{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:25:59Z","timestamp":1773786359038,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,29]]},"DOI":"10.1145\/3607828.3617796","type":"proceedings-article","created":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T04:12:17Z","timestamp":1698293537000},"page":"61-69","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Diffusion Model with Clustering-based Conditioning for Food Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4494-5455","authenticated-orcid":false,"given":"Yue","family":"Han","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8552-9880","authenticated-orcid":false,"given":"Jiangpeng","family":"He","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6181-1403","authenticated-orcid":false,"given":"Mridul","family":"Gupta","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2909-7323","authenticated-orcid":false,"given":"Edward J.","family":"Delp","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3863-3220","authenticated-orcid":false,"given":"Fengqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2015.39"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.copbio.2021.02.007"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0029665116002913"},{"key":"e_1_3_2_1_5_1","volume-title":"A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks (October","author":"Buda Mateusz","year":"2018","unstructured":"Mateusz Buda, Atsuto Maki, and Maciej A Mazurowski. 2018. A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks (October 2018), 249--259."},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Cao Kaidi","year":"2019","unstructured":"Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Arechiga, and Tengyu Ma. 2019. Learning imbalanced datasets with label-distribution-aware margin loss. Advances in Neural Information Processing Systems , Vol. 32 (December 2019), 1567--1578."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/BHI.2018.8333411"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_1_9_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems , Vol. 34 (December 2021), 8780--8794."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-54244-5"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230519.3230594"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/nu11040877"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451461"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532312"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1136800"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.2352\/EI.2023.35.7.IMAGE-268"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3181789"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (December","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. Proceedings of the International Conference on Neural Information Processing Systems (December 2014), 2672--2680. Montreal, Canada."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093463"},{"key":"e_1_3_2_1_22_1","volume-title":"MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs. arXiv preprint arXiv:2012.02821 (December","author":"Han Fangda","year":"2020","unstructured":"Fangda Han, Guoyao Hao, Ricardo Guerrero, and Vladimir Pavlovic. 2020b. MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs. arXiv preprint arXiv:2012.02821 (December 2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00454"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2021.8.IMAWM-286"},{"key":"e_1_3_2_1_25_1","first-page":"12","article-title":"a","volume":"15","author":"He Jiangpeng","year":"2023","unstructured":"Jiangpeng He, Luotao Lin, Heather A Eicher-Miller, and Fengqing Zhu. 2023 a. Long-Tailed Food Classification. Nutrients, Vol. 15, 12 (June 2023), 2751.","journal-title":"Long-Tailed Food Classification. Nutrients"},{"key":"e_1_3_2_1_26_1","volume-title":"2023 b. Long-Tailed Continual Learning For Visual Food Recognition. arXiv preprint arXiv:2307.00183 (June","author":"He Jiangpeng","year":"2023","unstructured":"Jiangpeng He, Luotao Lin, Jack Ma, Heather A. Eicher-Miller, and Fengqing Zhu. 2023 b. Long-Tailed Continual Learning For Visual Food Recognition. arXiv preprint arXiv:2307.00183 (June 2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2021.8.IMAWM-285"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01394"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR49039.2020.00018"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00265"},{"key":"e_1_3_2_1_31_1","volume-title":"Exemplar-Free Online Continual Learning. 2022 IEEE International Conference on Image Processing (October","author":"He Jiangpeng","year":"2022","unstructured":"Jiangpeng He and Fengqing Zhu. 2022. Exemplar-Free Online Continual Learning. 2022 IEEE International Conference on Image Processing (October 2022), 541--545."},{"key":"e_1_3_2_1_32_1","volume-title":"Single-Stage Heavy-Tailed Food Classification. arXiv preprint arXiv:2307.00182 (July","author":"He Jiangpeng","year":"2023","unstructured":"Jiangpeng He and Fengqing Zhu. 2023. Single-Stage Heavy-Tailed Food Classification. arXiv preprint arXiv:2307.00182 (July 2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_34_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in Neural Information Processing Systems , Vol. 30 (December 2017), 6629----6640."},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems , Vol. 33 (December 2020), 6840--6851."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3347448.3357166"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230519.3230598"},{"key":"e_1_3_2_1_38_1","volume-title":"DeepFood: food image analysis and dietary assessment via deep model","author":"Jiang Landu","year":"2020","unstructured":"Landu Jiang, Bojia Qiu, Xue Liu, Chenxi Huang, and Kunhui Lin. 2020b. DeepFood: food image analysis and dietary assessment via deep model. IEEE Access , Vol. 8 (February 2020), 47477--47489."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3391624"},{"key":"e_1_3_2_1_40_1","volume-title":"Abu Naser Mojumder, Mitun Kanti Paul, Pranta Barua, Shahidullah Kayshar, Syeda Sabrina Akter, Mizanur Rahman, and Amirul Islam.","author":"Jubayer Fahad","year":"2021","unstructured":"Fahad Jubayer, Janibul Alam Soeb, Abu Naser Mojumder, Mitun Kanti Paul, Pranta Barua, Shahidullah Kayshar, Syeda Sabrina Akter, Mizanur Rahman, and Amirul Islam. 2021. Detection of mold on the food surface using YOLOv5. Current Research in Food Science , Vol. 4 (October 2021), 724--728."},{"key":"e_1_3_2_1_41_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Karras Tero","year":"2021","unstructured":"Tero Karras, Miika Aittala, Samuli Laine, Erik H\"ark\u00f6nen, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2021. Alias-free generative adversarial networks. Advances in Neural Information Processing Systems , Vol. 34 (December 2021), 852--863."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the European Conference on Computer Vision Workshop (September","author":"Kawano Yoshiyuki","year":"2014","unstructured":"Yoshiyuki Kawano and Keiji Yanai. 2014a. Automatic expansion of a food image dataset leveraging existing categories with domain adaptation. Proceedings of the European Conference on Computer Vision Workshop (September 2014), 3--17. Zurich, Switzerland."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04117-9_38"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_46_1","volume-title":"nutrition, and cancer risk: what do we know and what is the way forward BMJ","author":"Key Timothy J","year":"2020","unstructured":"Timothy J Key, Kathryn E Bradbury, Aurora Perez-Cornago, Rashmi Sinha, Konstantinos K Tsilidis, and Shoichiro Tsugane. 2020. Diet, nutrition, and cancer risk: what do we know and what is the way forward BMJ , Vol. 368 (March 2020), m511."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2011.07.003"},{"key":"e_1_3_2_1_48_1","volume-title":"The Most Frequently Consumed and the Largest Energy Contributing Foods of US Insulin Takers Using NHANES 2009--2016","volume":"5","author":"Lin Luotao","year":"2021","unstructured":"Luotao Lin, Fengqing Zhu, Edward Delp, and Heather Eicher-Miller. 2021. The Most Frequently Consumed and the Largest Energy Contributing Foods of US Insulin Takers Using NHANES 2009--2016. Current Developments in Nutrition , Vol. 5 (June 2021), 426--426."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20154283"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP53017.2021.9733586"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68821-9_47"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"e_1_3_2_1_56_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (November","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (November 2014)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.10.IMAWM-163"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00676"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00077"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18576-2_12"},{"key":"e_1_3_2_1_61_1","volume-title":"Online Class-Incremental Learning For Real-World Food Classification. arXiv preprint arXiv: 2301.05246 (January","author":"Raghavan Siddeshwar","year":"2023","unstructured":"Siddeshwar Raghavan, Jiangpeng He, and Fengqing Zhu. 2023. Online Class-Incremental Learning For Real-World Food Classification. arXiv preprint arXiv: 2301.05246 (January 2023)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_63_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ren Jiawei","year":"2020","unstructured":"Jiawei Ren, Cunjun Yu, Xiao Ma, Haiyu Zhao, Shuai Yi, et al. 2020. Balanced meta-softmax for long-tailed visual recognition. Advances in Neural Information Processing Systems , Vol. 33 (December 2020), 4175--4186."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_67_1","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems , Vol. 35 (November 2022), 25278--25294."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP53017.2021.9733557"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475725.3483625"},{"key":"e_1_3_2_1_70_1","volume-title":"An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image. arXiv preprint arXiv:2308.01810 (July","author":"Shao Zeman","year":"2023","unstructured":"Zeman Shao, Gautham Vinod, Jiangpeng He, and Fengqing Zhu. 2023. An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image. arXiv preprint arXiv:2308.01810 (July 2023)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2008.4911602"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22208006"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207181"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273614"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 8th International Workshop on Multimedia Assisted Dietary Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3607828.3617796","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3607828.3617796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:05Z","timestamp":1750178225000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3607828.3617796"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":76,"alternative-id":["10.1145\/3607828.3617796","10.1145\/3607828"],"URL":"https:\/\/doi.org\/10.1145\/3607828.3617796","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]},"assertion":[{"value":"2023-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}