{"url":"/dataset/textseg","name":"TextSeg","full_name":null,"description_markdown":"**TextSeg** is a large-scale fine-annotated and multi-purpose text detection and segmentation dataset, collecting scene and design text with six types of annotations: word- and character-wise bounding polygons, masks and transcriptions.\n\nSource: [https://github.com/SHI-Labs/Rethinking-Text-Segmentation](https://github.com/SHI-Labs/Rethinking-Text-Segmentation)\nImage Source: [https://github.com/SHI-Labs/Rethinking-Text-Segmentation](https://github.com/SHI-Labs/Rethinking-Text-Segmentation)","description_withheld":null,"homepage":"https://github.com/SHI-Labs/Rethinking-Text-Segmentation","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/rethinking-text-segmentation-a-novel-dataset","title":"Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach","first_author":"Xingqian Xu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Style Transfer","url":"/task/style-transfer","datasets_with_task":"/datasets/task/style-transfer"},{"name":"Text Style Transfer","url":"/task/text-style-transfoer","datasets_with_task":"/datasets/task/text-style-transfoer"},{"name":"self-supervised scene text recognition","url":"/task/self-supervised-scene-text-recognition","datasets_with_task":"/datasets/task/self-supervised-scene-text-recognition"}],"languages":[],"variants":["TextSeg"],"data_loaders":[{"repo":"https://github.com/SHI-Labs/Rethinking-Text-Segmentation","url":"https://github.com/SHI-Labs/Rethinking-Text-Segmentation","frameworks":[]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/self-supervised-scene-text-recognition-on-1","task":"self-supervised scene text recognition","dataset_variant":"TextSeg","rows":1,"metrics":["IoU (%)"],"first_row_in_archive_order":{"model":"CCD-ViT-Small","paper":"/paper/self-supervised-character-to-character","metrics":{"IoU (%)":"84.8"},"code_links":[{"title":"tongkunguan/ccd","url":"https://github.com/tongkunguan/ccd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}