{"url":"/dataset/oven","name":"OVEN","full_name":"Open-domain Visual Entity Recognition","description_markdown":"In this project, we formally present the task of Open-domain Visual Entity recognitioN (OVEN), where a model need to link an image onto a Wikipedia entity with respect to a text query. We construct OVEN-Wiki by re-purposing 14 existing datasets with all labels grounded onto one single label space: Wikipedia entities. OVEN challenges models to select among six million possible Wikipedia entities, making it a general visual recognition benchmark with the largest number of labels.","description_withheld":null,"homepage":"https://open-vision-language.github.io/oven/","introduced_date":"2023-02-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/open-domain-visual-entity-recognition-towards","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","first_author":"Hexiang Hu","url":null},"license":{"name":"Apache-2.0","url":"https://github.com/open-vision-language/oven/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"},{"name":"Fine-Grained Image Recognition","url":"/task/fine-grained-image-recognition","datasets_with_task":"/datasets/task/fine-grained-image-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OVEN"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/fine-grained-image-recognition-on-oven","task":"Fine-Grained Image Recognition","dataset_variant":"OVEN","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLI-X","paper":"/paper/pali-x-on-scaling-up-a-multilingual-vision","metrics":{"Accuracy":"23.1"},"code_links":[{"title":"kyegomez/PALI","url":"https://github.com/kyegomez/PALI"},{"title":"doc-doc/NExT-OE","url":"https://github.com/doc-doc/NExT-OE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/retrieval-enhanced-contrastive-vision-text","title":"Retrieval-Enhanced Contrastive Vision-Text Models","date":"2023-06-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":6,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/open-domain-visual-entity-recognition-towards","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","date":"2023-02-22","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":11,"samples_ran":7,"samples_unverified":4,"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."}