{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/msra-td500","name":"MSRA-TD500","full_name":"MSRA Text Detection 500 Database","description_markdown":"The **MSRA-TD500** dataset is a text detection dataset that contains 300 training images and 200 test images. Text regions are arbitrarily orientated and annotated at sentence level. Different from the other datasets, it contains both English and Chinese text.\r\n\r\nSource: [Detecting Text in the Wild with Deep Character Embedding Network](https://arxiv.org/abs/1901.00363)\r\nImage Source: [http://www.iapr-tc11.org/mediawiki/images/MSRA-TD500_Example.jpg](http://www.iapr-tc11.org/mediawiki/images/MSRA-TD500_Example.jpg)","description_withheld":null,"homepage":"http://www.iapr-tc11.org/mediawiki/index.php/MSRA_Text_Detection_500_Database_(MSRA-TD500)","introduced_date":"2012-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Detecting texts of arbitrary orientations in natural images","first_author":null,"url":"https://doi.org/10.1109/CVPR.2012.6247787"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Scene Text Detection","url":"/task/scene-text-detection","datasets_with_task":"/datasets/task/scene-text-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MSRA-TD500"],"data_loaders":[],"num_papers_in_archive":124,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset_variant":"MSRA-TD500","rows":18,"metrics":["F-Measure","Precision","Recall","FPS"],"first_row_in_archive_order":{"model":"MixNet","paper":"/paper/mixnet-toward-accurate-detection-of","metrics":{"F-Measure":"89.4","FPS":"15.2","Precision":"90.7","Recall":"88.1"},"code_links":[{"title":"D641593/MixNet","url":"https://github.com/D641593/MixNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":13,"of":13,"counts":{"papers_with_a_benchmark_row":13,"with_a_code_link":11,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/mixnet-toward-accurate-detection-of","slug":"mixnet-toward-accurate-detection-of","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","date":"2023-08-23","arxiv_id":"2308.12817","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-time-scene-text-detection-with-1","slug":"real-time-scene-text-detection-with-1","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","date":"2022-02-21","arxiv_id":"2202.10304","rows_on_this_dataset":3,"code_links":5,"syntology":null},{"paper":"/paper/fast-searching-for-a-faster-arbitrarily","slug":"fast-searching-for-a-faster-arbitrarily","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","date":"2021-11-03","arxiv_id":"2111.02394","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/real-time-scene-text-detection-with","slug":"real-time-scene-text-detection-with","title":"Real-time Scene Text Detection with Differentiable Binarization","date":"2019-11-20","arxiv_id":"1911.08947","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":1,"official":{"repos":["MhLiao/DB"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/real-time-scene-text-detection-with#ran","syntology_url":"https://syntology.ai/paper/1911.08947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08947"}}}},{"paper":"/paper/efficient-and-accurate-arbitrary-shaped-text","slug":"efficient-and-accurate-arbitrary-shaped-text","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","date":"2019-08-16","arxiv_id":"1908.05900","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":28,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":4,"samples_unverified":11,"pointer_only_for_licence":2,"official":{"repos":["whai362/pan_pp.pytorch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-and-accurate-arbitrary-shaped-text#ran","syntology_url":"https://syntology.ai/paper/1908.05900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.05900"}}}},{"paper":"/paper/character-region-awareness-for-text-detection","slug":"character-region-awareness-for-text-detection","title":"Character Region Awareness for Text Detection","date":"2019-04-03","arxiv_id":"1904.01941","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":5,"samples_unverified":15,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/character-region-awareness-for-text-detection#ran","syntology_url":"https://syntology.ai/paper/1904.01941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01941"}}}},{"paper":"/paper/textsnake-a-flexible-representation-for","slug":"textsnake-a-flexible-representation-for","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","date":"2018-07-04","arxiv_id":"1807.01544","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textsnake-a-flexible-representation-for#ran","syntology_url":"https://syntology.ai/paper/1807.01544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.01544"}}}},{"paper":"/paper/rotation-sensitive-regression-for-oriented","slug":"rotation-sensitive-regression-for-oriented","title":"Rotation-Sensitive Regression for Oriented Scene Text Detection","date":"2018-03-14","arxiv_id":"1803.05265","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-oriented-scene-text-detection-via","slug":"multi-oriented-scene-text-detection-via","title":"Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation","date":"2018-02-25","arxiv_id":"1802.08948","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pixellink-detecting-scene-text-via-instance","slug":"pixellink-detecting-scene-text-via-instance","title":"PixelLink: Detecting Scene Text via Instance Segmentation","date":"2018-01-04","arxiv_id":"1801.01315","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/fused-text-segmentation-networks-for-multi","slug":"fused-text-segmentation-networks-for-multi","title":"Fused Text Segmentation Networks for Multi-oriented Scene Text Detection","date":"2017-09-11","arxiv_id":"1709.03272","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/east-an-efficient-and-accurate-scene-text","slug":"east-an-efficient-and-accurate-scene-text","title":"EAST: An Efficient and Accurate Scene Text Detector","date":"2017-04-11","arxiv_id":"1704.03155","rows_on_this_dataset":1,"code_links":31,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/east-an-efficient-and-accurate-scene-text#ran","syntology_url":"https://syntology.ai/paper/1704.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03155"}}}},{"paper":"/paper/detecting-oriented-text-in-natural-images-by","slug":"detecting-oriented-text-in-natural-images-by","title":"Detecting Oriented Text in Natural Images by Linking Segments","date":"2017-03-19","arxiv_id":"1703.06520","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/detecting-oriented-text-in-natural-images-by#ran","syntology_url":"https://syntology.ai/paper/1703.06520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06520"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/mixnet-toward-accurate-detection-of","slug":"mixnet-toward-accurate-detection-of","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","date":"2023-08-23","arxiv_id":"2308.12817","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-time-scene-text-detection-with-1","slug":"real-time-scene-text-detection-with-1","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","date":"2022-02-21","arxiv_id":"2202.10304","rows_on_this_dataset":3,"code_links":5,"syntology":null},{"paper":"/paper/fast-searching-for-a-faster-arbitrarily","slug":"fast-searching-for-a-faster-arbitrarily","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","date":"2021-11-03","arxiv_id":"2111.02394","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/real-time-scene-text-detection-with","slug":"real-time-scene-text-detection-with","title":"Real-time Scene Text Detection with Differentiable Binarization","date":"2019-11-20","arxiv_id":"1911.08947","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":1,"official":{"repos":["MhLiao/DB"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/real-time-scene-text-detection-with#ran","syntology_url":"https://syntology.ai/paper/1911.08947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08947"}}}},{"paper":"/paper/efficient-and-accurate-arbitrary-shaped-text","slug":"efficient-and-accurate-arbitrary-shaped-text","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","date":"2019-08-16","arxiv_id":"1908.05900","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":28,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":4,"samples_unverified":11,"pointer_only_for_licence":2,"official":{"repos":["whai362/pan_pp.pytorch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-and-accurate-arbitrary-shaped-text#ran","syntology_url":"https://syntology.ai/paper/1908.05900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.05900"}}}},{"paper":"/paper/character-region-awareness-for-text-detection","slug":"character-region-awareness-for-text-detection","title":"Character Region Awareness for Text Detection","date":"2019-04-03","arxiv_id":"1904.01941","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":5,"samples_unverified":15,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/character-region-awareness-for-text-detection#ran","syntology_url":"https://syntology.ai/paper/1904.01941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01941"}}}},{"paper":"/paper/textsnake-a-flexible-representation-for","slug":"textsnake-a-flexible-representation-for","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","date":"2018-07-04","arxiv_id":"1807.01544","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/textsnake-a-flexible-representation-for#ran","syntology_url":"https://syntology.ai/paper/1807.01544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.01544"}}}},{"paper":"/paper/rotation-sensitive-regression-for-oriented","slug":"rotation-sensitive-regression-for-oriented","title":"Rotation-Sensitive Regression for Oriented Scene Text Detection","date":"2018-03-14","arxiv_id":"1803.05265","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-oriented-scene-text-detection-via","slug":"multi-oriented-scene-text-detection-via","title":"Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation","date":"2018-02-25","arxiv_id":"1802.08948","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pixellink-detecting-scene-text-via-instance","slug":"pixellink-detecting-scene-text-via-instance","title":"PixelLink: Detecting Scene Text via Instance Segmentation","date":"2018-01-04","arxiv_id":"1801.01315","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/fused-text-segmentation-networks-for-multi","slug":"fused-text-segmentation-networks-for-multi","title":"Fused Text Segmentation Networks for Multi-oriented Scene Text Detection","date":"2017-09-11","arxiv_id":"1709.03272","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/east-an-efficient-and-accurate-scene-text","slug":"east-an-efficient-and-accurate-scene-text","title":"EAST: An Efficient and Accurate Scene Text Detector","date":"2017-04-11","arxiv_id":"1704.03155","rows_on_this_dataset":1,"code_links":31,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/east-an-efficient-and-accurate-scene-text#ran","syntology_url":"https://syntology.ai/paper/1704.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03155"}}}},{"paper":"/paper/detecting-oriented-text-in-natural-images-by","slug":"detecting-oriented-text-in-natural-images-by","title":"Detecting Oriented Text in Natural Images by Linking Segments","date":"2017-03-19","arxiv_id":"1703.06520","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/detecting-oriented-text-in-natural-images-by#ran","syntology_url":"https://syntology.ai/paper/1703.06520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06520"}}}}],"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/dataset/msra-td500/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/msra-td500/papers/ran/1","json":"/dataset/msra-td500/papers/ran/1.json","rows":6}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":6,"samples_harvested":106,"samples_ran":74,"samples_constructed":0,"samples_ran_checked":55,"samples_ran_instrument_failed":19,"samples_unverified":32,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":6,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":2,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"90a035795821a2b4315c605d93a232f9326ecf3959aea2d9dddd826873b2ec7c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}