{"url":"/dataset/polaris","name":"Polaris","full_name":"Polaris dataset","description_markdown":"The Polaris dataset offers a large-scale, diverse benchmark for evaluating metrics for image captioning, surpassing existing datasets in terms of size, caption diversity, number of human judgments, and granularity of the evaluations. It includes 131,020 generated captions and 262,040 reference captions. The generated captions have a vocabulary of 3,154 unique words and the reference captions have a vocabulary of 22,275 unique words.","description_withheld":null,"homepage":"https://huggingface.co/datasets/yuwd/Polaris","introduced_date":"2024-02-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/polos-multimodal-metric-learning-from-human","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning","first_author":"Yuiga Wada","url":null},"license":{"name":"BSD-3-Clause-Clear","url":"https://github.com/keio-smilab24/Polos/blob/master/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Polaris"],"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."}