{"url":"/task/self-supervised-scene-text-recognition","name":"self-supervised scene text recognition","slug":"self-supervised-scene-text-recognition","description_markdown":"scene text recognition task\r\n\r\nself-supervised scene text recognition task\r\n\r\ntext segmentation task\r\n\r\ntext image super-resolution task","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2,"papers_with_code":2,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/self-supervised-scene-text-recognition-on","slug":"self-supervised-scene-text-recognition-on","dataset":"TextZoom","dataset_url":"/dataset/textzoom","rows_in_archive":1,"metrics":["Average PSNR (dB)","SSIM"],"first_row_in_archive_order":{"model":"CCD-ViT-Small","paper_title":"Self-supervised Character-to-Character Distillation for Text Recognition","paper_url":"/paper/self-supervised-character-to-character","paper_date":"2022-11-01","arxiv_id":"2211.00288","code_links":[{"title":"tongkunguan/ccd","url":"https://github.com/tongkunguan/ccd"}],"syntology":null}},{"leaderboard":"/sota/self-supervised-scene-text-recognition-on-1","slug":"self-supervised-scene-text-recognition-on-1","dataset":"TextSeg","dataset_url":"/dataset/textseg","rows_in_archive":1,"metrics":["IoU (%)"],"first_row_in_archive_order":{"model":"CCD-ViT-Small","paper_title":"Self-supervised Character-to-Character Distillation for Text Recognition","paper_url":"/paper/self-supervised-character-to-character","paper_date":"2022-11-01","arxiv_id":"2211.00288","code_links":[{"title":"tongkunguan/ccd","url":"https://github.com/tongkunguan/ccd"}],"syntology":null}},{"leaderboard":"/sota/self-supervised-scene-text-recognition-on-2","slug":"self-supervised-scene-text-recognition-on-2","dataset":"Scene Text Recognition Benchmarks","dataset_url":null,"rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"CCD-ViT-Small","paper_title":"Self-supervised Character-to-Character Distillation for Text Recognition","paper_url":"/paper/self-supervised-character-to-character","paper_date":"2022-11-01","arxiv_id":"2211.00288","code_links":[{"title":"tongkunguan/ccd","url":"https://github.com/tongkunguan/ccd"}],"syntology":null}}],"datasets":[{"url":"/dataset/textzoom","name":"TextZoom","full_name":null,"num_papers_in_archive":28},{"url":"/dataset/textseg","name":"TextSeg","full_name":null,"num_papers_in_archive":16}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":2,"items":[{"url":"/paper/linguistics-aware-masked-image-modeling-for","title":"Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition","date":"2025-03-24","arxiv_id":"2503.18746","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":6}},{"url":"/paper/self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","arxiv_id":"2211.00288","repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}