{"url":"/dataset/imdb-face","name":"IMDb-Face","full_name":null,"description_markdown":"IMDb-Face is  large-scale noise-controlled dataset for face recognition research. The dataset contains about 1.7 million faces, 59k identities, which is manually cleaned from 2.0 million raw images. All images are obtained from the IMDb website. \r\n\r\nSource: [The Devil of Face Recognition is in the Noise](/paper/the-devil-of-face-recognition-is-in-the-noise)","description_withheld":null,"homepage":"https://github.com/fwang91/IMDb-Face","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-devil-of-face-recognition-is-in-the-noise","title":"The Devil of Face Recognition is in the Noise","first_author":"Fei Wang","url":null},"license":{"name":"Custom","url":"https://github.com/fwang91/IMDb-Face"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Face Recognition","url":"/task/face-recognition","datasets_with_task":"/datasets/task/face-recognition"}],"languages":[],"variants":["IMDb-Face"],"data_loaders":[{"repo":"https://github.com/fwang91/IMDb-Face","url":"https://github.com/fwang91/IMDb-Face","frameworks":[]}],"num_papers_in_archive":22,"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."}