{"url":"/dataset/uicaption","name":"UICaption","full_name":null,"description_markdown":"**UICaption** is a dataset of 114k UI images paired with descriptions of their functionality. It is designed for the tasks of UI action entailment, instruction-based UI image retrieval, grounding referring expressions, and UI entity recognition.\r\n\r\nSource: [Lexi: Self-Supervised Learning of the UI Language](https://arxiv.org/pdf/2301.10165v1.pdf)","description_withheld":null,"homepage":"https://github.com/microsoft/UICaption","introduced_date":"2023-01-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/lexi-self-supervised-learning-of-the-ui","title":"Lexi: Self-Supervised Learning of the UI Language","first_author":"Pratyay Banerjee","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["UICaption"],"data_loaders":[],"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."}