{"url":"/dataset/ovdeval","name":"OVDEval","full_name":null,"description_markdown":"**OVDEval** includes 9 sub-tasks and introduces evaluations on commonsense knowledge, attribute understanding, position understanding, object relation comprehension, and more. The dataset is meticulously created to provide hard negatives that challenge models' true understanding of visual and linguistic input.","description_withheld":null,"homepage":"https://github.com/om-ai-lab/OVDEval","introduced_date":"2023-08-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/how-to-evaluate-the-generalization-of","title":"How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection","first_author":"Yiyang Yao","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/om-ai-lab/OVDEval/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Proper Noun","url":"/task/proper-noun","datasets_with_task":"/datasets/task/proper-noun"},{"name":"Negation","url":"/task/negation","datasets_with_task":"/datasets/task/negation"}],"languages":[],"variants":["OVDEval"],"data_loaders":[],"num_papers_in_archive":4,"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."}