{"url":"/dataset/sk-vg","name":"SK-VG","full_name":null,"description_markdown":"**SK-VG** is a dataset for Scene Knowledge-guided Visual Grounding, where the image content and referring expressions are not sufficient to ground the target objects, forcing the models to have a reasoning ability on the long-form scene knowledge. To perform this task, SK-VG is the first dataset of the fourth type, where for each image, we provide human-written knowledge to describe its content.","description_withheld":null,"homepage":"https://github.com/zhjohnchan/SK-VG","introduced_date":"2023-07-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/advancing-visual-grounding-with-scene-1","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","first_author":"Zhihong Chen","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Visual Grounding","url":"/task/visual-grounding","datasets_with_task":"/datasets/task/visual-grounding"}],"languages":[],"variants":["SK-VG"],"data_loaders":[],"num_papers_in_archive":2,"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."}