{"url":"/dataset/ms-celeb-1m","name":"MS-Celeb-1M","full_name":null,"description_markdown":"The **MS-Celeb-1M** dataset is a large-scale face recognition dataset consists of 100K identities, and each identity has about 100 facial images. The original identity labels are obtained automatically from webpages.\r\n\r\n**NOTE**: This dataset [is currently inactive](https://exposing.ai/msceleb/). \r\n\r\nSource: [Learning to Cluster Faces on an Affinity Graph](https://arxiv.org/abs/1904.02749)\r\nImage Source: [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://arxiv.org/abs/1607.08221)","description_withheld":null,"homepage":null,"introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/ms-celeb-1m-a-dataset-and-benchmark-for-large","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","first_author":"Yandong Guo","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Face Recognition","url":"/task/face-recognition","datasets_with_task":"/datasets/task/face-recognition"},{"name":"Face Verification","url":"/task/face-verification","datasets_with_task":"/datasets/task/face-verification"},{"name":"Face Identification","url":"/task/face-identification","datasets_with_task":"/datasets/task/face-identification"}],"languages":[],"variants":["MS-Celeb-1M"],"data_loaders":[],"num_papers_in_archive":257,"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."}