{"url":"/dataset/whos-waldo","name":"Who’s Waldo","full_name":null,"description_markdown":"**Who's Waldo** is a dataset of 270K image–caption pairs, depicting interactions of people, that is automatically mined from Wikimedia Commons. It is a benchmark dataset for person-centric visual grounding, the problem of linking between people named in a caption and people pictured in an image.","description_withheld":null,"homepage":"https://whoswaldo.github.io","introduced_date":"2021-08-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/who-s-waldo-linking-people-across-text-and","title":"Who's Waldo? Linking People Across Text and Images","first_author":"Claire Yuqing Cui","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://whoswaldo.github.io/dataset.html#dataset-license"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Person-centric Visual Grounding","url":"/task/person-centric-visual-grounding","datasets_with_task":"/datasets/task/person-centric-visual-grounding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Who’s Waldo"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/person-centric-visual-grounding-on-whos-waldo","task":"Person-centric Visual Grounding","dataset_variant":"Who’s Waldo","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Who's Waldo","paper":"/paper/who-s-waldo-linking-people-across-text-and","metrics":{"Accuracy":"63.5"},"code_links":[{"title":"clairecyq/whos-waldo","url":"https://github.com/clairecyq/whos-waldo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/who-s-waldo-linking-people-across-text-and","title":"Who's Waldo? Linking People Across Text and Images","date":"2021-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}