{"url":"/dataset/sbu-captions-dataset","name":"SBU Captions Dataset","full_name":null,"description_markdown":"A collection that allows researchers to approach the extremely challenging problem of description generation using relatively simple non-parametric methods and produces surprisingly effective results.\r\n\r\nSource: [Im2Text: Describing Images Using 1 Million Captioned Photographs](/paper/im2text-describing-images-using-1-million)","description_withheld":null,"homepage":"https://www.cs.rice.edu/~vo9/sbucaptions/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/im2text-describing-images-using-1-million","title":"Im2Text: Describing Images Using 1 Million Captioned Photographs","first_author":"Vicente Ordonez","url":null},"license":null,"modalities":[],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[],"variants":["SBU Captions Dataset"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/vicenteor/sbu_captions","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/sbu_captions","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.SBU.html","frameworks":["pytorch"]}],"num_papers_in_archive":11,"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."}