{"url":"/task/table-recognition","name":"Table Recognition","slug":"table-recognition","description_markdown":"Table recognition refers to the process of automatically identifying and extracting tabular structures from unstructured data sources such as text documents, images, or scanned documents. The goal of table recognition is to accurately detect the presence of tables within the data and extract their contents, including rows, columns, headers, and cell values.","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":50,"papers_with_code":28,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/table-recognition-on-pubtabnet","slug":"table-recognition-on-pubtabnet","dataset":"PubTabNet","dataset_url":"/dataset/pubtabnet","rows_in_archive":13,"metrics":["TEDS (all samples)","TEDS-Struct"],"first_row_in_archive_order":{"model":"MuTabNet","paper_title":"Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition","paper_url":"/paper/multi-cell-decoder-and-mutual-learning-for","paper_date":"2024-04-20","arxiv_id":"2404.13268","code_links":[{"title":"JG1VPP/MuTabNet","url":"https://github.com/JG1VPP/MuTabNet"}],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-table-recognition","slug":"table-recognition-on-table-recognition","dataset":"Table Recognition Challenge mini-test","dataset_url":null,"rows_in_archive":4,"metrics":["TEDS (all samples)","TEDS (simple samples)","TEDS (complex samples)"],"first_row_in_archive_order":{"model":"Re0","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-table-recognition-2","slug":"table-recognition-on-table-recognition-2","dataset":"Table Recognition Challenge test","dataset_url":null,"rows_in_archive":2,"metrics":["TEDS (all samples)","TEDS (simple samples)","TEDS (complex samples)"],"first_row_in_archive_order":{"model":"Habitat-Web","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-icdar2013-table","slug":"table-recognition-on-icdar2013-table","dataset":"ICDAR2013 table structure recognition","dataset_url":null,"rows_in_archive":1,"metrics":["F-Measure"],"first_row_in_archive_order":{"model":"Proposed System (With post- processing)","paper_title":"Guided Table Structure Recognition through Anchor Optimization","paper_url":"/paper/guided-table-structure-recognition-through","paper_date":"2021-04-21","arxiv_id":"2104.10538","code_links":[],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-wtw","slug":"table-recognition-on-wtw","dataset":"WTW","dataset_url":"/dataset/wtw","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"StrucTexTv2 (small)","paper_title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","paper_url":"/paper/structextv2-masked-visual-textual-prediction","paper_date":"2023-03-01","arxiv_id":"2303.00289","code_links":[{"title":"PaddlePaddle/VIMER","url":"https://github.com/PaddlePaddle/VIMER/tree/main/StrucTexT/v2"}],"syntology":null}}],"datasets":[{"url":"/dataset/pubtabnet","name":"PubTabNet","full_name":"PubTabNet","num_papers_in_archive":51},{"url":"/dataset/fintabnet","name":"FinTabNet","full_name":"","num_papers_in_archive":35},{"url":"/dataset/wtw","name":"WTW","full_name":"Wired Table in the Wild","num_papers_in_archive":18},{"url":"/dataset/pubtables-1m","name":"PubTables-1M","full_name":"PubMed Tables One Million","num_papers_in_archive":15},{"url":"/dataset/tncr-dataset","name":"TNCR Dataset","full_name":"Table Net Detection and Classification Dataset","num_papers_in_archive":2},{"url":"/dataset/wikitableset","name":"WikiTableSet","full_name":"Wikipedia Table Image Dataset","num_papers_in_archive":2},{"url":"/dataset/cisol","name":"CISOL","full_name":"Construction Industry Steel Ordering Lists Dataset","num_papers_in_archive":1}],"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":28,"of":28,"tagged_in_all":50,"items":[{"url":"/paper/image-based-table-recognition-data-model-and","title":"Image-based table recognition: data, model, and evaluation","date":"2019-11-25","arxiv_id":"1911.10683","repositories_listed":6,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/rethinking-table-parsing-using-graph-neural","title":"Rethinking Table Recognition using Graph Neural Networks","date":"2019-05-31","arxiv_id":"1905.13391","repositories_listed":5,"syntology":null},{"url":"/paper/deep-learning-for-table-detection-and","title":"Deep learning for table detection and structure recognition: A survey","date":"2022-11-15","arxiv_id":"2211.08469","repositories_listed":3,"syntology":null},{"url":"/paper/icdar-2021-competition-on-scientific","title":"ICDAR 2021 Competition on Scientific Literature Parsing","date":"2021-06-08","arxiv_id":"2106.14616","repositories_listed":3,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/pingan-vcgroup-s-solution-for-icdar-2021","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","date":"2021-05-05","arxiv_id":"2105.01848","repositories_listed":3,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/cascadetabnet-an-approach-for-end-to-end","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","date":"2020-04-27","arxiv_id":"2004.12629","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/high-performance-transformers-for-table","title":"High-Performance Transformers for Table Structure Recognition Need Early Convolutions","date":"2023-11-09","arxiv_id":"2311.05565","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/an-end-to-end-multi-task-learning-model-for-1","title":"An End-to-End Multi-Task Learning Model for Image-based Table Recognition","date":"2023-03-15","arxiv_id":"2303.08648","repositories_listed":2,"syntology":null},{"url":"/paper/lore-logical-location-regression-network-for","title":"LORE: Logical Location Regression Network for Table Structure Recognition","date":"2023-03-07","arxiv_id":"2303.03730","repositories_listed":2,"syntology":null},{"url":"/paper/scientific-evidence-extraction","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","date":"2021-09-30","arxiv_id":"2110.00061","repositories_listed":2,"syntology":{"n":13,"n_ran":5,"n_unverified":8,"n_pointer_only":10}},{"url":"/paper/lgpma-complicated-table-structure-recognition","title":"LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment","date":"2021-05-13","arxiv_id":"2105.06224","repositories_listed":2,"syntology":null},{"url":"/paper/omniparser-v2-structured-points-of-thought","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","date":"2025-02-22","arxiv_id":"2502.16161","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-table-recognition-with-vision-llms","title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","date":"2024-12-30","arxiv_id":"2412.20662","repositories_listed":1,"syntology":null},{"url":"/paper/pdftable-a-unified-toolkit-for-deep-learning","title":"PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction","date":"2024-09-08","arxiv_id":"2409.05125","repositories_listed":1,"syntology":null},{"url":"/paper/multi-cell-decoder-and-mutual-learning-for","title":"Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition","date":"2024-04-20","arxiv_id":"2404.13268","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizing-realistic-data-for-table","title":"Synthesizing Realistic Data for Table Recognition","date":"2024-04-17","arxiv_id":"2404.11100","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-a-unified-framework-for-text","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","date":"2024-03-28","arxiv_id":"2403.19128","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/unitable-towards-a-unified-framework-for","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","date":"2024-03-07","arxiv_id":"2403.04822","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/omniparser-a-unified-framework-for-text-1","title":"OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-large-scale-dataset-for-end-to-end-table","title":"A large-scale dataset for end-to-end table recognition in the wild","date":"2023-03-27","arxiv_id":"2303.14884","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-image-based-table-recognition","title":"Rethinking Image-based Table Recognition Using Weakly Supervised Methods","date":"2023-03-14","arxiv_id":"2303.07641","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-benchmark-datasets-for-table","title":"Aligning benchmark datasets for table structure recognition","date":"2023-03-01","arxiv_id":"2303.00716","repositories_listed":1,"syntology":null},{"url":"/paper/pp-structurev2-a-stronger-document-analysis","title":"PP-StructureV2: A Stronger Document Analysis System","date":"2022-10-11","arxiv_id":"2210.05391","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-layout-templates-in-complex","title":"Detecting Layout Templates in Complex Multiregion Files","date":"2021-09-14","arxiv_id":"2109.06630","repositories_listed":1,"syntology":null},{"url":"/paper/tgrnet-a-table-graph-reconstruction-network","title":"TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition","date":"2021-06-20","arxiv_id":"2106.10598","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tab-iais-flexible-table-recognition-and","title":"Flexible Table Recognition and Semantic Interpretation System","date":"2021-05-25","arxiv_id":"2105.11879","repositories_listed":1,"syntology":null},{"url":"/paper/multi-type-td-tsr-extracting-tables-from","title":"Multi-Type-TD-TSR -- Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations","date":"2021-05-23","arxiv_id":"2105.11021","repositories_listed":1,"syntology":null},{"url":"/paper/table-structure-recognition-using-top-down-1","title":"Table Structure Recognition using Top-Down and Bottom-Up Cues","date":"2020-10-09","arxiv_id":"2010.04565","repositories_listed":1,"syntology":null}],"syntology_records":9,"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"}}