{"url":"/task/person-centric-visual-grounding","name":"Person-centric Visual Grounding","slug":"person-centric-visual-grounding","description_markdown":"Person-centric visual grounding is the problem of linking between people named in a caption and people pictured in an image. Introduced in \"Who's Waldo? Linking People Across Text and Images\" (Cui et al, ICCV 2021).","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":4,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/person-centric-visual-grounding-on-whos-waldo","slug":"person-centric-visual-grounding-on-whos-waldo","dataset":"Who’s Waldo","dataset_url":"/dataset/whos-waldo","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Who's Waldo","paper_title":"Who's Waldo? Linking People Across Text and Images","paper_url":"/paper/who-s-waldo-linking-people-across-text-and","paper_date":"2021-08-16","arxiv_id":"2108.07253","code_links":[{"title":"clairecyq/whos-waldo","url":"https://github.com/clairecyq/whos-waldo"}],"syntology":null}}],"datasets":[{"url":"/dataset/whos-waldo","name":"Who’s Waldo","full_name":"","num_papers_in_archive":8}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-grounding","name":"Visual Grounding"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":4,"items":[{"url":"/paper/to-find-waldo-you-need-contextual-cues-1","title":"To Find Waldo You Need Contextual Cues: Debiasing Who’s Waldo","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tubedetr-spatio-temporal-video-grounding-with","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","date":"2022-03-30","arxiv_id":"2203.16434","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/to-find-waldo-you-need-contextual-cues","title":"To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo","date":"2022-03-30","arxiv_id":"2203.16682","repositories_listed":1,"syntology":null},{"url":"/paper/who-s-waldo-linking-people-across-text-and","title":"Who's Waldo? Linking People Across Text and Images","date":"2021-08-16","arxiv_id":"2108.07253","repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}