{"url":"/dataset/foodi-ml","name":"FooDI-ML","full_name":"Food Drinks and groceries Images Multi Lingual","description_markdown":"Food Drinks and groceries Images Multi Lingual (FooDI-ML) is a dataset that contains over 1.5M unique images and over 9.5M store names, product names descriptions, and collection sections gathered from the Glovo application. The data made available corresponds to food, drinks and groceries products from 37 countries in Europe, the Middle East, Africa and Latin America. The dataset comprehends 33 languages, including 870K samples of languages of countries from Eastern Europe and Western Asia such as Ukrainian and Kazakh, which have been so far underrepresented in publicly available visiolinguistic datasets. The dataset also includes widely spoken languages such as Spanish and English.\r\n\r\nDescription from: [FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions](https://arxiv.org/abs/2110.02035)\r\n\r\nImage source: [https://github.com/Glovo/foodi-ml-dataset](https://github.com/Glovo/foodi-ml-dataset)","description_withheld":null,"homepage":"https://github.com/Glovo/foodi-ml-dataset","introduced_date":"2021-10-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/foodi-ml-a-large-multi-language-dataset-of","title":"FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions","first_author":"David Amat Olóndriz","url":null},"license":{"name":"CC BY-NC-SA 2.0","url":"https://creativecommons.org/licenses/by-nc-sa/2.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"}],"languages":[],"variants":["FooDI-ML","FooDI-ML (Spain)","FooDI-ML (Global)"],"data_loaders":[{"repo":"https://github.com/glovo/foodi-ml-dataset","url":"https://github.com/glovo/foodi-ml-dataset","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-retrieval-on-foodi-ml-global","task":"Image Retrieval","dataset_variant":"FooDI-ML (Global)","rows":1,"metrics":["A-R@1","A-R@10","A-R@5","Re-R@1","Re-R@10","Re-R@5"],"first_row_in_archive_order":{"model":"ADAPT-I2T","paper":"/paper/foodi-ml-a-large-multi-language-dataset-of","metrics":{"A-R@1":"0.005","A-R@10":"0.05","A-R@5":"0.02","Re-R@1":"0.01","Re-R@10":"0.045","Re-R@5":"0.03"},"code_links":[{"title":"glovo/foodi-ml-dataset","url":"https://github.com/glovo/foodi-ml-dataset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-retrieval-on-foodi-ml-spain","task":"Image Retrieval","dataset_variant":"FooDI-ML (Spain)","rows":1,"metrics":["A-R@1","A-R@10","A-R@5","Re-R@1","Re-R@10","Re-R@5"],"first_row_in_archive_order":{"model":"ADAPT-I2T","paper":"/paper/foodi-ml-a-large-multi-language-dataset-of","metrics":{"A-R@1":"0.93","A-R@10":"5.8","A-R@5":"3.33","Re-R@1":"0.73","Re-R@10":"5.67","Re-R@5":"2.93"},"code_links":[{"title":"glovo/foodi-ml-dataset","url":"https://github.com/glovo/foodi-ml-dataset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/foodi-ml-a-large-multi-language-dataset-of","title":"FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions","date":"2021-10-05","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}