{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:29:58Z","timestamp":1764588598350,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680977","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"127-136","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Navigating Weight Prediction with Diet Diary"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9345-3275","authenticated-orcid":false,"given":"Yinxuan","family":"Gui","sequence":"first","affiliation":[{"name":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9213-2611","authenticated-orcid":false,"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1737-3420","authenticated-orcid":false,"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-8261","authenticated-orcid":false,"given":"Chong Wah","family":"Ngo","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"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","volume-title":"New Trends in Image Analysis and Processing--ICIAP 2017: ICIAP International Workshops, WBICV, SSPandBE, 3AS, RGBD, NIVAR, IWBAAS, and MADiMa","author":"Marc Bola","year":"2017","unstructured":"Marc Bola nos, Aina Ferr\u00e0, and Petia Radeva. 2017. Food ingredients recognition through multi-label learning. In New Trends in Image Analysis and Processing--ICIAP 2017: ICIAP International Workshops, WBICV, SSPandBE, 3AS, RGBD, NIVAR, IWBAAS, and MADiMa 2017, Catania, Italy, September 11--15, 2017, Revised Selected Papers 19. Springer, 394--402."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings, Part VI 13","author":"Bossard Lukas","year":"2014","unstructured":"Lukas Bossard, Matthieu Guillaumin, and Luc Van Gool. 2014. Food-101--mining discriminative components with random forests. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part VI 13. Springer, 446--461."},{"volume-title":"Time series analysis: forecasting and control","author":"Box George EP","key":"e_1_3_2_1_4_1","unstructured":"George EP Box, Gwilym M Jenkins, Gregory C Reinsel, and Greta M Ljung. 2015. Time series analysis: forecasting and control. John Wiley & Sons."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"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","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6626"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045639"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 25th ACM international conference on Multimedia. 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. 1771--1779."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240627"},{"key":"e_1_3_2_1_11_1","volume-title":"Chinesefoodnet: 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. Chinesefoodnet: A large-scale image dataset for chinese food recognition. arXiv preprint arXiv:1705.02743 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00800"},{"key":"e_1_3_2_1_13_1","volume-title":"Long-term forecasting with tide: Time-series dense encoder. arXiv preprint arXiv:2304.08424","author":"Das Abhimanyu","year":"2023","unstructured":"Abhimanyu Das, Weihao Kong, Andrew Leach, Rajat Sen, and Rose Yu. 2023. Long-term forecasting with tide: Time-series dense encoder. arXiv preprint arXiv:2304.08424 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_15_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599533"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI51738.2020.00039"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/BSN.2018.8329671"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475465"},{"key":"e_1_3_2_1_20_1","volume-title":"Companion Proceedings of the Web Conference","author":"Lee Helena H.","year":"2020","unstructured":"Helena H. Lee, Ke Shu, Palakorn Achananuparp, Philips Kokoh Prasetyo, Yue Liu, Ee-Peng Lim, and Lav R Varshney. 2020. RecipeGPT: Generative pre-training based cooking recipe generation and evaluation system. In Companion Proceedings of the Web Conference 2020. 181--184."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.2337\/db07-0882"},{"key":"e_1_3_2_1_22_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531426"},{"key":"e_1_3_2_1_24_1","volume-title":"Regulation of body weight in humans. Physiological reviews","author":"J\u00e9quier Eric","year":"1999","unstructured":"Eric J\u00e9quier and Luc Tappy. 1999. Regulation of body weight in humans. Physiological reviews, Vol. 79, 2 (1999), 451--480."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2929447"},{"key":"e_1_3_2_1_26_1","unstructured":"Pengkun Jiao Xinlan Wu Bin Zhu Jingjing Chen Chong-Wah Ngo and Yugang Jiang. 2024. RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models. arXiv preprint arXiv:2407.12730 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_28_1","volume-title":"Deep learning approaches in food recognition. Machine Learning Paradigms: Advances in Deep Learning-based Technological Applications","author":"Kiourt Chairi","year":"2020","unstructured":"Chairi Kiourt, George Pavlidis, and Stella Markantonatou. 2020. Deep learning approaches in food recognition. Machine Learning Paradigms: Advances in Deep Learning-based Technological Applications (2020), 83--108."},{"key":"e_1_3_2_1_29_1","volume-title":"Foodsam: Any food segmentation","author":"Lan Xing","year":"2023","unstructured":"Xing Lan, Jiayi Lyu, Hanyu Jiang, Kun Dong, Zehai Niu, Yi Zhang, and Jian Xue. 2023. Foodsam: Any food segmentation. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Food and ingredient joint learning for fine-grained recognition","author":"Liu Chengxu","year":"2020","unstructured":"Chengxu Liu, Yuanzhi Liang, Yao Xue, Xueming Qian, and Jianlong Fu. 2020. Food and ingredient joint learning for fine-grained recognition. IEEE transactions on circuits and Systems for Video Technology, Vol. 31, 6 (2020), 2480--2493."},{"key":"e_1_3_2_1_31_1","volume-title":"From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios","author":"Liu Guoshan","year":"2024","unstructured":"Guoshan Liu, Yang Jiao, Jingjing Chen, Bin Zhu, and Yu-Gang Jiang. 2024. From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios. IEEE Transactions on Multimedia (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on learning representations.","author":"Liu Shizhan","year":"2021","unstructured":"Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X Liu, and Schahram Dustdar. 2021. Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In International conference on learning representations."},{"key":"e_1_3_2_1_33_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Liu Yong","year":"2023","unstructured":"Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, and Mingsheng Long. 2023. iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2942831"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2942831"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19030564"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00068"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.146"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329168"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475725.3483626"},{"key":"e_1_3_2_1_42_1","volume-title":"International Conference on Learning Representations.","author":"Nie Yuqi","year":"2023","unstructured":"Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2023. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413636"},{"key":"e_1_3_2_1_44_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"David Salinas Valentin Flunkert Jan Gasthaus and Tim Januschowski. 2020. DeepAR: Probabilistic forecasting with autoregressive recurrent networks. International journal of forecasting Vol. 36 3 (2020) 1181--1191.","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01070"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01522"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00503"},{"key":"e_1_3_2_1_50_1","volume-title":"Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective. In European Conference on Computer Vision.","author":"Song Fangzhou","year":"2024","unstructured":"Fangzhou Song, Bin Zhu, Yanbin Hao, and Shuo Wang. 2024. Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9175807"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3607828.3617799"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2017.1380080"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00879"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01184"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3083109"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIBD49809.2020.9137492"},{"key":"e_1_3_2_1_58_1","volume-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in neural information processing systems","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in neural information processing systems, Vol. 34 (2021), 22419--22430."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475201"},{"key":"e_1_3_2_1_60_1","volume-title":"FoodLMM: A Versatile Food Assistant using Large Multi-modal Model. arXiv preprint arXiv:2312.14991","author":"Yin Yuehao","year":"2023","unstructured":"Yuehao Yin, Huiyan Qi, Bin Zhu, Jingjing Chen, Yu-Gang Jiang, and Chong-Wah Ngo. 2023. FoodLMM: A Versatile Food Assistant using Large Multi-modal Model. arXiv preprint arXiv:2312.14991 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3360899"},{"key":"e_1_3_2_1_64_1","volume-title":"International conference on machine learning. PMLR, 27268--27286","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International conference on machine learning. PMLR, 27268--27286."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413809"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680977","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:35Z","timestamp":1750295855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680977"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":67,"alternative-id":["10.1145\/3664647.3680977","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680977","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}