{"url":"/dataset/m5product","name":"M5Product","full_name":null,"description_markdown":"The **M5Product** dataset is a large-scale multi-modal pre-training dataset with coarse and fine-grained annotations for E-products.\r\n\r\n• 6 Million multi-modal samples, 5k properties with 24 Million values\r\n\r\n• 5 modalities-image text table video audio\r\n\r\n• 6 Million category annotations with 6k classes\r\n\r\n• Wide data source (1 Million merchants provide)","description_withheld":null,"homepage":"https://xiaodongsuper.github.io/M5Product_dataset","introduced_date":"2021-09-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/m5product-a-multi-modal-pretraining-benchmark","title":"M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining","first_author":"Xiao Dong","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Tables","url":"/datasets/modality/tables"}],"tasks":[],"languages":[],"variants":["M5Product"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}