedings of the 25th ACM international conference on Multimedia. ACM, 1771--1779 . Jing-jing Chen, Chong-Wah Ngo, and Tat-Seng Chua. 2017. Cross-modal recipe retrieval with rich food attributes. In Proceedings of the 25th ACM international conference on Multimedia. ACM, 1771--1779."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1818719.1818817"},{"key":"e_1_3_2_1_9_1","volume-title":"Chinese- FoodNet: A large-scale image dataset for chinese food recognition. arXiv preprint arXiv:1705.02743","author":"Chen Xin","year":"2017","unstructured":"Xin Chen , Yu Zhu , Hua Zhou , Liang Diao , and Dongyan Wang . 2017. Chinese- FoodNet: A large-scale image dataset for chinese food recognition. arXiv preprint arXiv:1705.02743 ( 2017 ). Xin Chen, Yu Zhu, Hua Zhou, Liang Diao, and Dongyan Wang. 2017. Chinese- FoodNet: A large-scale image dataset for chinese food recognition. arXiv preprint arXiv:1705.02743 (2017)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2986035.2986047"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2017.145"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.23919\/MVA.2017.7986835"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230519.3230594"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63309-1_25"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2986035.2986042"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings on the International Conference on Artificial Intelligence (ICAI). The Steering Committee of The World Congress in Computer Science, 22--28","author":"Heng Zhao","year":"2018","unstructured":"Zhao Heng , Sharmili Roy , Kim-Hui Yap , Alex Kot , and Lingyu Duan . 2018 . Personalized Knowledge Distillation-based Mobile Food Recognition . In Proceedings on the International Conference on Artificial Intelligence (ICAI). The Steering Committee of The World Congress in Computer Science, 22--28 . Zhao Heng, Sharmili Roy, Kim-Hui Yap, Alex Kot, and Lingyu Duan. 2018. Personalized Knowledge Distillation-based Mobile Food Recognition. In Proceedings on the International Conference on Artificial Intelligence (ICAI). The Steering Committee of The World Congress in Computer Science, 22--28."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2614861"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2010.51"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2814339"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.5"},{"key":"e_1_3_2_1_25_1","volume-title":"European Conference on Computer Vision. Springer, 3--17","author":"Kawano Yoshiyuki","year":"2014","unstructured":"Yoshiyuki Kawano and Keiji Yanai . 2014 . Automatic expansion of a food image dataset leveraging existing categories with domain adaptation . In European Conference on Computer Vision. Springer, 3--17 . Yoshiyuki Kawano and Keiji Yanai. 2014. Automatic expansion of a food image dataset leveraging existing categories with domain adaptation. In European Conference on Computer Vision. Springer, 3--17."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2638728.2641339"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39601-9_4"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00068"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2012.157"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2986035.2986036"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.146"},{"key":"e_1_3_2_1_33_1","volume-title":"Food Photo Recognition for Dietary Tracking: System and Experiment. In International Conference on Multimedia Modeling. Springer, 129--141","author":"Ming Zhao-Yan","year":"2018","unstructured":"Zhao-Yan Ming , Jingjing Chen , Yu Cao , Ciar\u00e1n Forde , Chong-Wah Ngo , and Tat Seng Chua . 2018 . Food Photo Recognition for Dietary Tracking: System and Experiment. In International Conference on Multimedia Modeling. Springer, 129--141 . Zhao-Yan Ming, Jingjing Chen, Yu Cao, Ciar\u00e1n Forde, Chong-Wah Ngo, and Tat Seng Chua. 2018. Food Photo Recognition for Dietary Tracking: System and Experiment. In International Conference on Multimedia Modeling. Springer, 129--141."},{"key":"e_1_3_2_1_34_1","first-page":"36","article-title":"Mobile multi-food recognition using deep learning","volume":"13","author":"Pouladzadeh Parisa","year":"2017","unstructured":"Parisa Pouladzadeh and Shervin Shirmohammadi . 2017 . Mobile multi-food recognition using deep learning . ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 13 , 3s (2017), 36 . Parisa Pouladzadeh and Shervin Shirmohammadi. 2017. Mobile multi-food recognition using deep learning. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 13, 3s (2017), 36.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_36_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99."},{"key":"e_1_3_2_1_37_1","volume-title":"Monte Carlo statistical methods","author":"Robert Christian","unstructured":"Christian Robert and George Casella . 2013. Monte Carlo statistical methods . Springer Science & Business Media . Christian Robert and George Casella. 2013. Monte Carlo statistical methods. Springer Science & Business Media."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2986035.2986043"},{"key":"e_1_3_2_1_39_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and AndrewZisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and AndrewZisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_40_1","unstructured":"Qianru Sun Yaoyao Liu Tat-Seng Chua and Bernt Schiele. 2019. Meta-Transfer Learning for Few-Shot Learning. In CVPR.  Qianru Sun Yaoyao Liu Tat-Seng Chua and Bernt Schiele. 2019. Meta-Transfer Learning for Few-Shot Learning. In CVPR."},{"key":"e_1_3_2_1_41_1","unstructured":"Qianru Sun Bernt Schiele and Mario Fritz. 2017. A Domain Based Approach to Social Relation Recognition. In CVPR. 435--444.  Qianru Sun Bernt Schiele and Mario Fritz. 2017. A Domain Based Approach to Social Relation Recognition. In CVPR. 435--444."},{"key":"e_1_3_2_1_42_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez ?ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez ?ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Martin JWainwright Michael I Jordan etal 2008. Graphical models exponential families and variational inference. Foundations and Trends\u00ae in Machine Learning 1 1--2 (2008) 1--305.  Martin JWainwright Michael I Jordan et al. 2008. Graphical models exponential families and variational inference. Foundations and Trends\u00ae in Machine Learning 1 1--2 (2008) 1--305.","DOI":"10.1561\/2200000001"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2438717"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451422"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1177\/1932296815582222"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351147","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:12Z","timestamp":1750201992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":46,"alternative-id":["10.1145\/3343031.3351147","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351147","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}