{"url":"/dataset/glami-1m","name":"GLAMI-1M","full_name":"A Multilingual Image-Text Fashion Dataset","description_markdown":"We introduce GLAMI-1M: the largest multilingual image-text classification dataset and benchmark. The dataset contains images of fashion products with item descriptions, each in 1 of 13 languages. Categorization into 191 classes has high-quality annotations: all 100k images in the test set and 75% of the 1M training set were human-labeled. The paper presents baselines for image-text classification showing that the dataset presents a challenging fine-grained classification problem: The best scoring EmbraceNet model using both visual and textual features achieves 69.7% accuracy. Experiments with a modified Imagen model show the dataset is also suitable for image generation conditioned on text.","description_withheld":null,"homepage":"https://github.com/glami/glami-1m","introduced_date":"2022-11-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/glami-1m-a-multilingual-image-text-fashion-1","title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","first_author":"Vaclav Kosar","url":null},"license":{"name":"Apache-2.0","url":"https://github.com/glami/glami-1m/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"},{"name":"Multilingual Image-Text Classification","url":"/task/multi-lingual-image-text-classification","datasets_with_task":"/datasets/task/multi-lingual-image-text-classification"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"Multilingual","url":"/datasets/language/multilingual"},{"name":"Bulgarian","url":"/datasets/language/bulgarian"},{"name":"Croatian","url":"/datasets/language/croatian"},{"name":"Czech","url":"/datasets/language/czech"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Latvian","url":"/datasets/language/latvian"},{"name":"Lithuanian","url":"/datasets/language/lithuanian"},{"name":"Romanian","url":"/datasets/language/romanian"},{"name":"Slovak","url":"/datasets/language/slovak"},{"name":"Slovenian","url":"/datasets/language/slovenian"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Greek","url":"/datasets/language/greek"}],"variants":["GLAMI-1M"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-lingual-image-text-classification-on","task":"Multilingual Image-Text Classification","dataset_variant":"GLAMI-1M","rows":2,"metrics":["Top 1 Accuracy %","Top 5 Accuracy %"],"first_row_in_archive_order":{"model":"EmbraceNet (image+text)","paper":"/paper/glami-1m-a-multilingual-image-text-fashion-1","metrics":{"Top 1 Accuracy %":"69.7","Top 5 Accuracy %":"94.0"},"code_links":[{"title":"glami/glami-1m","url":"https://github.com/glami/glami-1m"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/glami-1m-a-multilingual-image-text-fashion-1","title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","date":"2022-11-17","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."}