{"url":"/dataset/t2-guiding","name":"T2 Guiding","full_name":null,"description_markdown":"T2 Guiding is a dataset of 1000 images, each with six image labels. The images are from the Open Images Dataset (OID) and the dataset includes 2 sets of machine-generated labels for these images.\r\n\r\n* Object labels: Three random object labels generated by a FRCNN model trained on Visual Genome.\r\n* Image labels: Three random image labels obtained from Google Cloud Vision API.\r\n\r\nSource: [T2-Guiding](https://github.com/google-research-datasets/T2-Guiding)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/T2-Guiding","introduced_date":"2020-12-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/understanding-guided-image-captioning","title":"Understanding Guided Image Captioning Performance across Domains","first_author":"Edwin G. Ng","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[],"variants":["T2 Guiding"],"data_loaders":[{"repo":"https://github.com/google-research-datasets/T2-Guiding","url":"https://github.com/google-research-datasets/T2-Guiding","frameworks":[]}],"num_papers_in_archive":1,"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."}