{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:13:43Z","timestamp":1783113223773,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"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":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679885","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"3872-3876","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4281-9794","authenticated-orcid":false,"given":"Peiyu","family":"Li","sequence":"first","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1679-3888","authenticated-orcid":false,"given":"Xiaobao","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2795-6080","authenticated-orcid":false,"given":"Yijun","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3932-5956","authenticated-orcid":false,"given":"Nitesh V.","family":"Chawla","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 13th International Conference on Natural Language Generation. 22--28","author":"Maciejewska Martyna","year":"2020","unstructured":"Martyna Maciejewska, Wojciech Taisner, Dawid Wisniewski, and Agnieszka Lawrynowicz. 2020. RecipeNLG: A cooking recipes dataset for semi-structured text generation. In Proceedings of the 13th International Conference on Natural Language Generation. 22--28."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00800"},{"key":"e_1_3_2_1_4_1","volume-title":"MAGMA--Multimodal Augmentation of Generative Models through Adapter-based Finetuning. arXiv preprint arXiv:2112.05253","author":"Eichenberg Constantin","year":"2021","unstructured":"Constantin Eichenberg, Sidney Black, SamuelWeinbach, Letitia Parcalabescu, and Anette Frank. 2021. MAGMA--Multimodal Augmentation of Generative Models through Adapter-based Finetuning. arXiv preprint arXiv:2112.05253 (2021)."},{"key":"e_1_3_2_1_5_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_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093463"},{"key":"e_1_3_2_1_7_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_8_1","volume-title":"Generating images with multimodal language models. Advances in Neural Information Processing Systems 36","author":"Koh Jing Yu","year":"2024","unstructured":"Jing Yu Koh, Daniel Fried, and Russ R Salakhutdinov. 2024. Generating images with multimodal language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 17283--17300","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Ruslan Salakhutdinov, and Daniel Fried. 2023. Grounding language models to images for multimodal inputs and outputs. In International Conference on Machine Learning. PMLR, 17283--17300."},{"key":"e_1_3_2_1_10_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74--81. https:\/\/aclanthology.org\/W04--1013"},{"key":"e_1_3_2_1_11_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413636"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00819"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_2_1_16_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_17_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01070"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"e_1_3_2_1_21_1","volume-title":"Chawla","author":"Tian Yijun","year":"2022","unstructured":"Yijun Tian, Chuxu Zhang, Zhichun Guo, Chao Huang, Ronald Metoyer, and Nitesh V. Chawla. 2022. RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation. In IJCAI."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Yijun Tian Chuxu Zhang Zhichun Guo Yihong Ma Ronald Metoyer and Nitesh V Chawla. 2022. Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks. In IJCAI.","DOI":"10.24963\/ijcai.2022\/482"},{"key":"e_1_3_2_1_23_1","volume-title":"Chawla","author":"Tian Yijun","year":"2022","unstructured":"Yijun Tian, Chuxu Zhang, Ronald Metoyer, and Nitesh V. Chawla. 2022. Recipe Recommendation With Hierarchical Graph Attention Network. Frontiers in Big Data (2022)."},{"key":"e_1_3_2_1_24_1","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli Maria","year":"2021","unstructured":"Maria Tsimpoukelli, Jacob L Menick, Serkan Cabi, SM Eslami, Oriol Vinyals, and Felix Hill. 2021. Multimodal few-shot learning with frozen language models. Advances in Neural Information Processing Systems 34 (2021), 200--212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_26_1","first-page":"3363","article-title":"Learning structural representations for recipe generation and food retrieval","volume":"45","author":"Wang Hao","year":"2022","unstructured":"Hao Wang, Guosheng Lin, Steven CH Hoi, and Chunyan Miao. 2022. Learning structural representations for recipe generation and food retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2022), 3363--3377.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01184"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367629"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2010.44"},{"key":"e_1_3_2_1_30_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679885","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:08Z","timestamp":1750294688000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":32,"alternative-id":["10.1145\/3627673.3679885","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679885","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}