{"url":"/dataset/chinese-text-in-the-wild","name":"Chinese Text in the Wild","full_name":null,"description_markdown":"Chinese Text in the Wild is a dataset of Chinese text with about 1 million Chinese characters from 3850 unique ones annotated by experts in over 30000 street view images. This is a challenging dataset with good diversity containing planar text, raised text, text under poor illumination, distant text, partially occluded text, etc.","description_withheld":null,"homepage":"https://ctwdataset.github.io/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/chinese-text-in-the-wild","title":"Chinese Text in the Wild","first_author":"Tai-Ling Yuan","url":null},"license":{"name":"Various (see link)","url":"https://ctwdataset.github.io/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Scene Text Detection","url":"/task/scene-text-detection","datasets_with_task":"/datasets/task/scene-text-detection"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Chinese Text in the Wild"],"data_loaders":[],"num_papers_in_archive":5,"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."}